Search

Large language models (LLMs) excel in various tasks but are primarily trained on text data, limiting their application scope. Expanding LLM capabilities to include vision-language understanding is vital, yet training them on multimodal data from scratch is challenging and costly. Existing instruction tuning methods, e.g., LLAVA, often connects a pretrained CLIP vision encoder and LLMs via fully fine-tuning LLMs to bridge the modality gap. However, full fine-tuning is plagued by catastrophic forgetting, i.e., forgetting previous knowledge, and high training costs particularly in the era of increasing tasks and modalities. To solve this issue, we introduce MoExtend, an effective framework designed to streamline the modality adaptation and extension of Mixture-of-Experts (MoE) models. MoExtend seamlessly integrates new experts into pre-trained MoE models, endowing them with novel knowledge without the need to tune pretrained models such as MoE and vision encoders. This approach enables rapid adaptation and extension to new modal data or tasks, effectively addressing the challenge of accommodating new modalities within LLMs. Furthermore, MoExtend avoids tuning pretrained models, thus mitigating the risk of catastrophic forgetting. Experimental results demonstrate the efficacy and efficiency of MoExtend in enhancing the multimodal capabilities of LLMs, contributing to advancements in multimodal AI research. Code: https://github.com/zhongshsh/MoExtend., Comment: ACL 2024 - SRW

With the significant development of large models in recent years, Large Vision-Language Models (LVLMs) have demonstrated remarkable capabilities across a wide range of multimodal understanding and reasoning tasks. Compared to traditional Large Language Models (LLMs), LVLMs present great potential and challenges due to its closer proximity to the multi-resource real-world applications and the complexity of multi-modal processing. However, the vulnerability of LVLMs is relatively underexplored, posing potential security risks in daily usage. In this paper, we provide a comprehensive review of the various forms of existing LVLM attacks. Specifically, we first introduce the background of attacks targeting LVLMs, including the attack preliminary, attack challenges, and attack resources. Then, we systematically review the development of LVLM attack methods, such as adversarial attacks that manipulate model outputs, jailbreak attacks that exploit model vulnerabilities for unauthorized actions, prompt injection attacks that engineer the prompt type and pattern, and data poisoning that affects model training. Finally, we discuss promising research directions in the future. We believe that our survey provides insights into the current landscape of LVLM vulnerabilities, inspiring more researchers to explore and mitigate potential safety issues in LVLM developments. The latest papers on LVLM attacks are continuously collected in https://github.com/liudaizong/Awesome-LVLM-Attack.

Recently, Multimodal Large Language Models (MLLMs) have been used as agents to control keyboard and mouse inputs by directly perceiving the Graphical User Interface (GUI) and generating corresponding code. However, current agents primarily exhibit excellent understanding capabilities in static environments and are predominantly applied in relatively simple domains, such as Web or mobile interfaces. We argue that a robust GUI agent should be capable of perceiving temporal information on the GUI, including dynamic Web content and multi-step tasks. Additionally, it should possess a comprehensive understanding of various GUI scenarios, including desktop software and multi-window interactions. To this end, this paper introduces a new dataset, termed GUI-World, which features meticulously crafted Human-MLLM annotations, extensively covering six GUI scenarios and eight types of GUI-oriented questions in three formats. We evaluate the capabilities of current state-of-the-art MLLMs, including ImageLLMs and VideoLLMs, in understanding various types of GUI content, especially dynamic and sequential content. Our findings reveal that ImageLLMs struggle with dynamic GUI content without manually annotated keyframes or operation history. On the other hand, VideoLLMs fall short in all GUI-oriented tasks given the sparse GUI video dataset. Based on GUI-World, we take the initial step of leveraging a fine-tuned VideoLLM as a GUI agent, demonstrating an improved understanding of various GUI tasks. However, due to the limitations in the performance of base LLMs, we conclude that using VideoLLMs as GUI agents remains a significant challenge. We believe our work provides valuable insights for future research in dynamic GUI content understanding. The code and dataset are publicly available at our project homepage: https://gui-world.github.io/.

Recent 3D large reconstruction models (LRMs) can generate high-quality 3D content in sub-seconds by integrating multi-view diffusion models with scalable multi-view reconstructors. Current works further leverage 3D Gaussian Splatting as 3D representation for improved visual quality and rendering efficiency. However, we observe that existing Gaussian reconstruction models often suffer from multi-view inconsistency and blurred textures. We attribute this to the compromise of multi-view information propagation in favor of adopting powerful yet computationally intensive architectures (e.g., Transformers). To address this issue, we introduce MVGamba, a general and lightweight Gaussian reconstruction model featuring a multi-view Gaussian reconstructor based on the RNN-like State Space Model (SSM). Our Gaussian reconstructor propagates causal context containing multi-view information for cross-view self-refinement while generating a long sequence of Gaussians for fine-detail modeling with linear complexity. With off-the-shelf multi-view diffusion models integrated, MVGamba unifies 3D generation tasks from a single image, sparse images, or text prompts. Extensive experiments demonstrate that MVGamba outperforms state-of-the-art baselines in all 3D content generation scenarios with approximately only $0.1\times$ of the model size.

Question answering, asking, and assessment are three innate human traits crucial for understanding the world and acquiring knowledge. By enhancing these capabilities, humans can more effectively utilize data, leading to better comprehension and learning outcomes. However, current Multimodal Large Language Models (MLLMs) primarily focus on question answering, often neglecting the full potential of questioning and assessment skills. In this study, we introduce LOVA3, an innovative framework named ``Learning tO Visual Question Answering, Asking and Assessment,'' designed to equip MLLMs with these additional capabilities. Our approach involves the creation of two supplementary training tasks GenQA and EvalQA, aiming at fostering the skills of asking and assessing questions in the context of images. To develop the questioning ability, we compile a comprehensive set of multimodal foundational tasks. For assessment, we introduce a new benchmark called EvalQABench, comprising 64,000 training samples (split evenly between positive and negative samples) and 5,000 testing samples. We posit that enhancing MLLMs with the capabilities to answer, ask, and assess questions will improve their multimodal comprehension and lead to better performance. We validate our hypothesis by training an MLLM using the LOVA3 framework and testing it on 10 multimodal benchmarks. The results demonstrate consistent performance improvements, thereby confirming the efficacy of our approach., Comment: The code is available at https://github.com/showlab/LOVA3

Backdoor attacks have been well-studied in visible light object detection (VLOD) in recent years. However, VLOD can not effectively work in dark and temperature-sensitive scenarios. Instead, thermal infrared object detection (TIOD) is the most accessible and practical in such environments. In this paper, our team is the first to investigate the security vulnerabilities associated with TIOD in the context of backdoor attacks, spanning both the digital and physical realms. We introduce two novel types of backdoor attacks on TIOD, each offering unique capabilities: Object-affecting Attack and Range-affecting Attack. We conduct a comprehensive analysis of key factors influencing trigger design, which include temperature, size, material, and concealment. These factors, especially temperature, significantly impact the efficacy of backdoor attacks on TIOD. A thorough understanding of these factors will serve as a foundation for designing physical triggers and temperature controlling experiments. Our study includes extensive experiments conducted in both digital and physical environments. In the digital realm, we evaluate our approach using benchmark datasets for TIOD, achieving an Attack Success Rate (ASR) of up to 98.21%. In the physical realm, we test our approach in two real-world settings: a traffic intersection and a parking lot, using a thermal infrared camera. Here, we attain an ASR of up to 98.38%., Comment: To appear in CVPR 2024.11pages, 8 figures and 4 tables

