Search

Capitalizing on vast amount of image-text data, large-scale vision-language pre-training has demonstrated remarkable zero-shot capabilities and has been utilized in several applications. However, models trained on general everyday web-crawled data often exhibit sub-optimal performance for specialized domains, likely due to domain shift. Recent works have tackled this problem for some domains (e.g., healthcare) by constructing domain-specialized image-text data. However, constructing a dedicated large-scale image-text dataset for sustainable area of agriculture and livestock is still open to research. Further, this domain desires fine-grained feature learning due to the subtle nature of the downstream tasks (e.g, nutrient deficiency detection, livestock breed classification). To address this we present AgriCLIP, a vision-language foundational model dedicated to the domain of agriculture and livestock. First, we propose a large-scale dataset, named ALive, that leverages customized prompt generation strategy to overcome the scarcity of expert annotations. Our ALive dataset covers crops, livestock, and fishery, with around 600,000 image-text pairs. Second, we propose a training pipeline that integrates both contrastive and self-supervised learning to learn both global semantic and local fine-grained domain-specialized features. Experiments on diverse set of 20 downstream tasks demonstrate the effectiveness of AgriCLIP framework, achieving an absolute gain of 7.8\% in terms of average zero-shot classification accuracy, over the standard CLIP adaptation via domain-specialized ALive dataset. Our ALive dataset and code can be accessible at \href{https://github.com/umair1221/AgriCLIP/tree/main}{Github}.

Recent attention-based volumetric segmentation (VS) methods have achieved remarkable performance in the medical domain which focuses on modeling long-range dependencies. However, for voxel-wise prediction tasks, discriminative local features are key components for the performance of the VS models which is missing in attention-based VS methods. Aiming at resolving this issue, we deliberately incorporate the convolutional encoder branch with transformer backbone to extract local and global features in a parallel manner and aggregate them in Cross Feature Mixer Module (CFMM) for better prediction of segmentation mask. Consequently, we observe that the derived model, Y-CT-Net, achieves competitive performance on multiple medical segmentation tasks. For example, on multi-organ segmentation, Y-CT-Net achieves an 82.4% dice score, surpassing well-tuned VS Transformer/CNN-like baselines UNETR/ResNet-3D by 2.9%/1.4%. With the success of Y-CT-Net, we extend this concept with hybrid attention models, that derived Y-CH-Net model, which brings a 3% improvement in terms of HD95 score for same segmentation task. The effectiveness of both models Y-CT-Net and Y-CH-Net verifies our hypothesis and motivates us to initiate the concept of Y-CA-Net, a versatile generic architecture based upon any two encoders and a decoder backbones, to fully exploit the complementary strengths of both convolution and attention mechanisms. Based on experimental results, we argue Y-CA-Net is a key player in achieving superior results for volumetric segmentation.

Large multimodal models (LMMs) have shown encouraging performance in the natural image domain using visual instruction tuning. However, these LMMs struggle to describe the content of remote sensing images for tasks such as image or region grounding, classification, etc. Recently, GeoChat make an effort to describe the contents of the RS images. Although, GeoChat achieves promising performance for various RS tasks, it struggles to describe the changes between bi-temporal RS images which is a key RS task. This necessitates the development of an LMM that can describe the changes between the bi-temporal RS images. However, there is insufficiency of datasets that can be utilized to tune LMMs. In order to achieve this, we introduce a change description instruction dataset that can be utilized to finetune an LMM and provide better change descriptions for RS images. Furthermore, we show that the LLaVA-1.5 model, with slight modifications, can be finetuned on the change description instruction dataset and achieve favorably better performance.

State-space models (SSMs), exemplified by S4, have introduced a novel context modeling method by integrating state-space techniques into deep learning. However, they struggle with global context modeling due to their data-independent matrices. The Mamba model addressed this with data-dependent variants via the S6 selective-scan algorithm, enhancing context modeling, especially for long sequences. However, Mamba-based architectures are difficult to scale with respect to the number of parameters, which is a major limitation for vision applications. This paper addresses the scalability issue of large SSMs for image classification and action recognition without requiring additional techniques like knowledge distillation. We analyze the distinct characteristics of Mamba-based and Attention-based models, proposing a Mamba-Attention interleaved architecture that enhances scalability, robustness, and performance. We demonstrate that the stable and efficient interleaved architecture resolves the scalability issue of Mamba-based architectures for images and videos and increases robustness to common artifacts like JPEG compression. Our thorough evaluation on the ImageNet-1K, Kinetics-400 and Something-Something-v2 benchmarks demonstrates that our approach improves the accuracy of state-of-the-art Mamba-based architectures by up to $+1.7$.

The rapid proliferation of large-scale text-to-image generation (T2IG) models has led to concerns about their potential misuse in generating harmful content. Though many methods have been proposed for erasing undesired concepts from T2IG models, they only provide a false sense of security, as recent works demonstrate that concept-erased models (CEMs) can be easily deceived to generate the erased concept through adversarial attacks. The problem of adversarially robust concept erasing without significant degradation to model utility (ability to generate benign concepts) remains an unresolved challenge, especially in the white-box setting where the adversary has access to the CEM. To address this gap, we propose an approach called STEREO that involves two distinct stages. The first stage searches thoroughly enough for strong and diverse adversarial prompts that can regenerate an erased concept from a CEM, by leveraging robust optimization principles from adversarial training. In the second robustly erase once stage, we introduce an anchor-concept-based compositional objective to robustly erase the target concept at one go, while attempting to minimize the degradation on model utility. By benchmarking the proposed STEREO approach against four state-of-the-art concept erasure methods under three adversarial attacks, we demonstrate its ability to achieve a better robustness vs. utility trade-off. Our code and models are available at https://github.com/koushiksrivats/robust-concept-erasing., Comment: Project Page: https://koushiksrivats.github.io/robust-concept-erasing/

Medical vision-language models (Med-VLMs) trained on large datasets of medical image-text pairs and later fine-tuned for specific tasks have emerged as a mainstream paradigm in medical image analysis. However, recent studies have highlighted the susceptibility of these Med-VLMs to adversarial attacks, raising concerns about their safety and robustness. Randomized smoothing is a well-known technique for turning any classifier into a model that is certifiably robust to adversarial perturbations. However, this approach requires retraining the Med-VLM-based classifier so that it classifies well under Gaussian noise, which is often infeasible in practice. In this paper, we propose a novel framework called PromptSmooth to achieve efficient certified robustness of Med-VLMs by leveraging the concept of prompt learning. Given any pre-trained Med-VLM, PromptSmooth adapts it to handle Gaussian noise by learning textual prompts in a zero-shot or few-shot manner, achieving a delicate balance between accuracy and robustness, while minimizing the computational overhead. Moreover, PromptSmooth requires only a single model to handle multiple noise levels, which substantially reduces the computational cost compared to traditional methods that rely on training a separate model for each noise level. Comprehensive experiments based on three Med-VLMs and across six downstream datasets of various imaging modalities demonstrate the efficacy of PromptSmooth. Our code and models are available at https://github.com/nhussein/promptsmooth., Comment: Accepted to MICCAI 2024

