Search

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

Unsupervised domain adaptive person re-identification has received significant attention due to its high practical value. In past years, by following the clustering and finetuning paradigm, researchers propose to utilize the teacher-student framework in their methods to decrease the domain gap between different person re-identification datasets. Inspired by recent teacher-student framework based methods, which try to mimic the human learning process either by making the student directly copy behavior from the teacher or selecting reliable learning materials, we propose to conduct further exploration to imitate the human learning process from different aspects, \textit{i.e.}, adaptively updating learning materials, selectively imitating teacher behaviors, and analyzing learning materials structures. The explored three components, collaborate together to constitute a new method for unsupervised domain adaptive person re-identification, which is called Human Learning Imitation framework. The experimental results on three benchmark datasets demonstrate the efficacy of our proposed method.

Transformers have shown great potential in computer vision tasks. A common belief is their attention-based token mixer module contributes most to their competence. However, recent works show the attention-based module in Transformers can be replaced by spatial MLPs and the resulted models still perform quite well. Based on this observation, we hypothesize that the general architecture of the Transformers, instead of the specific token mixer module, is more essential to the model's performance. To verify this, we deliberately replace the attention module in Transformers with an embarrassingly simple spatial pooling operator to conduct only basic token mixing. Surprisingly, we observe that the derived model, termed as PoolFormer, achieves competitive performance on multiple computer vision tasks. For example, on ImageNet-1K, PoolFormer achieves 82.1% top-1 accuracy, surpassing well-tuned Vision Transformer/MLP-like baselines DeiT-B/ResMLP-B24 by 0.3%/1.1% accuracy with 35%/52% fewer parameters and 50%/62% fewer MACs. The effectiveness of PoolFormer verifies our hypothesis and urges us to initiate the concept of "MetaFormer", a general architecture abstracted from Transformers without specifying the token mixer. Based on the extensive experiments, we argue that MetaFormer is the key player in achieving superior results for recent Transformer and MLP-like models on vision tasks. This work calls for more future research dedicated to improving MetaFormer instead of focusing on the token mixer modules. Additionally, our proposed PoolFormer could serve as a starting baseline for future MetaFormer architecture design. Code is available at https://github.com/sail-sg/poolformer., Comment: CVPR 2022 (Oral). Code: https://github.com/sail-sg/poolformer

Edge devices in federated learning usually have much more limited computation and communication resources compared to servers in a data center. Recently, advanced model compression methods, like the Lottery Ticket Hypothesis, have already been implemented on federated learning to reduce the model size and communication cost. However, Backdoor Attack can compromise its implementation in the federated learning scenario. The malicious edge device trains the client model with poisoned private data and uploads parameters to the center, embedding a backdoor to the global shared model after unwitting aggregative optimization. During the inference phase, the model with backdoors classifies samples with a certain trigger as one target category, while shows a slight decrease in inference accuracy to clean samples. In this work, we empirically demonstrate that Lottery Ticket models are equally vulnerable to backdoor attacks as the original dense models, and backdoor attacks can influence the structure of extracted tickets. Based on tickets' similarities between each other, we provide a feasible defense for federated learning against backdoor attacks on various datasets.

Unifying acoustic and linguistic representation learning has become increasingly crucial to transfer the knowledge learned on the abundance of high-resource language data for low-resource speech recognition. Existing approaches simply cascade pre-trained acoustic and language models to learn the transfer from speech to text. However, how to solve the representation discrepancy of speech and text is unexplored, which hinders the utilization of acoustic and linguistic information. Moreover, previous works simply replace the embedding layer of the pre-trained language model with the acoustic features, which may cause the catastrophic forgetting problem. In this work, we introduce Wav-BERT, a cooperative acoustic and linguistic representation learning method to fuse and utilize the contextual information of speech and text. Specifically, we unify a pre-trained acoustic model (wav2vec 2.0) and a language model (BERT) into an end-to-end trainable framework. A Representation Aggregation Module is designed to aggregate acoustic and linguistic representation, and an Embedding Attention Module is introduced to incorporate acoustic information into BERT, which can effectively facilitate the cooperation of two pre-trained models and thus boost the representation learning. Extensive experiments show that our Wav-BERT significantly outperforms the existing approaches and achieves state-of-the-art performance on low-resource speech recognition.