Score distillation sampling~(SDS) has been widely adopted to overcome the absence of unseen views in reconstructing 3D objects from a \textbf{single} image. It leverages pre-trained 2D diffusion models as teacher to guide the reconstruction of student 3D models. Despite their remarkable success, SDS-based methods often encounter geometric artifacts and texture saturation. We find out the crux is the overlooked indiscriminate treatment of diffusion time-steps during optimization: it unreasonably treats the student-teacher knowledge distillation to be equal at all time-steps and thus entangles coarse-grained and fine-grained modeling. Therefore, we propose the Diffusion Time-step Curriculum one-image-to-3D pipeline (DTC123), which involves both the teacher and student models collaborating with the time-step curriculum in a coarse-to-fine manner. Extensive experiments on NeRF4, RealFusion15, GSO and Level50 benchmark demonstrate that DTC123 can produce multi-view consistent, high-quality, and diverse 3D assets. Codes and more generation demos will be released in https://github.com/yxymessi/DTC123., Comment: Accepted to CVPR 2024

We tackle the challenge of efficiently reconstructing a 3D asset from a single image at millisecond speed. Existing methods for single-image 3D reconstruction are primarily based on Score Distillation Sampling (SDS) with Neural 3D representations. Despite promising results, these approaches encounter practical limitations due to lengthy optimizations and significant memory consumption. In this work, we introduce Gamba, an end-to-end 3D reconstruction model from a single-view image, emphasizing two main insights: (1) Efficient Backbone Design: introducing a Mamba-based GambaFormer network to model 3D Gaussian Splatting (3DGS) reconstruction as sequential prediction with linear scalability of token length, thereby accommodating a substantial number of Gaussians; (2) Robust Gaussian Constraints: deriving radial mask constraints from multi-view masks to eliminate the need for warmup supervision of 3D point clouds in training. We trained Gamba on Objaverse and assessed it against existing optimization-based and feed-forward 3D reconstruction approaches on the GSO Dataset, among which Gamba is the only end-to-end trained single-view reconstruction model with 3DGS. Experimental results demonstrate its competitive generation capabilities both qualitatively and quantitatively and highlight its remarkable speed: Gamba completes reconstruction within 0.05 seconds on a single NVIDIA A100 GPU, which is about $1,000\times$ faster than optimization-based methods. Please see our project page at https://florinshen.github.io/gamba-project., Comment: project page: https://florinshen.github.io/gamba-project

Multi-agent perception (MAP) allows autonomous systems to understand complex environments by interpreting data from multiple sources. This paper investigates intermediate collaboration for MAP with a specific focus on exploring "good" properties of collaborative view (i.e., post-collaboration feature) and its underlying relationship to individual views (i.e., pre-collaboration features), which were treated as an opaque procedure by most existing works. We propose a novel framework named CMiMC (Contrastive Mutual Information Maximization for Collaborative Perception) for intermediate collaboration. The core philosophy of CMiMC is to preserve discriminative information of individual views in the collaborative view by maximizing mutual information between pre- and post-collaboration features while enhancing the efficacy of collaborative views by minimizing the loss function of downstream tasks. In particular, we define multi-view mutual information (MVMI) for intermediate collaboration that evaluates correlations between collaborative views and individual views on both global and local scales. We establish CMiMNet based on multi-view contrastive learning to realize estimation and maximization of MVMI, which assists the training of a collaboration encoder for voxel-level feature fusion. We evaluate CMiMC on V2X-Sim 1.0, and it improves the SOTA average precision by 3.08% and 4.44% at 0.5 and 0.7 IoU (Intersection-over-Union) thresholds, respectively. In addition, CMiMC can reduce communication volume to 1/32 while achieving performance comparable to SOTA. Code and Appendix are released at https://github.com/77SWF/CMiMC.

Even when using large multi-modal foundation models, few-shot learning is still challenging -- if there is no proper inductive bias, it is nearly impossible to keep the nuanced class attributes while removing the visually prominent attributes that spuriously correlate with class labels. To this end, we find an inductive bias that the time-steps of a Diffusion Model (DM) can isolate the nuanced class attributes, i.e., as the forward diffusion adds noise to an image at each time-step, nuanced attributes are usually lost at an earlier time-step than the spurious attributes that are visually prominent. Building on this, we propose Time-step Few-shot (TiF) learner. We train class-specific low-rank adapters for a text-conditioned DM to make up for the lost attributes, such that images can be accurately reconstructed from their noisy ones given a prompt. Hence, at a small time-step, the adapter and prompt are essentially a parameterization of only the nuanced class attributes. For a test image, we can use the parameterization to only extract the nuanced class attributes for classification. TiF learner significantly outperforms OpenCLIP and its adapters on a variety of fine-grained and customized few-shot learning tasks. Codes are in https://github.com/yue-zhongqi/tif., Comment: Accepted by CVPR 2024

Multimodal Large Language Models (MLLMs) have gained significant attention recently, showing remarkable potential in artificial general intelligence. However, assessing the utility of MLLMs presents considerable challenges, primarily due to the absence of multimodal benchmarks that align with human preferences. Drawing inspiration from the concept of LLM-as-a-Judge within LLMs, this paper introduces a novel benchmark, termed MLLM-as-a-Judge, to assess the ability of MLLMs in assisting judges across diverse modalities, encompassing three distinct tasks: Scoring Evaluation, Pair Comparison, and Batch Ranking. Our study reveals that, while MLLMs demonstrate remarkable human-like discernment in Pair Comparison, there is a significant divergence from human preferences in Scoring Evaluation and Batch Ranking. Furthermore, a closer examination reveals persistent challenges in the judgment capacities of LLMs, including diverse biases, hallucinatory responses, and inconsistencies in judgment, even in advanced models such as GPT-4V. These findings emphasize the pressing need for enhancements and further research efforts to be undertaken before regarding MLLMs as fully reliable evaluators. In light of this, we advocate for additional efforts dedicated to supporting the continuous development within the domain of MLLM functioning as judges. The code and dataset are publicly available at our project homepage: \url{https://mllm-judge.github.io/}., Comment: ICML 2024 (Oral)

Score distillation sampling (SDS) and its variants have greatly boosted the development of text-to-3D generation, but are vulnerable to geometry collapse and poor textures yet. To solve this issue, we first deeply analyze the SDS and find that its distillation sampling process indeed corresponds to the trajectory sampling of a stochastic differential equation (SDE): SDS samples along an SDE trajectory to yield a less noisy sample which then serves as a guidance to optimize a 3D model. However, the randomness in SDE sampling often leads to a diverse and unpredictable sample which is not always less noisy, and thus is not a consistently correct guidance, explaining the vulnerability of SDS. Since for any SDE, there always exists an ordinary differential equation (ODE) whose trajectory sampling can deterministically and consistently converge to the desired target point as the SDE, we propose a novel and effective "Consistent3D" method that explores the ODE deterministic sampling prior for text-to-3D generation. Specifically, at each training iteration, given a rendered image by a 3D model, we first estimate its desired 3D score function by a pre-trained 2D diffusion model, and build an ODE for trajectory sampling. Next, we design a consistency distillation sampling loss which samples along the ODE trajectory to generate two adjacent samples and uses the less noisy sample to guide another more noisy one for distilling the deterministic prior into the 3D model. Experimental results show the efficacy of our Consistent3D in generating high-fidelity and diverse 3D objects and large-scale scenes, as shown in Fig. 1. The codes are available at https://github.com/sail-sg/Consistent3D., Comment: Accepted to CVPR 2024

Multimodal Large Language Models (MLLMs) demonstrate exceptional problem-solving capabilities, but few research studies aim to gauge the ability to generate visual instruction tuning data. This paper proposes to explore the potential of empowering MLLMs to generate data independently without relying on GPT-4. We introduce Genixer, a comprehensive data generation pipeline consisting of four key steps: (i) instruction data collection, (ii) instruction template design, (iii) empowering MLLMs, and (iv) data generation and filtering. Additionally, we outline two modes of data generation: task-agnostic and task-specific, enabling controllable output. We demonstrate that a synthetic VQA-like dataset trained with LLaVA1.5 enhances performance on 10 out of 12 multimodal benchmarks. Additionally, the grounding MLLM Shikra, when trained with a REC-like synthetic dataset, shows improvements on 7 out of 8 REC datasets. Through experiments and synthetic data analysis, our findings are: (1) current MLLMs can serve as robust data generators without assistance from GPT-4V; (2) MLLMs trained with task-specific datasets can surpass GPT-4V in generating complex instruction tuning data; (3) synthetic datasets enhance performance across various multimodal benchmarks and help mitigate model hallucinations. The data, code, and models can be found at https://github.com/zhaohengyuan1/Genixer., Comment: Accepted by ECCV 2024