Deep learning-based face recognition (FR) systems pose significant privacy risks by tracking users without their consent. While adversarial attacks can protect privacy, they often produce visible artifacts compromising user experience. To mitigate this issue, recent facial privacy protection approaches advocate embedding adversarial noise into the natural looking makeup styles. However, these methods require training on large-scale makeup datasets that are not always readily available. In addition, these approaches also suffer from dataset bias. For instance, training on makeup data that predominantly contains female faces could compromise protection efficacy for male faces. To handle these issues, we propose a test-time optimization approach that solely optimizes an untrained neural network to transfer makeup style from a reference to a source image in an adversarial manner. We introduce two key modules: a correspondence module that aligns regions between reference and source images in latent space, and a decoder with conditional makeup layers. The untrained decoder, optimized via carefully designed structural and makeup consistency losses, generates a protected image that resembles the source but incorporates adversarial makeup to deceive FR models. As our approach does not rely on training with makeup face datasets, it avoids potential male/female dataset biases while providing effective protection. We further extend the proposed approach to videos by leveraging on temporal correlations. Experiments on benchmark datasets demonstrate superior performance in face verification and identification tasks and effectiveness against commercial FR systems. Our code and models will be available at https://github.com/fahadshamshad/deep-facial-privacy-prior, Comment: Proceedings of ECCV Workshop on Explainable AI for Biometrics, 2024

Medical foundation models are gaining prominence in the medical community for their ability to derive general representations from extensive collections of medical image-text pairs. Recent research indicates that these models are susceptible to backdoor attacks, which allow them to classify clean images accurately but fail when specific triggers are introduced. However, traditional backdoor attacks necessitate a considerable amount of additional data to maliciously pre-train a model. This requirement is often impractical in medical imaging applications due to the usual scarcity of data. Inspired by the latest developments in learnable prompts, this work introduces a method to embed a backdoor into the medical foundation model during the prompt learning phase. By incorporating learnable prompts within the text encoder and introducing imperceptible learnable noise trigger to the input images, we exploit the full capabilities of the medical foundation models (Med-FM). Our method, BAPLe, requires only a minimal subset of data to adjust the noise trigger and the text prompts for downstream tasks, enabling the creation of an effective backdoor attack. Through extensive experiments with four medical foundation models, each pre-trained on different modalities and evaluated across six downstream datasets, we demonstrate the efficacy of our approach. BAPLe achieves a high backdoor success rate across all models and datasets, outperforming the baseline backdoor attack methods. Our work highlights the vulnerability of Med-FMs towards backdoor attacks and strives to promote the safe adoption of Med-FMs before their deployment in real-world applications. Code is available at https://asif-hanif.github.io/baple/., Comment: MICCAI 2024

With the advent of large pre-trained transformer models, fine-tuning these models for various downstream tasks is a critical problem. Paucity of training data, the existence of data silos, and stringent privacy constraints exacerbate this fine-tuning problem in the medical imaging domain, creating a strong need for algorithms that enable collaborative fine-tuning of pre-trained models. Moreover, the large size of these models necessitates the use of parameter-efficient fine-tuning (PEFT) to reduce the communication burden in federated learning. In this work, we systematically investigate various federated PEFT strategies for adapting a Vision Transformer (ViT) model (pre-trained on a large natural image dataset) for medical image classification. Apart from evaluating known PEFT techniques, we introduce new federated variants of PEFT algorithms such as visual prompt tuning (VPT), low-rank decomposition of visual prompts, stochastic block attention fine-tuning, and hybrid PEFT methods like low-rank adaptation (LoRA)+VPT. Moreover, we perform a thorough empirical analysis to identify the optimal PEFT method for the federated setting and understand the impact of data distribution on federated PEFT, especially for out-of-domain (OOD) and non-IID data. The key insight of this study is that while most federated PEFT methods work well for in-domain transfer, there is a substantial accuracy vs. efficiency trade-off when dealing with OOD and non-IID scenarios, which is commonly the case in medical imaging. Specifically, every order of magnitude reduction in fine-tuned/exchanged parameters can lead to a 4% drop in accuracy. Thus, the initial model choice is crucial for federated PEFT. It is preferable to use medical foundation models learned from in-domain medical image data (if available) rather than general vision models.

The recent developments in Large Multi-modal Video Models (Video-LMMs) have significantly enhanced our ability to interpret and analyze video data. Despite their impressive capabilities, current Video-LMMs have not been evaluated for anomaly detection tasks, which is critical to their deployment in practical scenarios e.g., towards identifying deepfakes, manipulated video content, traffic accidents and crimes. In this paper, we introduce VANE-Bench, a benchmark designed to assess the proficiency of Video-LMMs in detecting and localizing anomalies and inconsistencies in videos. Our dataset comprises an array of videos synthetically generated using existing state-of-the-art text-to-video generation models, encompassing a variety of subtle anomalies and inconsistencies grouped into five categories: unnatural transformations, unnatural appearance, pass-through, disappearance and sudden appearance. Additionally, our benchmark features real-world samples from existing anomaly detection datasets, focusing on crime-related irregularities, atypical pedestrian behavior, and unusual events. The task is structured as a visual question-answering challenge to gauge the models' ability to accurately detect and localize the anomalies within the videos. We evaluate nine existing Video-LMMs, both open and closed sources, on this benchmarking task and find that most of the models encounter difficulties in effectively identifying the subtle anomalies. In conclusion, our research offers significant insights into the current capabilities of Video-LMMs in the realm of anomaly detection, highlighting the importance of our work in evaluating and improving these models for real-world applications. Our code and data is available at https://hananshafi.github.io/vane-benchmark/, Comment: Data: https://huggingface.co/datasets/rohit901/VANE-Bench

Vision State Space Models (VSSMs), a novel architecture that combines the strengths of recurrent neural networks and latent variable models, have demonstrated remarkable performance in visual perception tasks by efficiently capturing long-range dependencies and modeling complex visual dynamics. However, their robustness under natural and adversarial perturbations remains a critical concern. In this work, we present a comprehensive evaluation of VSSMs' robustness under various perturbation scenarios, including occlusions, image structure, common corruptions, and adversarial attacks, and compare their performance to well-established architectures such as transformers and Convolutional Neural Networks. Furthermore, we investigate the resilience of VSSMs to object-background compositional changes on sophisticated benchmarks designed to test model performance in complex visual scenes. We also assess their robustness on object detection and segmentation tasks using corrupted datasets that mimic real-world scenarios. To gain a deeper understanding of VSSMs' adversarial robustness, we conduct a frequency-based analysis of adversarial attacks, evaluating their performance against low-frequency and high-frequency perturbations. Our findings highlight the strengths and limitations of VSSMs in handling complex visual corruptions, offering valuable insights for future research. Our code and models will be available at https://github.com/HashmatShadab/MambaRobustness.

