With the recent boom of video-based social platforms (e.g., YouTube and TikTok), video retrieval using sentence queries has become an important demand and attracts increasing research attention. Despite the decent performance, existing text-video retrieval models in vision and language communities are impractical for large-scale Web search because they adopt brute-force search based on high-dimensional embeddings. To improve efficiency, Web search engines widely apply vector compression libraries (e.g., FAISS) to post-process the learned embeddings. Unfortunately, separate compression from feature encoding degrades the robustness of representations and incurs performance decay. To pursue a better balance between performance and efficiency, we propose the first quantized representation learning method for cross-view video retrieval, namely Hybrid Contrastive Quantization (HCQ). Specifically, HCQ learns both coarse-grained and fine-grained quantizations with transformers, which provide complementary understandings for texts and videos and preserve comprehensive semantic information. By performing Asymmetric-Quantized Contrastive Learning (AQ-CL) across views, HCQ aligns texts and videos at coarse-grained and multiple fine-grained levels. This hybrid-grained learning strategy serves as strong supervision on the cross-view video quantization model, where contrastive learning at different levels can be mutually promoted. Extensive experiments on three Web video benchmark datasets demonstrate that HCQ achieves competitive performance with state-of-the-art non-compressed retrieval methods while showing high efficiency in storage and computation. Code and configurations are available at https://github.com/gimpong/WWW22-HCQ.
Visual object tracking (VOT) has been widely adopted in mission-critical applications, such as autonomous driving and intelligent surveillance systems. In current practice, third-party resources such as datasets, backbone networks, and training platforms are frequently used to train high-performance VOT models. Whilst these resources bring certain convenience, they also introduce new security threats into VOT models. In this paper, we reveal such a threat where an adversary can easily implant hidden backdoors into VOT models by tempering with the training process. Specifically, we propose a simple yet effective few-shot backdoor attack (FSBA) that optimizes two losses alternately: 1) a \emph{feature loss} defined in the hidden feature space, and 2) the standard \emph{tracking loss}. We show that, once the backdoor is embedded into the target model by our FSBA, it can trick the model to lose track of specific objects even when the \emph{trigger} only appears in one or a few frames. We examine our attack in both digital and physical-world settings and show that it can significantly degrade the performance of state-of-the-art VOT trackers. We also show that our attack is resistant to potential defenses, highlighting the vulnerability of VOT models to potential backdoor attacks.
Obtaining a well-trained model involves expensive data collection and training procedures, therefore the model is a valuable intellectual property. Recent studies revealed that adversaries can `steal' deployed models even when they have no training samples and can not get access to the model parameters or structures. Currently, there were some defense methods to alleviate this threat, mostly by increasing the cost of model stealing. In this paper, we explore the defense from another angle by verifying whether a suspicious model contains the knowledge of defender-specified \emph{external features}. Specifically, we embed the external features by tempering a few training samples with style transfer. We then train a meta-classifier to determine whether a model is stolen from the victim. This approach is inspired by the understanding that the stolen models should contain the knowledge of features learned by the victim model. We examine our method on both CIFAR-10 and ImageNet datasets. Experimental results demonstrate that our method is effective in detecting different types of model stealing simultaneously, even if the stolen model is obtained via a multi-stage stealing process. The codes for reproducing main results are available at Github (https://github.com/zlh-thu/StealingVerification).
Adversarial robustness has received increasing attention along with the study of adversarial examples. So far, existing works show that robust models not only obtain robustness against various adversarial attacks but also boost the performance in some downstream tasks. However, the underlying mechanism of adversarial robustness is still not clear. In this paper, we interpret adversarial robustness from the perspective of linear components, and find that there exist some statistical properties for comprehensively robust models. Specifically, robust models show obvious hierarchical clustering effect on their linearized sub-networks, when removing or replacing all non-linear components (e.g., batch normalization, maximum pooling, or activation layers). Based on these observations, we propose a novel understanding of adversarial robustness and apply it on more tasks including domain adaption and robustness boosting. Experimental evaluations demonstrate the rationality and superiority of our proposed clustering strategy.