Chain-of-Thought (CoT) guides large language models (LLMs) to reason step-by-step, and can motivate their logical reasoning ability. While effective for logical tasks, CoT is not conducive to creative problem-solving which often requires out-of-box thoughts and is crucial for innovation advancements. In this paper, we explore the Leap-of-Thought (LoT) abilities within LLMs -- a non-sequential, creative paradigm involving strong associations and knowledge leaps. To this end, we study LLMs on the popular Oogiri game which needs participants to have good creativity and strong associative thinking for responding unexpectedly and humorously to the given image, text, or both, and thus is suitable for LoT study. Then to investigate LLMs' LoT ability in the Oogiri game, we first build a multimodal and multilingual Oogiri-GO dataset which contains over 130,000 samples from the Oogiri game, and observe the insufficient LoT ability or failures of most existing LLMs on the Oogiri game. Accordingly, we introduce a creative Leap-of-Thought (CLoT) paradigm to improve LLM's LoT ability. CLoT first formulates the Oogiri-GO dataset into LoT-oriented instruction tuning data to train pretrained LLM for achieving certain LoT humor generation and discrimination abilities. Then CLoT designs an explorative self-refinement that encourages the LLM to generate more creative LoT data via exploring parallels between seemingly unrelated concepts and selects high-quality data to train itself for self-refinement. CLoT not only excels in humor generation in the Oogiri game but also boosts creative abilities in various tasks like cloud guessing game and divergent association task. These findings advance our understanding and offer a pathway to improve LLMs' creative capacities for innovative applications across domains. The dataset, code, and models will be released online. https://zhongshsh.github.io/CLoT/., Comment: Technical report

Text-to-image diffusion models allow seamless generation of personalized images from scant reference photos. Yet, these tools, in the wrong hands, can fabricate misleading or harmful content, endangering individuals. To address this problem, existing poisoning-based approaches perturb user images in an imperceptible way to render them "unlearnable" from malicious uses. We identify two limitations of these defending approaches: i) sub-optimal due to the hand-crafted heuristics for solving the intractable bilevel optimization and ii) lack of robustness against simple data transformations like Gaussian filtering. To solve these challenges, we propose MetaCloak, which solves the bi-level poisoning problem with a meta-learning framework with an additional transformation sampling process to craft transferable and robust perturbation. Specifically, we employ a pool of surrogate diffusion models to craft transferable and model-agnostic perturbation. Furthermore, by incorporating an additional transformation process, we design a simple denoising-error maximization loss that is sufficient for causing transformation-robust semantic distortion and degradation in a personalized generation. Extensive experiments on the VGGFace2 and CelebA-HQ datasets show that MetaCloak outperforms existing approaches. Notably, MetaCloak can successfully fool online training services like Replicate, in a black-box manner, demonstrating the effectiveness of MetaCloak in real-world scenarios. Our code is available at https://github.com/liuyixin-louis/MetaCloak., Comment: Accepted to CVPR 2024 (Oral)

Text-to-3D generation has attracted much attention from the computer vision community. Existing methods mainly optimize a neural field from scratch for each text prompt, relying on heavy and repetitive training cost which impedes their practical deployment. In this paper, we propose a novel framework for fast text-to-3D generation, dubbed Instant3D. Once trained, Instant3D is able to create a 3D object for an unseen text prompt in less than one second with a single run of a feedforward network. We achieve this remarkable speed by devising a new network that directly constructs a 3D triplane from a text prompt. The core innovation of our Instant3D lies in our exploration of strategies to effectively inject text conditions into the network. In particular, we propose to combine three key mechanisms: cross-attention, style injection, and token-to-plane transformation, which collectively ensure precise alignment of the output with the input text. Furthermore, we propose a simple yet effective activation function, the scaled-sigmoid, to replace the original sigmoid function, which speeds up the training convergence by more than ten times. Finally, to address the Janus (multi-head) problem in 3D generation, we propose an adaptive Perp-Neg algorithm that can dynamically adjust its concept negation scales according to the severity of the Janus problem during training, effectively reducing the multi-head effect. Extensive experiments on a wide variety of benchmark datasets demonstrate that the proposed algorithm performs favorably against the state-of-the-art methods both qualitatively and quantitatively, while achieving significantly better efficiency. The code, data, and models are available at https://github.com/ming1993li/Instant3DCodes., Comment: Project page: https://ming1993li.github.io/Instant3DProj

Deep neural networks (DNNs) are vulnerable to adversarial examples crafted by well-designed perturbations. This could lead to disastrous results on critical applications such as self-driving cars, surveillance security, and medical diagnosis. At present, adversarial training is one of the most effective defenses against adversarial examples. However, traditional adversarial training makes it difficult to achieve a good trade-off between clean accuracy and robustness since spurious features are still learned by DNNs. The intrinsic reason is that traditional adversarial training makes it difficult to fully learn core features from adversarial examples when adversarial noise and clean examples cannot be disentangled. In this paper, we disentangle the adversarial examples into natural and perturbed patterns by bit-plane slicing. We assume the higher bit-planes represent natural patterns and the lower bit-planes represent perturbed patterns, respectively. We propose a Feature-Focusing Adversarial Training (F$^2$AT), which differs from previous work in that it enforces the model to focus on the core features from natural patterns and reduce the impact of spurious features from perturbed patterns. The experimental results demonstrated that F$^2$AT outperforms state-of-the-art methods in clean accuracy and adversarial robustness.

In diffusion models, UNet is the most popular network backbone, since its long skip connects (LSCs) to connect distant network blocks can aggregate long-distant information and alleviate vanishing gradient. Unfortunately, UNet often suffers from unstable training in diffusion models which can be alleviated by scaling its LSC coefficients smaller. However, theoretical understandings of the instability of UNet in diffusion models and also the performance improvement of LSC scaling remain absent yet. To solve this issue, we theoretically show that the coefficients of LSCs in UNet have big effects on the stableness of the forward and backward propagation and robustness of UNet. Specifically, the hidden feature and gradient of UNet at any layer can oscillate and their oscillation ranges are actually large which explains the instability of UNet training. Moreover, UNet is also provably sensitive to perturbed input, and predicts an output distant from the desired output, yielding oscillatory loss and thus oscillatory gradient. Besides, we also observe the theoretical benefits of the LSC coefficient scaling of UNet in the stableness of hidden features and gradient and also robustness. Finally, inspired by our theory, we propose an effective coefficient scaling framework ScaleLong that scales the coefficients of LSC in UNet and better improves the training stability of UNet. Experimental results on four famous datasets show that our methods are superior to stabilize training and yield about 1.5x training acceleration on different diffusion models with UNet or UViT backbones. Code: https://github.com/sail-sg/ScaleLong, Comment: accepted by NeurIPS 2023