Volumetric medical segmentation models have achieved significant success on organ and tumor-based segmentation tasks in recent years. However, their vulnerability to adversarial attacks remains largely unexplored, raising serious concerns regarding the real-world deployment of tools employing such models in the healthcare sector. This underscores the importance of investigating the robustness of existing models. In this context, our work aims to empirically examine the adversarial robustness across current volumetric segmentation architectures, encompassing Convolutional, Transformer, and Mamba-based models. We extend this investigation across four volumetric segmentation datasets, evaluating robustness under both white box and black box adversarial attacks. Overall, we observe that while both pixel and frequency-based attacks perform reasonably well under \emph{white box} setting, the latter performs significantly better under transfer-based black box attacks. Across our experiments, we observe transformer-based models show higher robustness than convolution-based models with Mamba-based models being the most vulnerable. Additionally, we show that large-scale training of volumetric segmentation models improves the model's robustness against adversarial attacks. The code and robust models are available at https://github.com/HashmatShadab/Robustness-of-Volumetric-Medical-Segmentation-Models., Comment: Accepted at British Machine Vision Conference 2024

Most existing multi-object tracking methods typically learn visual tracking features via maximizing dis-similarities of different instances and minimizing similarities of the same instance. While such a feature learning scheme achieves promising performance, learning discriminative features solely based on visual information is challenging especially in case of environmental interference such as occlusion, blur and domain variance. In this work, we argue that multi-modal language-driven features provide complementary information to classical visual features, thereby aiding in improving the robustness to such environmental interference. To this end, we propose a new multi-object tracking framework, named LG-MOT, that explicitly leverages language information at different levels of granularity (scene-and instance-level) and combines it with standard visual features to obtain discriminative representations. To develop LG-MOT, we annotate existing MOT datasets with scene-and instance-level language descriptions. We then encode both instance-and scene-level language information into high-dimensional embeddings, which are utilized to guide the visual features during training. At inference, our LG-MOT uses the standard visual features without relying on annotated language descriptions. Extensive experiments on three benchmarks, MOT17, DanceTrack and SportsMOT, reveal the merits of the proposed contributions leading to state-of-the-art performance. On the DanceTrack test set, our LG-MOT achieves an absolute gain of 2.2\% in terms of target object association (IDF1 score), compared to the baseline using only visual features. Further, our LG-MOT exhibits strong cross-domain generalizability. The dataset and code will be available at ~\url{https://github.com/WesLee88524/LG-MOT}.

In this work, we study the problem of generating novel images from complex multimodal prompt sequences. While existing methods achieve promising results for text-to-image generation, they often struggle to capture fine-grained details from lengthy prompts and maintain contextual coherence within prompt sequences. Moreover, they often result in misaligned image generation for prompt sequences featuring multiple objects. To address this, we propose a Multi-modal Generation via Cross-Modal In-Context Learning (MGCC) method that generates novel images from complex multimodal prompt sequences by leveraging the combined capabilities of large language models (LLMs) and diffusion models. Our MGCC comprises a novel Cross-Modal Refinement module to explicitly learn cross-modal dependencies between the text and image in the LLM embedding space, and a contextual object grounding module to generate object bounding boxes specifically targeting scenes with multiple objects. Our MGCC demonstrates a diverse range of multimodal capabilities, like novel image generation, the facilitation of multimodal dialogue, and generation of texts. Experimental evaluations on two benchmark datasets, demonstrate the effectiveness of our method. On Visual Story Generation (VIST) dataset with multimodal inputs, our MGCC achieves a CLIP Similarity score of $0.652$ compared to SOTA GILL $0.641$. Similarly, on Visual Dialogue Context (VisDial) having lengthy dialogue sequences, our MGCC achieves an impressive CLIP score of $0.660$, largely outperforming existing SOTA method scoring $0.645$. Code: https://github.com/VIROBO-15/MGCC, Comment: Technical Report

Recent advancements in Large Language Models (LLMs) have led to the development of Video Large Multi-modal Models (Video-LMMs) that can handle a wide range of video understanding tasks. These models have the potential to be deployed in real-world applications such as robotics, AI assistants, medical surgery, and autonomous vehicles. The widespread adoption of Video-LMMs in our daily lives underscores the importance of ensuring and evaluating their robust performance in mirroring human-like reasoning and interaction capabilities in complex, real-world contexts. However, existing benchmarks for Video-LMMs primarily focus on general video comprehension abilities and neglect assessing their reasoning capabilities over complex videos in the real-world context, and robustness of these models through the lens of user prompts as text queries. In this paper, we present the Complex Video Reasoning and Robustness Evaluation Suite (CVRR-ES), a novel benchmark that comprehensively assesses the performance of Video-LMMs across 11 diverse real-world video dimensions. We evaluate 9 recent models, including both open-source and closed-source variants, and find that most of the Video-LMMs, especially open-source ones, struggle with robustness and reasoning when dealing with complex videos. Based on our analysis, we develop a training-free Dual-Step Contextual Prompting (DSCP) technique to enhance the performance of existing Video-LMMs. Our findings provide valuable insights for building the next generation of human-centric AI systems with advanced robustness and reasoning capabilities. Our dataset and code are publicly available at: https://mbzuai-oryx.github.io/CVRR-Evaluation-Suite/., Comment: Technical report

Large-scale vision 2D vision language models, such as CLIP can be aligned with a 3D encoder to learn generalizable (open-vocabulary) 3D vision models. However, current methods require supervised pre-training for such alignment, and the performance of such 3D zero-shot models remains sub-optimal for real-world adaptation. In this work, we propose an optimization framework: Cross-MoST: Cross-Modal Self-Training, to improve the label-free classification performance of a zero-shot 3D vision model by simply leveraging unlabeled 3D data and their accompanying 2D views. We propose a student-teacher framework to simultaneously process 2D views and 3D point clouds and generate joint pseudo labels to train a classifier and guide cross-model feature alignment. Thereby we demonstrate that 2D vision language models such as CLIP can be used to complement 3D representation learning to improve classification performance without the need for expensive class annotations. Using synthetic and real-world 3D datasets, we further demonstrate that Cross-MoST enables efficient cross-modal knowledge exchange resulting in both image and point cloud modalities learning from each other's rich representations., Comment: To be published in Workshop for Learning 3D with Multi-View Supervision (3DMV) at CVPR 2024

Single source domain generalization (SDG) holds promise for more reliable and consistent image segmentation across real-world clinical settings particularly in the medical domain, where data privacy and acquisition cost constraints often limit the availability of diverse datasets. Depending solely on visual features hampers the model's capacity to adapt effectively to various domains, primarily because of the presence of spurious correlations and domain-specific characteristics embedded within the image features. Incorporating text features alongside visual features is a potential solution to enhance the model's understanding of the data, as it goes beyond pixel-level information to provide valuable context. Textual cues describing the anatomical structures, their appearances, and variations across various imaging modalities can guide the model in domain adaptation, ultimately contributing to more robust and consistent segmentation. In this paper, we propose an approach that explicitly leverages textual information by incorporating a contrastive learning mechanism guided by the text encoder features to learn a more robust feature representation. We assess the effectiveness of our text-guided contrastive feature alignment technique in various scenarios, including cross-modality, cross-sequence, and cross-site settings for different segmentation tasks. Our approach achieves favorable performance against existing methods in literature. Our code and model weights are available at https://github.com/ShahinaKK/LG_SDG.git., Comment: Accepted at ISBI2024