A key solution to temporal sentence grounding (TSG) exists in how to learn effective alignment between vision and language features extracted from an untrimmed video and a sentence description. Existing methods mainly leverage vanilla soft attention to perform the alignment in a single-step process. However, such single-step attention is insufficient in practice, since complicated relations between inter- and intra-modality are usually obtained through multi-step reasoning. In this paper, we propose an Iterative Alignment Network (IA-Net) for TSG task, which iteratively interacts inter- and intra-modal features within multiple steps for more accurate grounding. Specifically, during the iterative reasoning process, we pad multi-modal features with learnable parameters to alleviate the nowhere-to-attend problem of non-matched frame-word pairs, and enhance the basic co-attention mechanism in a parallel manner. To further calibrate the misaligned attention caused by each reasoning step, we also devise a calibration module following each attention module to refine the alignment knowledge. With such iterative alignment scheme, our IA-Net can robustly capture the fine-grained relations between vision and language domains step-by-step for progressively reasoning the temporal boundaries. Extensive experiments conducted on three challenging benchmarks demonstrate that our proposed model performs better than the state-of-the-arts., Comment: Accepted as a long paper in the main conference of EMNLP 2021

We address the problem of temporal sentence localization in videos (TSLV). Traditional methods follow a top-down framework which localizes the target segment with pre-defined segment proposals. Although they have achieved decent performance, the proposals are handcrafted and redundant. Recently, bottom-up framework attracts increasing attention due to its superior efficiency. It directly predicts the probabilities for each frame as a boundary. However, the performance of bottom-up model is inferior to the top-down counterpart as it fails to exploit the segment-level interaction. In this paper, we propose an Adaptive Proposal Generation Network (APGN) to maintain the segment-level interaction while speeding up the efficiency. Specifically, we first perform a foreground-background classification upon the video and regress on the foreground frames to adaptively generate proposals. In this way, the handcrafted proposal design is discarded and the redundant proposals are decreased. Then, a proposal consolidation module is further developed to enhance the semantic of the generated proposals. Finally, we locate the target moments with these generated proposals following the top-down framework. Extensive experiments on three challenging benchmarks show that our proposed APGN significantly outperforms previous state-of-the-art methods., Comment: Accepted as a long paper in the main conference of EMNLP 2021

Recent deep networks have convincingly demonstrated high capability in crowd counting, which is a critical task attracting widespread attention due to its various industrial applications. Despite such progress, trained data-dependent models usually can not generalize well to unseen scenarios because of the inherent domain shift. To facilitate this issue, this paper proposes a novel adversarial scoring network (ASNet) to gradually bridge the gap across domains from coarse to fine granularity. In specific, at the coarse-grained stage, we design a dual-discriminator strategy to adapt source domain to be close to the targets from the perspectives of both global and local feature space via adversarial learning. The distributions between two domains can thus be aligned roughly. At the fine-grained stage, we explore the transferability of source characteristics by scoring how similar the source samples are to target ones from multiple levels based on generative probability derived from coarse stage. Guided by these hierarchical scores, the transferable source features are properly selected to enhance the knowledge transfer during the adaptation process. With the coarse-to-fine design, the generalization bottleneck induced from the domain discrepancy can be effectively alleviated. Three sets of migration experiments show that the proposed methods achieve state-of-the-art counting performance compared with major unsupervised methods., Comment: Accepted by ACMMM2021

For an image query, unsupervised contrastive learning labels crops of the same image as positives, and other image crops as negatives. Although intuitive, such a native label assignment strategy cannot reveal the underlying semantic similarity between a query and its positives and negatives, and impairs performance, since some negatives are semantically similar to the query or even share the same semantic class as the query. In this work, we first prove that for contrastive learning, inaccurate label assignment heavily impairs its generalization for semantic instance discrimination, while accurate labels benefit its generalization. Inspired by this theory, we propose a novel self-labeling refinement approach for contrastive learning. It improves the label quality via two complementary modules: (i) self-labeling refinery (SLR) to generate accurate labels and (ii) momentum mixup (MM) to enhance similarity between query and its positive. SLR uses a positive of a query to estimate semantic similarity between a query and its positive and negatives, and combines estimated similarity with vanilla label assignment in contrastive learning to iteratively generate more accurate and informative soft labels. We theoretically show that our SLR can exactly recover the true semantic labels of label-corrupted data, and supervises networks to achieve zero prediction error on classification tasks. MM randomly combines queries and positives to increase semantic similarity between the generated virtual queries and their positives so as to improves label accuracy. Experimental results on CIFAR10, ImageNet, VOC and COCO show the effectiveness of our method. PyTorch code and model will be released online., Comment: under review. arXiv admin note: substantial text overlap with arXiv:1903.11680 by other authors