With the maturity of depth sensors, the vulnerability of 3D point cloud models has received increasing attention in various applications such as autonomous driving and robot navigation. Previous 3D adversarial attackers either follow the white-box setting to iteratively update the coordinate perturbations based on gradients, or utilize the output model logits to estimate noisy gradients in the black-box setting. However, these attack methods are hard to be deployed in real-world scenarios since realistic 3D applications will not share any model details to users. Therefore, we explore a more challenging yet practical 3D attack setting, \textit{i.e.}, attacking point clouds with black-box hard labels, in which the attacker can only have access to the prediction label of the input. To tackle this setting, we propose a novel 3D attack method, termed \textbf{3D} \textbf{H}ard-label att\textbf{acker} (\textbf{3DHacker}), based on the developed decision boundary algorithm to generate adversarial samples solely with the knowledge of class labels. Specifically, to construct the class-aware model decision boundary, 3DHacker first randomly fuses two point clouds of different classes in the spectral domain to craft their intermediate sample with high imperceptibility, then projects it onto the decision boundary via binary search. To restrict the final perturbation size, 3DHacker further introduces an iterative optimization strategy to move the intermediate sample along the decision boundary for generating adversarial point clouds with smallest trivial perturbations. Extensive evaluations show that, even in the challenging hard-label setting, 3DHacker still competitively outperforms existing 3D attacks regarding the attack performance as well as adversary quality., Comment: Accepted by ICCV 2023

Diffusion models (DMs) have been adopted across diverse fields with its remarkable abilities in capturing intricate data distributions. In this paper, we propose a Fast Diffusion Model (FDM) to significantly speed up DMs from a stochastic optimization perspective for both faster training and sampling. We first find that the diffusion process of DMs accords with the stochastic optimization process of stochastic gradient descent (SGD) on a stochastic time-variant problem. Then, inspired by momentum SGD that uses both gradient and an extra momentum to achieve faster and more stable convergence than SGD, we integrate momentum into the diffusion process of DMs. This comes with a unique challenge of deriving the noise perturbation kernel from the momentum-based diffusion process. To this end, we frame the process as a Damped Oscillation system whose critically damped state -- the kernel solution -- avoids oscillation and yields a faster convergence speed of the diffusion process. Empirical results show that our FDM can be applied to several popular DM frameworks, e.g., VP, VE, and EDM, and reduces their training cost by about 50% with comparable image synthesis performance on CIFAR-10, FFHQ, and AFHQv2 datasets. Moreover, FDM decreases their sampling steps by about 3x to achieve similar performance under the same samplers. The code is available at https://github.com/sail-sg/FDM.

This paper addresses the temporal sentence grounding (TSG). Although existing methods have made decent achievements in this task, they not only severely rely on abundant video-query paired data for training, but also easily fail into the dataset distribution bias. To alleviate these limitations, we introduce a novel Equivariant Consistency Regulation Learning (ECRL) framework to learn more discriminative query-related frame-wise representations for each video, in a self-supervised manner. Our motivation comes from that the temporal boundary of the query-guided activity should be consistently predicted under various video-level transformations. Concretely, we first design a series of spatio-temporal augmentations on both foreground and background video segments to generate a set of synthetic video samples. In particular, we devise a self-refine module to enhance the completeness and smoothness of the augmented video. Then, we present a novel self-supervised consistency loss (SSCL) applied on the original and augmented videos to capture their invariant query-related semantic by minimizing the KL-divergence between the sequence similarity of two videos and a prior Gaussian distribution of timestamp distance. At last, a shared grounding head is introduced to predict the transform-equivariant query-guided segment boundaries for both the original and augmented videos. Extensive experiments on three challenging datasets (ActivityNet, TACoS, and Charades-STA) demonstrate both effectiveness and efficiency of our proposed ECRL framework.

Inspired by the long-range modeling ability of ViTs, large-kernel convolutions are widely studied and adopted recently to enlarge the receptive field and improve model performance, like the remarkable work ConvNeXt which employs 7x7 depthwise convolution. Although such depthwise operator only consumes a few FLOPs, it largely harms the model efficiency on powerful computing devices due to the high memory access costs. For example, ConvNeXt-T has similar FLOPs with ResNet-50 but only achieves 60% throughputs when trained on A100 GPUs with full precision. Although reducing the kernel size of ConvNeXt can improve speed, it results in significant performance degradation. It is still unclear how to speed up large-kernel-based CNN models while preserving their performance. To tackle this issue, inspired by Inceptions, we propose to decompose large-kernel depthwise convolution into four parallel branches along channel dimension, i.e. small square kernel, two orthogonal band kernels, and an identity mapping. With this new Inception depthwise convolution, we build a series of networks, namely IncepitonNeXt, which not only enjoy high throughputs but also maintain competitive performance. For instance, InceptionNeXt-T achieves 1.6x higher training throughputs than ConvNeX-T, as well as attains 0.2% top-1 accuracy improvement on ImageNet-1K. We anticipate InceptionNeXt can serve as an economical baseline for future architecture design to reduce carbon footprint. Code is available at https://github.com/sail-sg/inceptionnext., Comment: Code: https://github.com/sail-sg/inceptionnext

Despite its success in image synthesis, we observe that diffusion probabilistic models (DPMs) often lack contextual reasoning ability to learn the relations among object parts in an image, leading to a slow learning process. To solve this issue, we propose a Masked Diffusion Transformer (MDT) that introduces a mask latent modeling scheme to explicitly enhance the DPMs' ability to contextual relation learning among object semantic parts in an image. During training, MDT operates in the latent space to mask certain tokens. Then, an asymmetric diffusion transformer is designed to predict masked tokens from unmasked ones while maintaining the diffusion generation process. Our MDT can reconstruct the full information of an image from its incomplete contextual input, thus enabling it to learn the associated relations among image tokens. We further improve MDT with a more efficient macro network structure and training strategy, named MDTv2. Experimental results show that MDTv2 achieves superior image synthesis performance, e.g., a new SOTA FID score of 1.58 on the ImageNet dataset, and has more than 10x faster learning speed than the previous SOTA DiT. The source code is released at https://github.com/sail-sg/MDT., Comment: Extension of ICCV 2023 work, source code: https://github.com/sail-sg/MDT

Given an untrimmed video, temporal sentence grounding (TSG) aims to locate a target moment semantically according to a sentence query. Although previous respectable works have made decent success, they only focus on high-level visual features extracted from the consecutive decoded frames and fail to handle the compressed videos for query modelling, suffering from insufficient representation capability and significant computational complexity during training and testing. In this paper, we pose a new setting, compressed-domain TSG, which directly utilizes compressed videos rather than fully-decompressed frames as the visual input. To handle the raw video bit-stream input, we propose a novel Three-branch Compressed-domain Spatial-temporal Fusion (TCSF) framework, which extracts and aggregates three kinds of low-level visual features (I-frame, motion vector and residual features) for effective and efficient grounding. Particularly, instead of encoding the whole decoded frames like previous works, we capture the appearance representation by only learning the I-frame feature to reduce delay or latency. Besides, we explore the motion information not only by learning the motion vector feature, but also by exploring the relations of neighboring frames via the residual feature. In this way, a three-branch spatial-temporal attention layer with an adaptive motion-appearance fusion module is further designed to extract and aggregate both appearance and motion information for the final grounding. Experiments on three challenging datasets shows that our TCSF achieves better performance than other state-of-the-art methods with lower complexity., Comment: Accepted by CVPR-23

Temporal sentence localization in videos (TSLV) aims to retrieve the most interested segment in an untrimmed video according to a given sentence query. However, almost of existing TSLV approaches suffer from the same limitations: (1) They only focus on either frame-level or object-level visual representation learning and corresponding correlation reasoning, but fail to integrate them both; (2) They neglect to leverage the rich semantic contexts to further benefit the query reasoning. To address these issues, in this paper, we propose a novel Hierarchical Visual- and Semantic-Aware Reasoning Network (HVSARN), which enables both visual- and semantic-aware query reasoning from object-level to frame-level. Specifically, we present a new graph memory mechanism to perform visual-semantic query reasoning: For visual reasoning, we design a visual graph memory to leverage visual information of video; For semantic reasoning, a semantic graph memory is also introduced to explicitly leverage semantic knowledge contained in the classes and attributes of video objects, and perform correlation reasoning in the semantic space. Experiments on three datasets demonstrate that our HVSARN achieves a new state-of-the-art performance., Comment: Accepted by ICASSP2023