Composed video retrieval (CoVR) is a challenging problem in computer vision which has recently highlighted the integration of modification text with visual queries for more sophisticated video search in large databases. Existing works predominantly rely on visual queries combined with modification text to distinguish relevant videos. However, such a strategy struggles to fully preserve the rich query-specific context in retrieved target videos and only represents the target video using visual embedding. We introduce a novel CoVR framework that leverages detailed language descriptions to explicitly encode query-specific contextual information and learns discriminative embeddings of vision only, text only and vision-text for better alignment to accurately retrieve matched target videos. Our proposed framework can be flexibly employed for both composed video (CoVR) and image (CoIR) retrieval tasks. Experiments on three datasets show that our approach obtains state-of-the-art performance for both CovR and zero-shot CoIR tasks, achieving gains as high as around 7% in terms of recall@K=1 score. Our code, models, detailed language descriptions for WebViD-CoVR dataset are available at \url{https://github.com/OmkarThawakar/composed-video-retrieval}, Comment: CVPR-2024

Recent studies have demonstrated the effectiveness of Large Language Models (LLMs) as reasoning modules that can deconstruct complex tasks into more manageable sub-tasks, particularly when applied to visual reasoning tasks for images. In contrast, this paper introduces a Video Understanding and Reasoning Framework (VURF) based on the reasoning power of LLMs. Ours is a novel approach to extend the utility of LLMs in the context of video tasks, leveraging their capacity to generalize from minimal input and output demonstrations within a contextual framework. By presenting LLMs with pairs of instructions and their corresponding high-level programs, we harness their contextual learning capabilities to generate executable visual programs for video understanding. To enhance program's accuracy and robustness, we implement two important strategies. Firstly, we employ a feedback-generation approach, powered by GPT-3.5, to rectify errors in programs utilizing unsupported functions. Secondly, taking motivation from recent works on self refinement of LLM outputs, we introduce an iterative procedure for improving the quality of the in-context examples by aligning the initial outputs to the outputs that would have been generated had the LLM not been bound by the structure of the in-context examples. Our results on several video-specific tasks, including visual QA, video anticipation, pose estimation and multi-video QA illustrate the efficacy of these enhancements in improving the performance of visual programming approaches for video tasks.

Self-supervised representation learning has been highly promising for histopathology image analysis with numerous approaches leveraging their patient-slide-patch hierarchy to learn better representations. In this paper, we explore how the combination of domain specific natural language information with such hierarchical visual representations can benefit rich representation learning for medical image tasks. Building on automated language description generation for features visible in histopathology images, we present a novel language-tied self-supervised learning framework, Hierarchical Language-tied Self-Supervision (HLSS) for histopathology images. We explore contrastive objectives and granular language description based text alignment at multiple hierarchies to inject language modality information into the visual representations. Our resulting model achieves state-of-the-art performance on two medical imaging benchmarks, OpenSRH and TCGA datasets. Our framework also provides better interpretability with our language aligned representation space. Code is available at https://github.com/Hasindri/HLSS., Comment: 13 pages and 5 figures

Recent advances in unsupervised learning have demonstrated the ability of large vision models to achieve promising results on downstream tasks by pre-training on large amount of unlabelled data. Such pre-training techniques have also been explored recently in the remote sensing domain due to the availability of large amount of unlabelled data. Different from standard natural image datasets, remote sensing data is acquired from various sensor technologies and exhibit diverse range of scale variations as well as modalities. Existing satellite image pre-training methods either ignore the scale information present in the remote sensing imagery or restrict themselves to use only a single type of data modality. In this paper, we re-visit transformers pre-training and leverage multi-scale information that is effectively utilized with multiple modalities. Our proposed approach, named SatMAE++, performs multi-scale pre-training and utilizes convolution based upsampling blocks to reconstruct the image at higher scales making it extensible to include more scales. Compared to existing works, the proposed SatMAE++ with multi-scale pre-training is equally effective for both optical as well as multi-spectral imagery. Extensive experiments on six datasets reveal the merits of proposed contributions, leading to state-of-the-art performance on all datasets. SatMAE++ achieves mean average precision (mAP) gain of 2.5\% for multi-label classification task on BigEarthNet dataset. Our code and pre-trained models are available at \url{https://github.com/techmn/satmae_pp}., Comment: Accepted at CVPR 2024

Given the large-scale multi-modal training of recent vision-based models and their generalization capabilities, understanding the extent of their robustness is critical for their real-world deployment. In this work, we evaluate the resilience of current vision-based models against diverse object-to-background context variations. The majority of robustness evaluation methods have introduced synthetic datasets to induce changes to object characteristics (viewpoints, scale, color) or utilized image transformation techniques (adversarial changes, common corruptions) on real images to simulate shifts in distributions. Recent works have explored leveraging large language models and diffusion models to generate changes in the background. However, these methods either lack in offering control over the changes to be made or distort the object semantics, making them unsuitable for the task. Our method, on the other hand, can induce diverse object-to-background changes while preserving the original semantics and appearance of the object. To achieve this goal, we harness the generative capabilities of text-to-image, image-to-text, and image-to-segment models to automatically generate a broad spectrum of object-to-background changes. We induce both natural and adversarial background changes by either modifying the textual prompts or optimizing the latents and textual embedding of text-to-image models. We produce various versions of standard vision datasets (ImageNet, COCO), incorporating either diverse and realistic backgrounds into the images or introducing color, texture, and adversarial changes in the background. We conduct extensive experiments to analyze the robustness of vision-based models against object-to-background context variations across diverse tasks. Code https://github.com/Muhammad-Huzaifaa/ObjectCompose.

Volumetric medical segmentation is a critical component of 3D medical image analysis that delineates different semantic regions. Deep neural networks have significantly improved volumetric medical segmentation, but they generally require large-scale annotated data to achieve better performance, which can be expensive and prohibitive to obtain. To address this limitation, existing works typically perform transfer learning or design dedicated pretraining-finetuning stages to learn representative features. However, the mismatch between the source and target domain can make it challenging to learn optimal representation for volumetric data, while the multi-stage training demands higher compute as well as careful selection of stage-specific design choices. In contrast, we propose a universal training framework called MedContext that is architecture-agnostic and can be incorporated into any existing training framework for 3D medical segmentation. Our approach effectively learns self supervised contextual cues jointly with the supervised voxel segmentation task without requiring large-scale annotated volumetric medical data or dedicated pretraining-finetuning stages. The proposed approach induces contextual knowledge in the network by learning to reconstruct the missing organ or parts of an organ in the output segmentation space. The effectiveness of MedContext is validated across multiple 3D medical datasets and four state-of-the-art model architectures. Our approach demonstrates consistent gains in segmentation performance across datasets and different architectures even in few-shot data scenarios. Our code and pretrained models are available at https://github.com/hananshafi/MedContext, Comment: Accepted at MICCAI 2024

Foundational vision-language models such as CLIP are becoming a new paradigm in vision, due to their excellent generalization abilities. However, adapting these models for downstream tasks while maintaining their generalization remains a challenge. In literature, one branch of methods adapts CLIP by learning prompts using visual information. While effective, most of these works require labeled data which is not practical, and often struggle to generalize towards new datasets due to over-fitting on the source data. An alternative approach resorts to training-free methods by generating class descriptions from large language models (LLMs) and perform prompt ensembling. However, these methods often generate class specific prompts that cannot be transferred to other classes, which incur higher costs by generating LLM descriptions for each class separately. In this work, we propose to combine the strengths of these both streams of methods by learning prompts using only text data derived from LLMs. As supervised training of prompts is not trivial due to absence of images, we develop a training approach that allows prompts to extract rich contextual knowledge from LLM data. Moreover, with LLM contextual data mapped within the learned prompts, it enables zero-shot transfer of prompts to new classes and datasets potentially cutting the LLM prompt engineering cost. To the best of our knowledge, this is the first work that learns generalized prompts using text only data. We perform extensive evaluations on 4 benchmarks where our method improves over prior ensembling works while being competitive to those utilizing labeled images. Our code and pre-trained models are available at https://github.com/muzairkhattak/ProText., Comment: Project Page: https://muzairkhattak.github.io/ProText/