This paper presents a new method to solve keypoint detection and instance association by using Transformer. For bottom-up multi-person pose estimation models, they need to detect keypoints and learn associative information between keypoints. We argue that these problems can be entirely solved by Transformer. Specifically, the self-attention in Transformer measures dependencies between any pair of locations, which can provide association information for keypoints grouping. However, the naive attention patterns are still not subjectively controlled, so there is no guarantee that the keypoints will always attend to the instances to which they belong. To address it we propose a novel approach of supervising self-attention for multi-person keypoint detection and instance association. By using instance masks to supervise self-attention to be instance-aware, we can assign the detected keypoints to their corresponding instances based on the pairwise attention scores, without using pre-defined offset vector fields or embedding like CNN-based bottom-up models. An additional benefit of our method is that the instance segmentation results of any number of people can be directly obtained from the supervised attention matrix, thereby simplifying the pixel assignment pipeline. The experiments on the COCO multi-person keypoint detection challenge and person instance segmentation task demonstrate the effectiveness and simplicity of the proposed method and show a promising way to control self-attention behavior for specific purposes.
Deep hashing has become a popular method in large-scale image retrieval due to its computational and storage efficiency. However, recent works raise the security concerns of deep hashing. Although existing works focus on the vulnerability of deep hashing in terms of adversarial perturbations, we identify a more pressing threat, backdoor attack, when the attacker has access to the training data. A backdoored deep hashing model behaves normally on original query images, while returning the images with the target label when the trigger presents, which makes the attack hard to be detected. In this paper, we uncover this security concern by utilizing clean-label data poisoning. To the best of our knowledge, this is the first attempt at the backdoor attack against deep hashing models. To craft the poisoned images, we first generate the targeted adversarial patch as the backdoor trigger. Furthermore, we propose the confusing perturbations to disturb the hashing code learning, such that the hashing model can learn more about the trigger. The confusing perturbations are imperceptible and generated by dispersing the images with the target label in the Hamming space. We have conducted extensive experiments to verify the efficacy of our backdoor attack under various settings. For instance, it can achieve 63% targeted mean average precision on ImageNet under 48 bits code length with only 40 poisoned images.
Deep hashing approaches, including deep quantization and deep binary hashing, have become a common solution to large-scale image retrieval due to high computation and storage efficiency. Most existing hashing methods can not produce satisfactory results for fine-grained retrieval, because they usually adopt the outputs of the last CNN layer to generate binary codes, which is less effective to capture subtle but discriminative visual details. To improve fine-grained image hashing, we propose Pyramid Hybrid Pooling Quantization (PHPQ). Specifically, we propose a Pyramid Hybrid Pooling (PHP) module to capture and preserve fine-grained semantic information from multi-level features. Besides, we propose a learnable quantization module with a partial attention mechanism, which helps to optimize the most relevant codewords and improves the quantization. Comprehensive experiments demonstrate that PHPQ outperforms state-of-the-art methods.
The high efficiency in computation and storage makes hashing (including binary hashing and quantization) a common strategy in large-scale retrieval systems. To alleviate the reliance on expensive annotations, unsupervised deep hashing becomes an important research problem. This paper provides a novel solution to unsupervised deep quantization, namely Contrastive Quantization with Code Memory (MeCoQ). Different from existing reconstruction-based strategies, we learn unsupervised binary descriptors by contrastive learning, which can better capture discriminative visual semantics. Besides, we uncover that codeword diversity regularization is critical to prevent contrastive learning-based quantization from model degeneration. Moreover, we introduce a novel quantization code memory module that boosts contrastive learning with lower feature drift than conventional feature memories. Extensive experiments on benchmark datasets show that MeCoQ outperforms state-of-the-art methods.
The 2D heatmap representation has dominated human pose estimation for years due to its high performance. However, heatmap-based approaches have some drawbacks: 1) The performance drops dramatically in the low-resolution images, which are frequently encountered in real-world scenarios. 2) To improve the localization precision, multiple upsample layers may be needed to recover the feature map resolution from low to high, which are computationally expensive. 3) Extra coordinate refinement is usually necessary to reduce the quantization error of downscaled heatmaps. To address these issues, we propose a \textbf{Sim}ple yet promising \textbf{D}isentangled \textbf{R}epresentation for keypoint coordinate (\emph{SimDR}), reformulating human keypoint localization as a task of classification. In detail, we propose to disentangle the representation of horizontal and vertical coordinates for keypoint location, leading to a more efficient scheme without extra upsampling and refinement. Comprehensive experiments conducted over COCO dataset show that the proposed \emph{heatmap-free} methods outperform \emph{heatmap-based} counterparts in all tested input resolutions, especially in lower resolutions by a large margin. Code will be made publicly available at \url{https://github.com/leeyegy/SimDR}.