We propose to perform video question answering (VideoQA) in a Contrastive manner via a Video Graph Transformer model (CoVGT). CoVGT's uniqueness and superiority are three-fold: 1) It proposes a dynamic graph transformer module which encodes video by explicitly capturing the visual objects, their relations and dynamics, for complex spatio-temporal reasoning. 2) It designs separate video and text transformers for contrastive learning between the video and text to perform QA, instead of multi-modal transformer for answer classification. Fine-grained video-text communication is done by additional cross-modal interaction modules. 3) It is optimized by the joint fully- and self-supervised contrastive objectives between the correct and incorrect answers, as well as the relevant and irrelevant questions respectively. With superior video encoding and QA solution, we show that CoVGT can achieve much better performances than previous arts on video reasoning tasks. Its performances even surpass those models that are pretrained with millions of external data. We further show that CoVGT can also benefit from cross-modal pretraining, yet with orders of magnitude smaller data. The results demonstrate the effectiveness and superiority of CoVGT, and additionally reveal its potential for more data-efficient pretraining. We hope our success can advance VideoQA beyond coarse recognition/description towards fine-grained relation reasoning of video contents. Our code is available at https://github.com/doc-doc/CoVGT., Comment: Accepted by IEEE T-PAMI'23

Temporal sentence grounding (TSG) aims to localize the temporal segment which is semantically aligned with a natural language query in an untrimmed video.Most existing methods extract frame-grained features or object-grained features by 3D ConvNet or detection network under a conventional TSG framework, failing to capture the subtle differences between frames or to model the spatio-temporal behavior of core persons/objects. In this paper, we introduce a new perspective to address the TSG task by tracking pivotal objects and activities to learn more fine-grained spatio-temporal behaviors. Specifically, we propose a novel Temporal Sentence Tracking Network (TSTNet), which contains (A) a Cross-modal Targets Generator to generate multi-modal templates and search space, filtering objects and activities, and (B) a Temporal Sentence Tracker to track multi-modal targets for modeling the targets' behavior and to predict query-related segment. Extensive experiments and comparisons with state-of-the-arts are conducted on challenging benchmarks: Charades-STA and TACoS. And our TSTNet achieves the leading performance with a considerable real-time speed., Comment: accepted by ICASSP2023

Existing methods of privacy-preserving action recognition (PPAR) mainly focus on frame-level (spatial) privacy removal through 2D CNNs. Unfortunately, they have two major drawbacks. First, they may compromise temporal dynamics in input videos, which are critical for accurate action recognition. Second, they are vulnerable to practical attacking scenarios where attackers probe for privacy from an entire video rather than individual frames. To address these issues, we propose a novel framework STPrivacy to perform video-level PPAR. For the first time, we introduce vision Transformers into PPAR by treating a video as a tubelet sequence, and accordingly design two complementary mechanisms, i.e., sparsification and anonymization, to remove privacy from a spatio-temporal perspective. In specific, our privacy sparsification mechanism applies adaptive token selection to abandon action-irrelevant tubelets. Then, our anonymization mechanism implicitly manipulates the remaining action-tubelets to erase privacy in the embedding space through adversarial learning. These mechanisms provide significant advantages in terms of privacy preservation for human eyes and action-privacy trade-off adjustment during deployment. We additionally contribute the first two large-scale PPAR benchmarks, VP-HMDB51 and VP-UCF101, to the community. Extensive evaluations on them, as well as two other tasks, validate the effectiveness and generalization capability of our framework.

Given an untrimmed video, temporal sentence localization (TSL) aims to localize a specific segment according to a given sentence query. Though respectable works have made decent achievements in this task, they severely rely on dense video frame annotations, which require a tremendous amount of human effort to collect. In this paper, we target another more practical and challenging setting: one-shot temporal sentence localization (one-shot TSL), which learns to retrieve the query information among the entire video with only one annotated frame. Particularly, we propose an effective and novel tree-structure baseline for one-shot TSL, called Multiple Hypotheses Segment Tree (MHST), to capture the query-aware discriminative frame-wise information under the insufficient annotations. Each video frame is taken as the leaf-node, and the adjacent frames sharing the same visual-linguistic semantics will be merged into the upper non-leaf node for tree building. At last, each root node is an individual segment hypothesis containing the consecutive frames of its leaf-nodes. During the tree construction, we also introduce a pruning strategy to eliminate the interference of query-irrelevant nodes. With our designed self-supervised loss functions, our MHST is able to generate high-quality segment hypotheses for ranking and selection with the query. Experiments on two challenging datasets demonstrate that MHST achieves competitive performance compared to existing methods., Comment: Accepted by AAAI2023

Temporal sentence grounding (TSG) aims to identify the temporal boundary of a specific segment from an untrimmed video by a sentence query. All existing works first utilize a sparse sampling strategy to extract a fixed number of video frames and then conduct multi-modal interactions with query sentence for reasoning. However, we argue that these methods have overlooked two indispensable issues: 1) Boundary-bias: The annotated target segment generally refers to two specific frames as corresponding start and end timestamps. The video downsampling process may lose these two frames and take the adjacent irrelevant frames as new boundaries. 2) Reasoning-bias: Such incorrect new boundary frames also lead to the reasoning bias during frame-query interaction, reducing the generalization ability of model. To alleviate above limitations, in this paper, we propose a novel Siamese Sampling and Reasoning Network (SSRN) for TSG, which introduces a siamese sampling mechanism to generate additional contextual frames to enrich and refine the new boundaries. Specifically, a reasoning strategy is developed to learn the inter-relationship among these frames and generate soft labels on boundaries for more accurate frame-query reasoning. Such mechanism is also able to supplement the absent consecutive visual semantics to the sampled sparse frames for fine-grained activity understanding. Extensive experiments demonstrate the effectiveness of SSRN on three challenging datasets., Comment: Accepted by EMNLP Findings, 2022

Vision-Language Pre-Training (VLP) has shown promising capabilities to align image and text pairs, facilitating a broad variety of cross-modal learning tasks. However, we observe that VLP models often lack the visual grounding/localization capability which is critical for many downstream tasks such as visual reasoning. In this work, we propose a novel Position-guided Text Prompt (PTP) paradigm to enhance the visual grounding ability of cross-modal models trained with VLP. Specifically, in the VLP phase, PTP divides the image into $N\times N$ blocks, and identifies the objects in each block through the widely used object detector in VLP. It then reformulates the visual grounding task into a fill-in-the-blank problem given a PTP by encouraging the model to predict the objects in the given blocks or regress the blocks of a given object, e.g. filling `P" or ``O" in aPTP ``The block P has a O". This mechanism improves the visual grounding capability of VLP models and thus helps them better handle various downstream tasks. By introducing PTP into several state-of-the-art VLP frameworks, we observe consistently significant improvements across representative cross-modal learning model architectures and several benchmarks, e.g. zero-shot Flickr30K Retrieval (+4.8 in average recall@1) for ViLT \cite{vilt} baseline, and COCO Captioning (+5.3 in CIDEr) for SOTA BLIP \cite{blip} baseline. Moreover, PTP achieves comparable results with object-detector based methods, and much faster inference speed since PTP discards its object detector for inference while the later cannot. Our code and pre-trained weight will be released at \url{https://github.com/sail-sg/ptp}., Comment: Camera-ready version, code is in https://github.com/sail-sg/ptp