Video grounding aims to localize a spatio-temporal section in a video corresponding to an input text query. This paper addresses a critical limitation in current video grounding methodologies by introducing an Open-Vocabulary Spatio-Temporal Video Grounding task. Unlike prevalent closed-set approaches that struggle with open-vocabulary scenarios due to limited training data and predefined vocabularies, our model leverages pre-trained representations from foundational spatial grounding models. This empowers it to effectively bridge the semantic gap between natural language and diverse visual content, achieving strong performance in closed-set and open-vocabulary settings. Our contributions include a novel spatio-temporal video grounding model, surpassing state-of-the-art results in closed-set evaluations on multiple datasets and demonstrating superior performance in open-vocabulary scenarios. Notably, the proposed model outperforms state-of-the-art methods in closed-set settings on VidSTG (Declarative and Interrogative) and HC-STVG (V1 and V2) datasets. Furthermore, in open-vocabulary evaluations on HC-STVG V1 and YouCook-Interactions, our model surpasses the recent best-performing models by $4.88$ m_vIoU and $1.83\%$ accuracy, demonstrating its efficacy in handling diverse linguistic and visual concepts for improved video understanding. Our codes will be publicly released.

In this work, we address the challenging and emergent problem of novel object detection (NOD), focusing on the accurate detection of both known and novel object categories during inference. Traditional object detection algorithms are inherently closed-set, limiting their capability to handle NOD. We present a novel approach to transform existing closed-set detectors into open-set detectors. This transformation is achieved by leveraging the complementary strengths of pre-trained foundational models, specifically CLIP and SAM, through our cooperative mechanism. Furthermore, by integrating this mechanism with state-of-the-art open-set detectors such as GDINO, we establish new benchmarks in object detection performance. Our method achieves 17.42 mAP in novel object detection and 42.08 mAP for known objects on the challenging LVIS dataset. Adapting our approach to the COCO OVD split, we surpass the current state-of-the-art by a margin of 7.2 $ \text{AP}_{50} $ for novel classes. Our code is available at https://rohit901.github.io/coop-foundation-models/ ., Comment: Accepted at WACV 2025

The promising zero-shot generalization of vision-language models such as CLIP has led to their adoption using prompt learning for numerous downstream tasks. Previous works have shown test-time prompt tuning using entropy minimization to adapt text prompts for unseen domains. While effective, this overlooks the key cause for performance degradation to unseen domains -- distribution shift. In this work, we explicitly handle this problem by aligning the out-of-distribution (OOD) test sample statistics to those of the source data using prompt tuning. We use a single test sample to adapt multi-modal prompts at test time by minimizing the feature distribution shift to bridge the gap in the test domain. Evaluating against the domain generalization benchmark, our method improves zero-shot top- 1 accuracy beyond existing prompt-learning techniques, with a 3.08% improvement over the baseline MaPLe. In cross-dataset generalization with unseen categories across 10 datasets, our method improves consistently across all datasets compared to the existing state-of-the-art. Our source code and models are available at https://jameelhassan.github.io/promptalign., Comment: Accepted to NeurIPS 2023

Vision-language models (VLMs) classify the query video by calculating a similarity score between the visual features and text-based class label representations. Recently, large language models (LLMs) have been used to enrich the text-based class labels by enhancing the descriptiveness of the class names. However, these improvements are restricted to the text-based classifier only, and the query visual features are not considered. In this paper, we propose a framework which combines pre-trained discriminative VLMs with pre-trained generative video-to-text and text-to-text models. We introduce two key modifications to the standard zero-shot setting. First, we propose language-guided visual feature enhancement and employ a video-to-text model to convert the query video to its descriptive form. The resulting descriptions contain vital visual cues of the query video, such as what objects are present and their spatio-temporal interactions. These descriptive cues provide additional semantic knowledge to VLMs to enhance their zeroshot performance. Second, we propose video-specific prompts to LLMs to generate more meaningful descriptions to enrich class label representations. Specifically, we introduce prompt techniques to create a Tree Hierarchy of Categories for class names, offering a higher-level action context for additional visual cues, We demonstrate the effectiveness of our approach in video understanding across three different zero-shot settings: 1) video action recognition, 2) video-to-text and textto-video retrieval, and 3) time-sensitive video tasks. Consistent improvements across multiple benchmarks and with various VLMs demonstrate the effectiveness of our proposed framework. Our code will be made publicly available.

Diffusion-based generative models have significantly advanced text-to-image generation but encounter challenges when processing lengthy and intricate text prompts describing complex scenes with multiple objects. While excelling in generating images from short, single-object descriptions, these models often struggle to faithfully capture all the nuanced details within longer and more elaborate textual inputs. In response, we present a novel approach leveraging Large Language Models (LLMs) to extract critical components from text prompts, including bounding box coordinates for foreground objects, detailed textual descriptions for individual objects, and a succinct background context. These components form the foundation of our layout-to-image generation model, which operates in two phases. The initial Global Scene Generation utilizes object layouts and background context to create an initial scene but often falls short in faithfully representing object characteristics as specified in the prompts. To address this limitation, we introduce an Iterative Refinement Scheme that iteratively evaluates and refines box-level content to align them with their textual descriptions, recomposing objects as needed to ensure consistency. Our evaluation on complex prompts featuring multiple objects demonstrates a substantial improvement in recall compared to baseline diffusion models. This is further validated by a user study, underscoring the efficacy of our approach in generating coherent and detailed scenes from intricate textual inputs., Comment: Accepted at ICLR 2024

Face anti-spoofing (FAS) or presentation attack detection is an essential component of face recognition systems deployed in security-critical applications. Existing FAS methods have poor generalizability to unseen spoof types, camera sensors, and environmental conditions. Recently, vision transformer (ViT) models have been shown to be effective for the FAS task due to their ability to capture long-range dependencies among image patches. However, adaptive modules or auxiliary loss functions are often required to adapt pre-trained ViT weights learned on large-scale datasets such as ImageNet. In this work, we first show that initializing ViTs with multimodal (e.g., CLIP) pre-trained weights improves generalizability for the FAS task, which is in line with the zero-shot transfer capabilities of vision-language pre-trained (VLP) models. We then propose a novel approach for robust cross-domain FAS by grounding visual representations with the help of natural language. Specifically, we show that aligning the image representation with an ensemble of class descriptions (based on natural language semantics) improves FAS generalizability in low-data regimes. Finally, we propose a multimodal contrastive learning strategy to boost feature generalization further and bridge the gap between source and target domains. Extensive experiments on three standard protocols demonstrate that our method significantly outperforms the state-of-the-art methods, achieving better zero-shot transfer performance than five-shot transfer of adaptive ViTs. Code: https://github.com/koushiksrivats/FLIP, Comment: Accepted to ICCV-2023. Project Page: https://koushiksrivats.github.io/FLIP/