Graph-level representations are critical in various real-world applications, such as predicting the properties of molecules. But in practice, precise graph annotations are generally very expensive and time-consuming. To address this issue, graph contrastive learning constructs instance discrimination task which pulls together positive pairs (augmentation pairs of the same graph) and pushes away negative pairs (augmentation pairs of different graphs) for unsupervised representation learning. However, since for a query, its negatives are uniformly sampled from all graphs, existing methods suffer from the critical sampling bias issue, i.e., the negatives likely having the same semantic structure with the query, leading to performance degradation. To mitigate this sampling bias issue, in this paper, we propose a Prototypical Graph Contrastive Learning (PGCL) approach. Specifically, PGCL models the underlying semantic structure of the graph data via clustering semantically similar graphs into the same group, and simultaneously encourages the clustering consistency for different augmentations of the same graph. Then given a query, it performs negative sampling via drawing the graphs from those clusters that differ from the cluster of query, which ensures the semantic difference between query and its negative samples. Moreover, for a query, PGCL further reweights its negative samples based on the distance between their prototypes (cluster centroids) and the query prototype such that those negatives having moderate prototype distance enjoy relatively large weights. This reweighting strategy is proved to be more effective than uniform sampling. Experimental results on various graph benchmarks testify the advantages of our PGCL over state-of-the-art methods. Code is publicly available at https://github.com/ha-lins/PGCL., Comment: To appear in TNNLS 2022

The consistency of a response to a given post at semantic-level and emotional-level is essential for a dialogue system to deliver human-like interactions. However, this challenge is not well addressed in the literature, since most of the approaches neglect the emotional information conveyed by a post while generating responses. This article addresses this problem by proposing a unifed end-to-end neural architecture, which is capable of simultaneously encoding the semantics and the emotions in a post for generating more intelligent responses with appropriately expressed emotions. Extensive experiments on real-world data demonstrate that the proposed method outperforms the state-of-the-art methods in terms of both content coherence and emotion appropriateness., Comment: Accepted at CIKM 2019. arXiv admin note: substantial text overlap with arXiv:2011.07432

Most existing named entity recognition (NER) approaches are based on sequence labeling models, which focus on capturing the local context dependencies. However, the way of taking one sentence as input prevents the modeling of non-sequential global context, which is useful especially when local context information is limited or ambiguous. To this end, we propose a model called Global Context enhanced Document-level NER (GCDoc) to leverage global contextual information from two levels, i.e., both word and sentence. At word-level, a document graph is constructed to model a wider range of dependencies between words, then obtain an enriched contextual representation for each word via graph neural networks (GNN). To avoid the interference of noise information, we further propose two strategies. First we apply the epistemic uncertainty theory to find out tokens whose representations are less reliable, thereby helping prune the document graph. Then a selective auxiliary classifier is proposed to effectively learn the weight of edges in document graph and reduce the importance of noisy neighbour nodes. At sentence-level, for appropriately modeling wider context beyond single sentence, we employ a cross-sentence module which encodes adjacent sentences and fuses it with the current sentence representation via attention and gating mechanisms. Extensive experiments on two benchmark NER datasets (CoNLL 2003 and Ontonotes 5.0 English dataset) demonstrate the effectiveness of our proposed model. Our model reaches F1 score of 92.22 (93.40 with BERT) on CoNLL 2003 dataset and 88.32 (90.49 with BERT) on Ontonotes 5.0 dataset, achieving new state-of-the-art performance., Comment: 11 pages, 5 figures

Though deep neural network models exhibit outstanding performance for various applications, their large model size and extensive floating-point operations render deployment on mobile computing platforms a major challenge, and, in particular, on Internet of Things devices. One appealing solution is model quantization that reduces the model size and uses integer operations commonly supported by microcontrollers . To this end, a 1-bit quantized DNN model or deep binary neural network maximizes the memory efficiency, where each parameter in a BNN model has only 1-bit. In this paper, we propose a reconfigurable BNN (RBNN) to further amplify the memory efficiency for resource-constrained IoT devices. Generally, the RBNN can be reconfigured on demand to achieve any one of M (M>1) distinct tasks with the same parameter set, thus only a single task determines the memory requirements. In other words, the memory utilization is improved by times M. Our extensive experiments corroborate that up to seven commonly used tasks can co-exist (the value of M can be larger). These tasks with a varying number of classes have no or negligible accuracy drop-off on three binarized popular DNN architectures including VGG, ResNet, and ReActNet. The tasks span across different domains, e.g., computer vision and audio domains validated herein, with the prerequisite that the model architecture can serve those cross-domain tasks. To protect the intellectual property of an RBNN model, the reconfiguration can be controlled by both a user key and a device-unique root key generated by the intrinsic hardware fingerprint. By doing so, an RBNN model can only be used per paid user per authorized device, thus benefiting both the user and the model provider.