MetaFormer, the abstracted architecture of Transformer, has been found to play a significant role in achieving competitive performance. In this paper, we further explore the capacity of MetaFormer, again, without focusing on token mixer design: we introduce several baseline models under MetaFormer using the most basic or common mixers, and summarize our observations as follows: (1) MetaFormer ensures solid lower bound of performance. By merely adopting identity mapping as the token mixer, the MetaFormer model, termed IdentityFormer, achieves >80% accuracy on ImageNet-1K. (2) MetaFormer works well with arbitrary token mixers. When specifying the token mixer as even a random matrix to mix tokens, the resulting model RandFormer yields an accuracy of >81%, outperforming IdentityFormer. Rest assured of MetaFormer's results when new token mixers are adopted. (3) MetaFormer effortlessly offers state-of-the-art results. With just conventional token mixers dated back five years ago, the models instantiated from MetaFormer already beat state of the art. (a) ConvFormer outperforms ConvNeXt. Taking the common depthwise separable convolutions as the token mixer, the model termed ConvFormer, which can be regarded as pure CNNs, outperforms the strong CNN model ConvNeXt. (b) CAFormer sets new record on ImageNet-1K. By simply applying depthwise separable convolutions as token mixer in the bottom stages and vanilla self-attention in the top stages, the resulting model CAFormer sets a new record on ImageNet-1K: it achieves an accuracy of 85.5% at 224x224 resolution, under normal supervised training without external data or distillation. In our expedition to probe MetaFormer, we also find that a new activation, StarReLU, reduces 71% FLOPs of activation compared with GELU yet achieves better performance. We expect StarReLU to find great potential in MetaFormer-like models alongside other neural networks., Comment: Accepted to TPAMI. Code: https://github.com/sail-sg/metaformer

Although increasingly training-expensive, most self-supervised learning (SSL) models have repeatedly been trained from scratch but not fully utilized, since only a few SOTAs are employed for downstream tasks. In this work, we explore a sustainable SSL framework with two major challenges: i) learning a stronger new SSL model based on the existing pretrained SSL model, also called as "base" model, in a cost-friendly manner, ii) allowing the training of the new model to be compatible with various base models. We propose a Target-Enhanced Conditional (TEC) scheme which introduces two components to the existing mask-reconstruction based SSL. Firstly, we propose patch-relation enhanced targets which enhances the target given by base model and encourages the new model to learn semantic-relation knowledge from the base model by using incomplete inputs. This hardening and target-enhancing help the new model surpass the base model, since they enforce additional patch relation modeling to handle incomplete input. Secondly, we introduce a conditional adapter that adaptively adjusts new model prediction to align with the target of different base models. Extensive experimental results show that our TEC scheme can accelerate the learning speed, and also improve SOTA SSL base models, e.g., MAE and iBOT, taking an explorative step towards sustainable SSL., Comment: Extension of NeurIPS 2022 workshop

For long-tailed classification, most works often pretrain a big model on a large-scale dataset, and then fine-tune the whole model for adapting to long-tailed data. Though promising, fine-tuning the whole pretrained model tends to suffer from high cost in computation and deployment of different models for different tasks, as well as weakened generalization ability for overfitting to certain features of long-tailed data. To alleviate these issues, we propose an effective Long-tailed Prompt Tuning method for long-tailed classification. LPT introduces several trainable prompts into a frozen pretrained model to adapt it to long-tailed data. For better effectiveness, we divide prompts into two groups: 1) a shared prompt for the whole long-tailed dataset to learn general features and to adapt a pretrained model into target domain; and 2) group-specific prompts to gather group-specific features for the samples which have similar features and also to empower the pretrained model with discrimination ability. Then we design a two-phase training paradigm to learn these prompts. In phase 1, we train the shared prompt via supervised prompt tuning to adapt a pretrained model to the desired long-tailed domain. In phase 2, we use the learnt shared prompt as query to select a small best matched set for a group of similar samples from the group-specific prompt set to dig the common features of these similar samples, then optimize these prompts with dual sampling strategy and asymmetric GCL loss. By only fine-tuning a few prompts while fixing the pretrained model, LPT can reduce training and deployment cost by storing a few prompts, and enjoys a strong generalization ability of the pretrained model. Experiments show that on various long-tailed benchmarks, with only ~1.1% extra parameters, LPT achieves comparable performance than previous whole model fine-tuning methods, and is more robust to domain-shift., Comment: ICLR 2023 (poster)

As an increasingly popular task in multimedia information retrieval, video moment retrieval (VMR) aims to localize the target moment from an untrimmed video according to a given language query. Most previous methods depend heavily on numerous manual annotations (i.e., moment boundaries), which are extremely expensive to acquire in practice. In addition, due to the domain gap between different datasets, directly applying these pre-trained models to an unseen domain leads to a significant performance drop. In this paper, we focus on a novel task: cross-domain VMR, where fully-annotated datasets are available in one domain (``source domain''), but the domain of interest (``target domain'') only contains unannotated datasets. As far as we know, we present the first study on cross-domain VMR. To address this new task, we propose a novel Multi-Modal Cross-Domain Alignment (MMCDA) network to transfer the annotation knowledge from the source domain to the target domain. However, due to the domain discrepancy between the source and target domains and the semantic gap between videos and queries, directly applying trained models to the target domain generally leads to a performance drop. To solve this problem, we develop three novel modules: (i) a domain alignment module is designed to align the feature distributions between different domains of each modality; (ii) a cross-modal alignment module aims to map both video and query features into a joint embedding space and to align the feature distributions between different modalities in the target domain; (iii) a specific alignment module tries to obtain the fine-grained similarity between a specific frame and the given query for optimal localization. By jointly training these three modules, our MMCDA can learn domain-invariant and semantic-aligned cross-modal representations., Comment: Accepted by IEEE Transactions on Multimedia

This paper studies the multimedia problem of temporal sentence grounding (TSG), which aims to accurately determine the specific video segment in an untrimmed video according to a given sentence query. Traditional TSG methods mainly follow the top-down or bottom-up framework and are not end-to-end. They severely rely on time-consuming post-processing to refine the grounding results. Recently, some transformer-based approaches are proposed to efficiently and effectively model the fine-grained semantic alignment between video and query. Although these methods achieve significant performance to some extent, they equally take frames of the video and words of the query as transformer input for correlating, failing to capture their different levels of granularity with distinct semantics. To address this issue, in this paper, we propose a novel Hierarchical Local-Global Transformer (HLGT) to leverage this hierarchy information and model the interactions between different levels of granularity and different modalities for learning more fine-grained multi-modal representations. Specifically, we first split the video and query into individual clips and phrases to learn their local context (adjacent dependency) and global correlation (long-range dependency) via a temporal transformer. Then, a global-local transformer is introduced to learn the interactions between the local-level and global-level semantics for better multi-modal reasoning. Besides, we develop a new cross-modal cycle-consistency loss to enforce interaction between two modalities and encourage the semantic alignment between them. Finally, we design a brand-new cross-modal parallel transformer decoder to integrate the encoded visual and textual features for final grounding. Extensive experiments on three challenging datasets show that our proposed HLGT achieves a new state-of-the-art performance.