Large-scale pre-trained Vision Language Models (VLMs) have proven effective for zero-shot classification. Despite the success, most traditional VLMs-based methods are restricted by the assumption of partial source supervision or ideal vocabularies, which rarely satisfy the open-world scenario. In this paper, we aim at a more challenging setting, Realistic Zero-Shot Classification, which assumes no annotation but instead a broad vocabulary. To address this challenge, we propose the Self Structural Semantic Alignment (S^3A) framework, which extracts the structural semantic information from unlabeled data while simultaneously self-learning. Our S^3A framework adopts a unique Cluster-Vote-Prompt-Realign (CVPR) algorithm, which iteratively groups unlabeled data to derive structural semantics for pseudo-supervision. Our CVPR process includes iterative clustering on images, voting within each cluster to identify initial class candidates from the vocabulary, generating discriminative prompts with large language models to discern confusing candidates, and realigning images and the vocabulary as structural semantic alignment. Finally, we propose to self-learn the CLIP image encoder with both individual and structural semantic alignment through a teacher-student learning strategy. Our comprehensive experiments across various generic and fine-grained benchmarks demonstrate that the S^3A method offers substantial improvements over existing VLMs-based approaches, achieving a more than 15% accuracy improvement over CLIP on average. Our codes, models, and prompts are publicly released at https://github.com/sheng-eatamath/S3A., Comment: AAAI'24

Vision systems to see and reason about the compositional nature of visual scenes are fundamental to understanding our world. The complex relations between objects and their locations, ambiguities, and variations in the real-world environment can be better described in human language, naturally governed by grammatical rules and other modalities such as audio and depth. The models learned to bridge the gap between such modalities coupled with large-scale training data facilitate contextual reasoning, generalization, and prompt capabilities at test time. These models are referred to as foundational models. The output of such models can be modified through human-provided prompts without retraining, e.g., segmenting a particular object by providing a bounding box, having interactive dialogues by asking questions about an image or video scene or manipulating the robot's behavior through language instructions. In this survey, we provide a comprehensive review of such emerging foundational models, including typical architecture designs to combine different modalities (vision, text, audio, etc), training objectives (contrastive, generative), pre-training datasets, fine-tuning mechanisms, and the common prompting patterns; textual, visual, and heterogeneous. We discuss the open challenges and research directions for foundational models in computer vision, including difficulties in their evaluations and benchmarking, gaps in their real-world understanding, limitations of their contextual understanding, biases, vulnerability to adversarial attacks, and interpretability issues. We review recent developments in this field, covering a wide range of applications of foundation models systematically and comprehensively. A comprehensive list of foundational models studied in this work is available at \url{https://github.com/awaisrauf/Awesome-CV-Foundational-Models}., Comment: Project page: https://github.com/awaisrauf/Awesome-CV-Foundational-Models

It is imperative to ensure the robustness of deep learning models in critical applications such as, healthcare. While recent advances in deep learning have improved the performance of volumetric medical image segmentation models, these models cannot be deployed for real-world applications immediately due to their vulnerability to adversarial attacks. We present a 3D frequency domain adversarial attack for volumetric medical image segmentation models and demonstrate its advantages over conventional input or voxel domain attacks. Using our proposed attack, we introduce a novel frequency domain adversarial training approach for optimizing a robust model against voxel and frequency domain attacks. Moreover, we propose frequency consistency loss to regulate our frequency domain adversarial training that achieves a better tradeoff between model's performance on clean and adversarial samples. Code is publicly available at https://github.com/asif-hanif/vafa., Comment: This paper has been accepted in MICCAI 2023 conference

Prompt learning has emerged as an efficient alternative for fine-tuning foundational models, such as CLIP, for various downstream tasks. Conventionally trained using the task-specific objective, i.e., cross-entropy loss, prompts tend to overfit downstream data distributions and find it challenging to capture task-agnostic general features from the frozen CLIP. This leads to the loss of the model's original generalization capability. To address this issue, our work introduces a self-regularization framework for prompting called PromptSRC (Prompting with Self-regulating Constraints). PromptSRC guides the prompts to optimize for both task-specific and task-agnostic general representations using a three-pronged approach by: (a) regulating prompted representations via mutual agreement maximization with the frozen model, (b) regulating with self-ensemble of prompts over the training trajectory to encode their complementary strengths, and (c) regulating with textual diversity to mitigate sample diversity imbalance with the visual branch. To the best of our knowledge, this is the first regularization framework for prompt learning that avoids overfitting by jointly attending to pre-trained model features, the training trajectory during prompting, and the textual diversity. PromptSRC explicitly steers the prompts to learn a representation space that maximizes performance on downstream tasks without compromising CLIP generalization. We perform extensive experiments on 4 benchmarks where PromptSRC overall performs favorably well compared to the existing methods. Our code and pre-trained models are publicly available at: https://github.com/muzairkhattak/PromptSRC., Comment: Accepted to ICCV-2023. Camera-Ready version. Project page: https://muzairkhattak.github.io/PromptSRC/

Recent video recognition models utilize Transformer models for long-range spatio-temporal context modeling. Video transformer designs are based on self-attention that can model global context at a high computational cost. In comparison, convolutional designs for videos offer an efficient alternative but lack long-range dependency modeling. Towards achieving the best of both designs, this work proposes Video-FocalNet, an effective and efficient architecture for video recognition that models both local and global contexts. Video-FocalNet is based on a spatio-temporal focal modulation architecture that reverses the interaction and aggregation steps of self-attention for better efficiency. Further, the aggregation step and the interaction step are both implemented using efficient convolution and element-wise multiplication operations that are computationally less expensive than their self-attention counterparts on video representations. We extensively explore the design space of focal modulation-based spatio-temporal context modeling and demonstrate our parallel spatial and temporal encoding design to be the optimal choice. Video-FocalNets perform favorably well against the state-of-the-art transformer-based models for video recognition on five large-scale datasets (Kinetics-400, Kinetics-600, SS-v2, Diving-48, and ActivityNet-1.3) at a lower computational cost. Our code/models are released at https://github.com/TalalWasim/Video-FocalNets., Comment: Accepted to ICCV-2023. Camera-Ready version. Project page: https://TalalWasim.github.io/Video-FocalNets/

The success of deep learning based face recognition systems has given rise to serious privacy concerns due to their ability to enable unauthorized tracking of users in the digital world. Existing methods for enhancing privacy fail to generate naturalistic images that can protect facial privacy without compromising user experience. We propose a novel two-step approach for facial privacy protection that relies on finding adversarial latent codes in the low-dimensional manifold of a pretrained generative model. The first step inverts the given face image into the latent space and finetunes the generative model to achieve an accurate reconstruction of the given image from its latent code. This step produces a good initialization, aiding the generation of high-quality faces that resemble the given identity. Subsequently, user-defined makeup text prompts and identity-preserving regularization are used to guide the search for adversarial codes in the latent space. Extensive experiments demonstrate that faces generated by our approach have stronger black-box transferability with an absolute gain of 12.06% over the state-of-the-art facial privacy protection approach under the face verification task. Finally, we demonstrate the effectiveness of the proposed approach for commercial face recognition systems. Our code is available at https://github.com/fahadshamshad/Clip2Protect., Comment: Accepted in CVPR 2023. Project page: https://fahadshamshad.github.io/Clip2Protect/