Crowd counting has drawn much attention due to its importance in safety-critical surveillance systems. Especially, deep neural network (DNN) methods have significantly reduced estimation errors for crowd counting missions. Recent studies have demonstrated that DNNs are vulnerable to adversarial attacks, i.e., normal images with human-imperceptible perturbations could mislead DNNs to make false predictions. In this work, we propose a robust attack strategy called Adversarial Patch Attack with Momentum (APAM) to systematically evaluate the robustness of crowd counting models, where the attacker's goal is to create an adversarial perturbation that severely degrades their performances, thus leading to public safety accidents (e.g., stampede accidents). Especially, the proposed attack leverages the extreme-density background information of input images to generate robust adversarial patches via a series of transformations (e.g., interpolation, rotation, etc.). We observe that by perturbing less than 6\% of image pixels, our attacks severely degrade the performance of crowd counting systems, both digitally and physically. To better enhance the adversarial robustness of crowd counting models, we propose the first regression model-based Randomized Ablation (RA), which is more sufficient than Adversarial Training (ADT) (Mean Absolute Error of RA is 5 lower than ADT on clean samples and 30 lower than ADT on adversarial examples). Extensive experiments on five crowd counting models demonstrate the effectiveness and generality of the proposed method. The supplementary materials and certificate retrained models are available at \url{https://www.dropbox.com/s/hc4fdx133vht0qb/ACM_MM2021_Supp.pdf?dl=0}, Comment: Accepted by ACM Multimedia 2021

Recently, attention-based encoder-decoder (AED) end-to-end (E2E) models have drawn more and more attention in the field of automatic speech recognition (ASR). AED models, however, still have drawbacks when deploying in commercial applications. Autoregressive beam search decoding makes it inefficient for high-concurrency applications. It is also inconvenient to integrate external word-level language models. The most important thing is that AED models are difficult for streaming recognition due to global attention mechanism. In this paper, we propose a novel framework, namely WNARS, using hybrid CTC-attention AED models and weighted finite-state transducers (WFST) to solve these problems together. We switch from autoregressive beam search to CTC branch decoding, which performs first-pass decoding with WFST in chunk-wise streaming way. The decoder branch then performs second-pass rescoring on the generated hypotheses non-autoregressively. On the AISHELL-1 task, our WNARS achieves a character error rate of 5.22% with 640ms latency, to the best of our knowledge, which is the state-of-the-art performance for online ASR. Further experiments on our 10,000-hour Mandarin task show the proposed method achieves more than 20% improvements with 50% latency compared to a strong TDNN-BLSTM lattice-free MMI baseline.

Neural architecture search (NAS) has been successfully applied to tasks like image classification and language modeling for finding efficient high-performance network architectures. In ASR field especially end-to-end ASR, the related research is still in its infancy. In this work, we focus on applying NAS on the most popular manually designed model: Conformer, and then propose an efficient ASR model searching method that benefits from the natural advantage of differentiable architecture search (Darts) in reducing computational overheads. We fuse Darts mutator and Conformer blocks to form a complete search space, within which a modified architecture called Darts-Conformer cell is found automatically. The entire searching process on AISHELL-1 dataset costs only 0.7 GPU days. Replacing the Conformer encoder by stacking searched cell, we get an end-to-end ASR model (named as Darts-Conformner) that outperforms the Conformer baseline by 4.7\% on the open-source AISHELL-1 dataset. Besides, we verify the transferability of the architecture searched on a small dataset to a larger 2k-hour dataset. To the best of our knowledge, this is the first successful attempt to apply gradient-based architecture search in the attention-based encoder-decoder ASR model., Comment: Submitted to ASRU 2021

Adversarial Transferability is an intriguing property - adversarial perturbation crafted against one model is also effective against another model, while these models are from different model families or training processes. To better protect ML systems against adversarial attacks, several questions are raised: what are the sufficient conditions for adversarial transferability and how to bound it? Is there a way to reduce the adversarial transferability in order to improve the robustness of an ensemble ML model? To answer these questions, in this work we first theoretically analyze and outline sufficient conditions for adversarial transferability between models; then propose a practical algorithm to reduce the transferability between base models within an ensemble to improve its robustness. Our theoretical analysis shows that only promoting the orthogonality between gradients of base models is not enough to ensure low transferability; in the meantime, the model smoothness is an important factor to control the transferability. We also provide the lower and upper bounds of adversarial transferability under certain conditions. Inspired by our theoretical analysis, we propose an effective Transferability Reduced Smooth(TRS) ensemble training strategy to train a robust ensemble with low transferability by enforcing both gradient orthogonality and model smoothness between base models. We conduct extensive experiments on TRS and compare with 6 state-of-the-art ensemble baselines against 8 whitebox attacks on different datasets, demonstrating that the proposed TRS outperforms all baselines significantly., Comment: Proceedings of the 35th Conference on Neural Information Processing Systems (NeurIPS 2021)