Crowd counting is a regression task that estimates the number of people in a scene image, which plays a vital role in a range of safety-critical applications, such as video surveillance, traffic monitoring and flow control. In this paper, we investigate the vulnerability of deep learning based crowd counting models to backdoor attacks, a major security threat to deep learning. A backdoor attack implants a backdoor trigger into a target model via data poisoning so as to control the model's predictions at test time. Different from image classification models on which most of existing backdoor attacks have been developed and tested, crowd counting models are regression models that output multi-dimensional density maps, thus requiring different techniques to manipulate. In this paper, we propose two novel Density Manipulation Backdoor Attacks (DMBA$^{-}$ and DMBA$^{+}$) to attack the model to produce arbitrarily large or small density estimations. Experimental results demonstrate the effectiveness of our DMBA attacks on five classic crowd counting models and four types of datasets. We also provide an in-depth analysis of the unique challenges of backdooring crowd counting models and reveal two key elements of effective attacks: 1) full and dense triggers and 2) manipulation of the ground truth counts or density maps. Our work could help evaluate the vulnerability of crowd counting models to potential backdoor attacks., Comment: To appear in ACMMM 2022. 10pages, 6 figures and 2 tables

This paper proposes a Video Graph Transformer (VGT) model for Video Quetion Answering (VideoQA). VGT's uniqueness are two-fold: 1) it designs a dynamic graph transformer module which encodes video by explicitly capturing the visual objects, their relations, and dynamics for complex spatio-temporal reasoning; and 2) it exploits disentangled video and text Transformers for relevance comparison between the video and text to perform QA, instead of entangled cross-modal Transformer for answer classification. Vision-text communication is done by additional cross-modal interaction modules. With more reasonable video encoding and QA solution, we show that VGT can achieve much better performances on VideoQA tasks that challenge dynamic relation reasoning than prior arts in the pretraining-free scenario. Its performances even surpass those models that are pretrained with millions of external data. We further show that VGT can also benefit a lot from self-supervised cross-modal pretraining, yet with orders of magnitude smaller data. These results clearly demonstrate the effectiveness and superiority of VGT, and reveal its potential for more data-efficient pretraining. With comprehensive analyses and some heuristic observations, we hope that VGT can promote VQA research beyond coarse recognition/description towards fine-grained relation reasoning in realistic videos. Our code is available at https://github.com/sail-sg/VGT., Comment: ECCV'22

Spatial-Temporal Video Grounding (STVG) is a challenging task which aims to localize the spatio-temporal tube of the interested object semantically according to a natural language query. Most previous works not only severely rely on the anchor boxes extracted by Faster R-CNN, but also simply regard the video as a series of individual frames, thus lacking their temporal modeling. Instead, in this paper, we are the first to propose an anchor-free framework for STVG, called Gaussian Kernel-based Cross Modal Network (GKCMN). Specifically, we utilize the learned Gaussian Kernel-based heatmaps of each video frame to locate the query-related object. A mixed serial and parallel connection network is further developed to leverage both spatial and temporal relations among frames for better grounding. Experimental results on VidSTG dataset demonstrate the effectiveness of our proposed GKCMN., Comment: Accepted by ICIP2022

For unsupervised pretraining, mask-reconstruction pretraining (MRP) approaches, e.g. MAE and data2vec, randomly mask input patches and then reconstruct the pixels or semantic features of these masked patches via an auto-encoder. Then for a downstream task, supervised fine-tuning the pretrained encoder remarkably surpasses the conventional ``supervised learning'' (SL) trained from scratch. However, it is still unclear 1) how MRP performs semantic feature learning in the pretraining phase and 2) why it helps in downstream tasks. To solve these problems, we first theoretically show that on an auto-encoder of a two/one-layered convolution encoder/decoder, MRP can capture all discriminative features of each potential semantic class in the pretraining dataset. Then considering the fact that the pretraining dataset is of huge size and high diversity and thus covers most features in downstream dataset, in fine-tuning phase, the pretrained encoder can capture as much features as it can in downstream datasets, and would not lost these features with theoretical guarantees. In contrast, SL only randomly captures some features due to lottery ticket hypothesis. So MRP provably achieves better performance than SL on the classification tasks. Experimental results testify to our data assumptions and also our theoretical implications.

Recent studies show that Transformer has strong capability of building long-range dependencies, yet is incompetent in capturing high frequencies that predominantly convey local information. To tackle this issue, we present a novel and general-purpose Inception Transformer, or iFormer for short, that effectively learns comprehensive features with both high- and low-frequency information in visual data. Specifically, we design an Inception mixer to explicitly graft the advantages of convolution and max-pooling for capturing the high-frequency information to Transformers. Different from recent hybrid frameworks, the Inception mixer brings greater efficiency through a channel splitting mechanism to adopt parallel convolution/max-pooling path and self-attention path as high- and low-frequency mixers, while having the flexibility to model discriminative information scattered within a wide frequency range. Considering that bottom layers play more roles in capturing high-frequency details while top layers more in modeling low-frequency global information, we further introduce a frequency ramp structure, i.e. gradually decreasing the dimensions fed to the high-frequency mixer and increasing those to the low-frequency mixer, which can effectively trade-off high- and low-frequency components across different layers. We benchmark the iFormer on a series of vision tasks, and showcase that it achieves impressive performance on image classification, COCO detection and ADE20K segmentation. For example, our iFormer-S hits the top-1 accuracy of 83.4% on ImageNet-1K, much higher than DeiT-S by 3.6%, and even slightly better than much bigger model Swin-B (83.3%) with only 1/4 parameters and 1/3 FLOPs. Code and models will be released at https://github.com/sail-sg/iFormer., Comment: Code and models will be released at https://github.com/sail-sg/iFormer

Graph neural networks (GNNs) have achieved state-of-the-art performance in many graph-based tasks such as node classification and graph classification. However, many recent works have demonstrated that an attacker can mislead GNN models by slightly perturbing the graph structure. Existing attacks to GNNs are either under the less practical threat model where the attacker is assumed to access the GNN model parameters, or under the practical black-box threat model but consider perturbing node features that are shown to be not enough effective. In this paper, we aim to bridge this gap and consider black-box attacks to GNNs with structure perturbation as well as with theoretical guarantees. We propose to address this challenge through bandit techniques. Specifically, we formulate our attack as an online optimization with bandit feedback. This original problem is essentially NP-hard due to the fact that perturbing the graph structure is a binary optimization problem. We then propose an online attack based on bandit optimization which is proven to be {sublinear} to the query number $T$, i.e., $\mathcal{O}(\sqrt{N}T^{3/4})$ where $N$ is the number of nodes in the graph. Finally, we evaluate our proposed attack by conducting experiments over multiple datasets and GNN models. The experimental results on various citation graphs and image graphs show that our attack is both effective and efficient. Source code is available at~\url{https://github.com/Metaoblivion/Bandit_GNN_Attack}, Comment: Accepted by CVPR 2022 Oral presentation

In self-supervised learning, multi-granular features are heavily desired though rarely investigated, as different downstream tasks (e.g., general and fine-grained classification) often require different or multi-granular features, e.g.~fine- or coarse-grained one or their mixture. In this work, for the first time, we propose an effective MUlti-Granular Self-supervised learning (Mugs) framework to explicitly learn multi-granular visual features. Mugs has three complementary granular supervisions: 1) an instance discrimination supervision (IDS), 2) a novel local-group discrimination supervision (LGDS), and 3) a group discrimination supervision (GDS). IDS distinguishes different instances to learn instance-level fine-grained features. LGDS aggregates features of an image and its neighbors into a local-group feature, and pulls local-group features from different crops of the same image together and push them away for others. It provides complementary instance supervision to IDS via an extra alignment on local neighbors, and scatters different local-groups separately to increase discriminability. Accordingly, it helps learn high-level fine-grained features at a local-group level. Finally, to prevent similar local-groups from being scattered randomly or far away, GDS brings similar samples close and thus pulls similar local-groups together, capturing coarse-grained features at a (semantic) group level. Consequently, Mugs can capture three granular features that often enjoy higher generality on diverse downstream tasks over single-granular features, e.g.~instance-level fine-grained features in contrastive learning. By only pretraining on ImageNet-1K, Mugs sets new SoTA linear probing accuracy 82.1$\%$ on ImageNet-1K and improves previous SoTA by $1.1\%$. It also surpasses SoTAs on other tasks, e.g. transfer learning, detection and segmentation., Comment: code and models are available at https://github.com/sail-sg/mugs