Hybrid volumetric medical image segmentation models, combining the advantages of local convolution and global attention, have recently received considerable attention. While mainly focusing on architectural modifications, most existing hybrid approaches still use conventional data-independent weight initialization schemes which restrict their performance due to ignoring the inherent volumetric nature of the medical data. To address this issue, we propose a learnable weight initialization approach that utilizes the available medical training data to effectively learn the contextual and structural cues via the proposed self-supervised objectives. Our approach is easy to integrate into any hybrid model and requires no external training data. Experiments on multi-organ and lung cancer segmentation tasks demonstrate the effectiveness of our approach, leading to state-of-the-art segmentation performance. Our proposed data-dependent initialization approach performs favorably as compared to the Swin-UNETR model pretrained using large-scale datasets on multi-organ segmentation task. Our source code and models are available at: https://github.com/ShahinaKK/LWI-VMS., Comment: Accepted at Elsevier AI in Medicine Journal

Adopting contrastive image-text pretrained models like CLIP towards video classification has gained attention due to its cost-effectiveness and competitive performance. However, recent works in this area face a trade-off. Finetuning the pretrained model to achieve strong supervised performance results in low zero-shot generalization. Similarly, freezing the backbone to retain zero-shot capability causes significant drop in supervised accuracy. Because of this, recent works in literature typically train separate models for supervised and zero-shot action recognition. In this work, we propose a multimodal prompt learning scheme that works to balance the supervised and zero-shot performance under a single unified training. Our prompting approach on the vision side caters for three aspects: 1) Global video-level prompts to model the data distribution; 2) Local frame-level prompts to provide per-frame discriminative conditioning; and 3) a summary prompt to extract a condensed video representation. Additionally, we define a prompting scheme on the text side to augment the textual context. Through this prompting scheme, we can achieve state-of-the-art zero-shot performance on Kinetics-600, HMDB51 and UCF101 while remaining competitive in the supervised setting. By keeping the pretrained backbone frozen, we optimize a much lower number of parameters and retain the existing general representation which helps achieve the strong zero-shot performance. Our codes/models are released at https://github.com/TalalWasim/Vita-CLIP., Comment: Accepted at CVPR-2023. Codes/models available at https://github.com/TalalWasim/Vita-CLIP

The transferability of adversarial perturbations between image models has been extensively studied. In this case, an attack is generated from a known surrogate \eg, the ImageNet trained model, and transferred to change the decision of an unknown (black-box) model trained on an image dataset. However, attacks generated from image models do not capture the dynamic nature of a moving object or a changing scene due to a lack of temporal cues within image models. This leads to reduced transferability of adversarial attacks from representation-enriched \emph{image} models such as Supervised Vision Transformers (ViTs), Self-supervised ViTs (\eg, DINO), and Vision-language models (\eg, CLIP) to black-box \emph{video} models. In this work, we induce dynamic cues within the image models without sacrificing their original performance on images. To this end, we optimize \emph{temporal prompts} through frozen image models to capture motion dynamics. Our temporal prompts are the result of a learnable transformation that allows optimizing for temporal gradients during an adversarial attack to fool the motion dynamics. Specifically, we introduce spatial (image) and temporal (video) cues within the same source model through task-specific prompts. Attacking such prompts maximizes the adversarial transferability from image-to-video and image-to-image models using the attacks designed for image models. Our attack results indicate that the attacker does not need specialized architectures, \eg, divided space-time attention, 3D convolutions, or multi-view convolution networks for different data modalities. Image models are effective surrogates to optimize an adversarial attack to fool black-box models in a changing environment over time. Code is available at https://bit.ly/3Xd9gRQ, Comment: International Conference on Learning Representations (ICLR'23), Code:https://bit.ly/3Xd9gRQ

Adversarial training is an effective approach to make deep neural networks robust against adversarial attacks. Recently, different adversarial training defenses are proposed that not only maintain a high clean accuracy but also show significant robustness against popular and well studied adversarial attacks such as PGD. High adversarial robustness can also arise if an attack fails to find adversarial gradient directions, a phenomenon known as `gradient masking'. In this work, we analyse the effect of label smoothing on adversarial training as one of the potential causes of gradient masking. We then develop a guided mechanism to avoid local minima during attack optimization, leading to a novel attack dubbed Guided Projected Gradient Attack (G-PGA). Our attack approach is based on a `match and deceive' loss that finds optimal adversarial directions through guidance from a surrogate model. Our modified attack does not require random restarts, large number of attack iterations or search for an optimal step-size. Furthermore, our proposed G-PGA is generic, thus it can be combined with an ensemble attack strategy as we demonstrate for the case of Auto-Attack, leading to efficiency and convergence speed improvements. More than an effective attack, G-PGA can be used as a diagnostic tool to reveal elusive robustness due to gradient masking in adversarial defenses., Comment: IEEE Transactions on Neural Networks and Learning Systems (TNNLS)

Although existing semi-supervised learning models achieve remarkable success in learning with unannotated in-distribution data, they mostly fail to learn on unlabeled data sampled from novel semantic classes due to their closed-set assumption. In this work, we target a pragmatic but under-explored Generalized Novel Category Discovery (GNCD) setting. The GNCD setting aims to categorize unlabeled training data coming from known and novel classes by leveraging the information of partially labeled known classes. We propose a two-stage Contrastive Affinity Learning method with auxiliary visual Prompts, dubbed PromptCAL, to address this challenging problem. Our approach discovers reliable pairwise sample affinities to learn better semantic clustering of both known and novel classes for the class token and visual prompts. First, we propose a discriminative prompt regularization loss to reinforce semantic discriminativeness of prompt-adapted pre-trained vision transformer for refined affinity relationships.Besides, we propose contrastive affinity learning to calibrate semantic representations based on our iterative semi-supervised affinity graph generation method for semantically-enhanced supervision. Extensive experimental evaluation demonstrates that our PromptCAL method is more effective in discovering novel classes even with limited annotations and surpasses the current state-of-the-art on generic and fine-grained benchmarks (e.g., with nearly 11% gain on CUB-200, and 9% on ImageNet-100) on overall accuracy. Our code is available at https://github.com/sheng-eatamath/PromptCAL., Comment: Accepted by CVPR2023

Vision Transformer (ViT), a radically different architecture than convolutional neural networks offers multiple advantages including design simplicity, robustness and state-of-the-art performance on many vision tasks. However, in contrast to convolutional neural networks, Vision Transformer lacks inherent inductive biases. Therefore, successful training of such models is mainly attributed to pre-training on large-scale datasets such as ImageNet with 1.2M or JFT with 300M images. This hinders the direct adaption of Vision Transformer for small-scale datasets. In this work, we show that self-supervised inductive biases can be learned directly from small-scale datasets and serve as an effective weight initialization scheme for fine-tuning. This allows to train these models without large-scale pre-training, changes to model architecture or loss functions. We present thorough experiments to successfully train monolithic and non-monolithic Vision Transformers on five small datasets including CIFAR10/100, CINIC10, SVHN, Tiny-ImageNet and two fine-grained datasets: Aircraft and Cars. Our approach consistently improves the performance of Vision Transformers while retaining their properties such as attention to salient regions and higher robustness. Our codes and pre-trained models are available at: https://github.com/hananshafi/vits-for-small-scale-datasets., Comment: Accepted at BMVC 2022