The few-shot learning ability of vision transformers (ViTs) is rarely investigated though heavily desired. In this work, we empirically find that with the same few-shot learning frameworks, \eg~Meta-Baseline, replacing the widely used CNN feature extractor with a ViT model often severely impairs few-shot classification performance. Moreover, our empirical study shows that in the absence of inductive bias, ViTs often learn the low-qualified token dependencies under few-shot learning regime where only a few labeled training data are available, which largely contributes to the above performance degradation. To alleviate this issue, for the first time, we propose a simple yet effective few-shot training framework for ViTs, namely Self-promoted sUpervisioN (SUN). Specifically, besides the conventional global supervision for global semantic learning SUN further pretrains the ViT on the few-shot learning dataset and then uses it to generate individual location-specific supervision for guiding each patch token. This location-specific supervision tells the ViT which patch tokens are similar or dissimilar and thus accelerates token dependency learning. Moreover, it models the local semantics in each patch token to improve the object grounding and recognition capability which helps learn generalizable patterns. To improve the quality of location-specific supervision, we further propose two techniques:~1) background patch filtration to filtrate background patches out and assign them into an extra background class; and 2) spatial-consistent augmentation to introduce sufficient diversity for data augmentation while keeping the accuracy of the generated local supervisions. Experimental results show that SUN using ViTs significantly surpasses other few-shot learning frameworks with ViTs and is the first one that achieves higher performance than those CNN state-of-the-arts., Comment: Code is available at https://github.com/DongSky/few-shot-vit

Temporal sentence grounding aims to localize a target segment in an untrimmed video semantically according to a given sentence query. Most previous works focus on learning frame-level features of each whole frame in the entire video, and directly match them with the textual information. Such frame-level feature extraction leads to the obstacles of these methods in distinguishing ambiguous video frames with complicated contents and subtle appearance differences, thus limiting their performance. In order to differentiate fine-grained appearance similarities among consecutive frames, some state-of-the-art methods additionally employ a detection model like Faster R-CNN to obtain detailed object-level features in each frame for filtering out the redundant background contents. However, these methods suffer from missing motion analysis since the object detection module in Faster R-CNN lacks temporal modeling. To alleviate the above limitations, in this paper, we propose a novel Motion- and Appearance-guided 3D Semantic Reasoning Network (MA3SRN), which incorporates optical-flow-guided motion-aware, detection-based appearance-aware, and 3D-aware object-level features to better reason the spatial-temporal object relations for accurately modelling the activity among consecutive frames. Specifically, we first develop three individual branches for motion, appearance, and 3D encoding separately to learn fine-grained motion-guided, appearance-guided, and 3D-aware object features, respectively. Then, both motion and appearance information from corresponding branches are associated to enhance the 3D-aware features for the final precise grounding. Extensive experiments on three challenging datasets (ActivityNet Caption, Charades-STA and TACoS) demonstrate that the proposed MA3SRN model achieves a new state-of-the-art., Comment: arXiv admin note: text overlap with arXiv:2201.00457

Temporal video grounding (TVG) aims to localize a target segment in a video according to a given sentence query. Though respectable works have made decent achievements in this task, they severely rely on abundant video-query paired data, which is expensive and time-consuming to collect in real-world scenarios. In this paper, we explore whether a video grounding model can be learned without any paired annotations. To the best of our knowledge, this paper is the first work trying to address TVG in an unsupervised setting. Considering there is no paired supervision, we propose a novel Deep Semantic Clustering Network (DSCNet) to leverage all semantic information from the whole query set to compose the possible activity in each video for grounding. Specifically, we first develop a language semantic mining module, which extracts implicit semantic features from the whole query set. Then, these language semantic features serve as the guidance to compose the activity in video via a video-based semantic aggregation module. Finally, we utilize a foreground attention branch to filter out the redundant background activities and refine the grounding results. To validate the effectiveness of our DSCNet, we conduct experiments on both ActivityNet Captions and Charades-STA datasets. The results demonstrate that DSCNet achieves competitive performance, and even outperforms most weakly-supervised approaches., Comment: Accepted by AAAI2022

This paper addresses temporal sentence grounding. Previous works typically solve this task by learning frame-level video features and align them with the textual information. A major limitation of these works is that they fail to distinguish ambiguous video frames with subtle appearance differences due to frame-level feature extraction. Recently, a few methods adopt Faster R-CNN to extract detailed object features in each frame to differentiate the fine-grained appearance similarities. However, the object-level features extracted by Faster R-CNN suffer from missing motion analysis since the object detection model lacks temporal modeling. To solve this issue, we propose a novel Motion-Appearance Reasoning Network (MARN), which incorporates both motion-aware and appearance-aware object features to better reason object relations for modeling the activity among successive frames. Specifically, we first introduce two individual video encoders to embed the video into corresponding motion-oriented and appearance-aspect object representations. Then, we develop separate motion and appearance branches to learn motion-guided and appearance-guided object relations, respectively. At last, both motion and appearance information from two branches are associated to generate more representative features for final grounding. Extensive experiments on two challenging datasets (Charades-STA and TACoS) show that our proposed MARN significantly outperforms previous state-of-the-art methods by a large margin., Comment: Accepted by AAAI2022

Temporal sentence grounding (TSG) is crucial and fundamental for video understanding. Although the existing methods train well-designed deep networks with a large amount of data, we find that they can easily forget the rarely appeared cases in the training stage due to the off-balance data distribution, which influences the model generalization and leads to undesirable performance. To tackle this issue, we propose a memory-augmented network, called Memory-Guided Semantic Learning Network (MGSL-Net), that learns and memorizes the rarely appeared content in TSG tasks. Specifically, MGSL-Net consists of three main parts: a cross-modal inter-action module, a memory augmentation module, and a heterogeneous attention module. We first align the given video-query pair by a cross-modal graph convolutional network, and then utilize a memory module to record the cross-modal shared semantic features in the domain-specific persistent memory. During training, the memory slots are dynamically associated with both common and rare cases, alleviating the forgetting issue. In testing, the rare cases can thus be enhanced by retrieving the stored memories, resulting in better generalization. At last, the heterogeneous attention module is utilized to integrate the enhanced multi-modal features in both video and query domains. Experimental results on three benchmarks show the superiority of our method on both effectiveness and efficiency, which substantially improves the accuracy not only on the entire dataset but also on rare cases., Comment: Accepted by AAAI2022

Natural language video localization (NLVL) is an important task in the vision-language understanding area, which calls for an in-depth understanding of not only computer vision and natural language side alone, but more importantly the interplay between both sides. Adversarial vulnerability has been well-recognized as a critical security issue of deep neural network models, which requires prudent investigation. Despite its extensive yet separated studies in video and language tasks, current understanding of the adversarial robustness in vision-language joint tasks like NLVL is less developed. This paper therefore aims to comprehensively investigate the adversarial robustness of NLVL models by examining three facets of vulnerabilities from both attack and defense aspects. To achieve the attack goal, we propose a new adversarial attack paradigm called synonymous sentences-aware adversarial attack on NLVL (SNEAK), which captures the cross-modality interplay between the vision and language sides.

While transformers have shown great potential on video recognition with their strong capability of capturing long-range dependencies, they often suffer high computational costs induced by the self-attention to the huge number of 3D tokens. In this paper, we present a new transformer architecture termed DualFormer, which can efficiently perform space-time attention for video recognition. Concretely, DualFormer stratifies the full space-time attention into dual cascaded levels, i.e., to first learn fine-grained local interactions among nearby 3D tokens, and then to capture coarse-grained global dependencies between the query token and global pyramid contexts. Different from existing methods that apply space-time factorization or restrict attention computations within local windows for improving efficiency, our local-global stratification strategy can well capture both short- and long-range spatiotemporal dependencies, and meanwhile greatly reduces the number of keys and values in attention computation to boost efficiency. Experimental results verify the superiority of DualFormer on five video benchmarks against existing methods. In particular, DualFormer achieves 82.9%/85.2% top-1 accuracy on Kinetics-400/600 with ~1000G inference FLOPs which is at least 3.2x fewer than existing methods with similar performance. We have released the source code at https://github.com/sail-sg/dualformer., Comment: Accepted by ECCV 2022