In the recent past, several domain generalization (DG) methods have been proposed, showing encouraging performance, however, almost all of them build on convolutional neural networks (CNNs). There is little to no progress on studying the DG performance of vision transformers (ViTs), which are challenging the supremacy of CNNs on standard benchmarks, often built on i.i.d assumption. This renders the real-world deployment of ViTs doubtful. In this paper, we attempt to explore ViTs towards addressing the DG problem. Similar to CNNs, ViTs also struggle in out-of-distribution scenarios and the main culprit is overfitting to source domains. Inspired by the modular architecture of ViTs, we propose a simple DG approach for ViTs, coined as self-distillation for ViTs. It reduces the overfitting of source domains by easing the learning of input-output mapping problem through curating non-zero entropy supervisory signals for intermediate transformer blocks. Further, it does not introduce any new parameters and can be seamlessly plugged into the modular composition of different ViTs. We empirically demonstrate notable performance gains with different DG baselines and various ViT backbones in five challenging datasets. Moreover, we report favorable performance against recent state-of-the-art DG methods. Our code along with pre-trained models are publicly available at: https://github.com/maryam089/SDViT., Comment: 23 pages, 12 figures

Transferable adversarial attacks optimize adversaries from a pretrained surrogate model and known label space to fool the unknown black-box models. Therefore, these attacks are restricted by the availability of an effective surrogate model. In this work, we relax this assumption and propose Adversarial Pixel Restoration as a self-supervised alternative to train an effective surrogate model from scratch under the condition of no labels and few data samples. Our training approach is based on a min-max scheme which reduces overfitting via an adversarial objective and thus optimizes for a more generalizable surrogate model. Our proposed attack is complimentary to the adversarial pixel restoration and is independent of any task specific objective as it can be launched in a self-supervised manner. We successfully demonstrate the adversarial transferability of our approach to Vision Transformers as well as Convolutional Neural Networks for the tasks of classification, object detection, and video segmentation. Our training approach improves the transferability of the baseline unsupervised training method by 16.4% on ImageNet val. set. Our codes & pre-trained surrogate models are available at: https://github.com/HashmatShadab/APR, Comment: Accepted at BMVC'22 (Oral)

In this paper, we propose self-supervised training for video transformers using unlabeled video data. From a given video, we create local and global spatiotemporal views with varying spatial sizes and frame rates. Our self-supervised objective seeks to match the features of these different views representing the same video, to be invariant to spatiotemporal variations in actions. To the best of our knowledge, the proposed approach is the first to alleviate the dependency on negative samples or dedicated memory banks in Self-supervised Video Transformer (SVT). Further, owing to the flexibility of Transformer models, SVT supports slow-fast video processing within a single architecture using dynamically adjusted positional encoding and supports long-term relationship modeling along spatiotemporal dimensions. Our approach performs well on four action recognition benchmarks (Kinetics-400, UCF-101, HMDB-51, and SSv2) and converges faster with small batch sizes. Code: https://git.io/J1juJ, Comment: Accepted to CVPR '22

Vision transformers (ViTs) process input images as sequences of patches via self-attention; a radically different architecture than convolutional neural networks (CNNs). This makes it interesting to study the adversarial feature space of ViT models and their transferability. In particular, we observe that adversarial patterns found via conventional adversarial attacks show very \emph{low} black-box transferability even for large ViT models. We show that this phenomenon is only due to the sub-optimal attack procedures that do not leverage the true representation potential of ViTs. A deep ViT is composed of multiple blocks, with a consistent architecture comprising of self-attention and feed-forward layers, where each block is capable of independently producing a class token. Formulating an attack using only the last class token (conventional approach) does not directly leverage the discriminative information stored in the earlier tokens, leading to poor adversarial transferability of ViTs. Using the compositional nature of ViT models, we enhance transferability of existing attacks by introducing two novel strategies specific to the architecture of ViT models. (i) Self-Ensemble: We propose a method to find multiple discriminative pathways by dissecting a single ViT model into an ensemble of networks. This allows explicitly utilizing class-specific information at each ViT block. (ii) Token Refinement: We then propose to refine the tokens to further enhance the discriminative capacity at each block of ViT. Our token refinement systematically combines the class tokens with structural information preserved within the patch tokens., Comment: ICLR'22 (Spotlight), the first two authors contributed equally. Code: https://t.ly/hBbW

Vision transformers (ViT) have demonstrated impressive performance across various machine vision problems. These models are based on multi-head self-attention mechanisms that can flexibly attend to a sequence of image patches to encode contextual cues. An important question is how such flexibility in attending image-wide context conditioned on a given patch can facilitate handling nuisances in natural images e.g., severe occlusions, domain shifts, spatial permutations, adversarial and natural perturbations. We systematically study this question via an extensive set of experiments encompassing three ViT families and comparisons with a high-performing convolutional neural network (CNN). We show and analyze the following intriguing properties of ViT: (a) Transformers are highly robust to severe occlusions, perturbations and domain shifts, e.g., retain as high as 60% top-1 accuracy on ImageNet even after randomly occluding 80% of the image content. (b) The robust performance to occlusions is not due to a bias towards local textures, and ViTs are significantly less biased towards textures compared to CNNs. When properly trained to encode shape-based features, ViTs demonstrate shape recognition capability comparable to that of human visual system, previously unmatched in the literature. (c) Using ViTs to encode shape representation leads to an interesting consequence of accurate semantic segmentation without pixel-level supervision. (d) Off-the-shelf features from a single ViT model can be combined to create a feature ensemble, leading to high accuracy rates across a range of classification datasets in both traditional and few-shot learning paradigms. We show effective features of ViTs are due to flexible and dynamic receptive fields possible via the self-attention mechanism., Comment: NeurIPS'21 (Spotlight), Code: https://git.io/Js15X

Human learning benefits from multi-modal inputs that often appear as rich semantics (e.g., description of an object's attributes while learning about it). This enables us to learn generalizable concepts from very limited visual examples. However, current few-shot learning (FSL) methods use numerical class labels to denote object classes which do not provide rich semantic meanings about the learned concepts. In this work, we show that by using 'class-level' language descriptions, that can be acquired with minimal annotation cost, we can improve the FSL performance. Given a support set and queries, our main idea is to create a bottleneck visual feature (hybrid prototype) which is then used to generate language descriptions of the classes as an auxiliary task during training. We develop a Transformer based forward and backward encoding mechanism to relate visual and semantic tokens that can encode intricate relationships between the two modalities. Forcing the prototypes to retain semantic information about class description acts as a regularizer on the visual features, improving their generalization to novel classes at inference. Furthermore, this strategy imposes a human prior on the learned representations, ensuring that the model is faithfully relating visual and semantic concepts, thereby improving model interpretability. Our experiments on four datasets and ablation studies show the benefit of effectively modeling rich semantics for FSL., Comment: Accepted to 32nd British Machine Vision Conference (BMVC 2021)