In recent years, self-supervised representation learning for skeleton-based action recognition has been developed with the advance of contrastive learning methods. The existing contrastive learning methods use normal augmentations to construct similar positive samples, which limits the ability to explore novel movement patterns. In this paper, to make better use of the movement patterns introduced by extreme augmentations, a Contrastive Learning framework utilizing Abundant Information Mining for self-supervised action Representation (AimCLR) is proposed. First, the extreme augmentations and the Energy-based Attention-guided Drop Module (EADM) are proposed to obtain diverse positive samples, which bring novel movement patterns to improve the universality of the learned representations. Second, since directly using extreme augmentations may not be able to boost the performance due to the drastic changes in original identity, the Dual Distributional Divergence Minimization Loss (D$^3$M Loss) is proposed to minimize the distribution divergence in a more gentle way. Third, the Nearest Neighbors Mining (NNM) is proposed to further expand positive samples to make the abundant information mining process more reasonable. Exhaustive experiments on NTU RGB+D 60, PKU-MMD, NTU RGB+D 120 datasets have verified that our AimCLR can significantly perform favorably against state-of-the-art methods under a variety of evaluation protocols with observed higher quality action representations. Our code is available at https://github.com/Levigty/AimCLR.
Occluded person re-identification is a challenging task as human body parts could be occluded by some obstacles (e.g. trees, cars, and pedestrians) in certain scenes. Some existing pose-guided methods solve this problem by aligning body parts according to graph matching, but these graph-based methods are not intuitive and complicated. Therefore, we propose a transformer-based Pose-guided Feature Disentangling (PFD) method by utilizing pose information to clearly disentangle semantic components (e.g. human body or joint parts) and selectively match non-occluded parts correspondingly. First, Vision Transformer (ViT) is used to extract the patch features with its strong capability. Second, to preliminarily disentangle the pose information from patch information, the matching and distributing mechanism is leveraged in Pose-guided Feature Aggregation (PFA) module. Third, a set of learnable semantic views are introduced in transformer decoder to implicitly enhance the disentangled body part features. However, those semantic views are not guaranteed to be related to the body without additional supervision. Therefore, Pose-View Matching (PVM) module is proposed to explicitly match visible body parts and automatically separate occlusion features. Fourth, to better prevent the interference of occlusions, we design a Pose-guided Push Loss to emphasize the features of visible body parts. Extensive experiments over five challenging datasets for two tasks (occluded and holistic Re-ID) demonstrate that our proposed PFD is superior promising, which performs favorably against state-of-the-art methods. Code is available at https://github.com/WangTaoAs/PFD_Net
Recently, an event-based end-to-end model (SEDT) has been proposed for sound event detection (SED) and achieves competitive performance. However, compared with the frame-based model, it requires more training data with temporal annotations to improve the localization ability. Synthetic data is an alternative, but it suffers from a great domain gap with real recordings. Inspired by the great success of UP-DETR in object detection, we propose to self-supervisedly pre-train SEDT (SP-SEDT) by detecting random patches (only cropped along the time axis). Experiments on the DCASE2019 task4 dataset show the proposed SP-SEDT can outperform fine-tuned frame-based model. The ablation study is also conducted to investigate the impact of different loss functions and patch size.
Estimating 3D human poses from monocular videos is a challenging task due to depth ambiguity and self-occlusion. Most existing works attempt to solve both issues by exploiting spatial and temporal relationships. However, those works ignore the fact that it is an inverse problem where multiple feasible solutions (i.e., hypotheses) exist. To relieve this limitation, we propose a Multi-Hypothesis Transformer (MHFormer) that learns spatio-temporal representations of multiple plausible pose hypotheses. In order to effectively model multi-hypothesis dependencies and build strong relationships across hypothesis features, the task is decomposed into three stages: (i) Generate multiple initial hypothesis representations; (ii) Model self-hypothesis communication, merge multiple hypotheses into a single converged representation and then partition it into several diverged hypotheses; (iii) Learn cross-hypothesis communication and aggregate the multi-hypothesis features to synthesize the final 3D pose. Through the above processes, the final representation is enhanced and the synthesized pose is much more accurate. Extensive experiments show that MHFormer achieves state-of-the-art results on two challenging datasets: Human3.6M and MPI-INF-3DHP. Without bells and whistles, its performance surpasses the previous best result by a large margin of 3% on Human3.6M. Code and models are available at https://github.com/Vegetebird/MHFormer.
This paper focuses on camouflaged object detection (COD), which is a task to detect objects hidden in the background. Most of the current COD models aim to highlight the target object directly while outputting ambiguous camouflaged boundaries. On the other hand, the performance of the models considering edge information is not yet satisfactory. To this end, we propose a new framework that makes full use of multiple visual cues, i.e., saliency as well as edges, to refine the predicted camouflaged map. This framework consists of three key components, i.e., a pseudo-edge generator, a pseudo-map generator, and an uncertainty-aware refinement module. In particular, the pseudo-edge generator estimates the boundary that outputs the pseudo-edge label, and the conventional COD method serves as the pseudo-map generator that outputs the pseudo-map label. Then, we propose an uncertainty-based module to reduce the uncertainty and noise of such two pseudo labels, which takes both pseudo labels as input and outputs an edge-accurate camouflaged map. Experiments on various COD datasets demonstrate the effectiveness of our method with superior performance to the existing state-of-the-art methods.
Universal user representation is an important research topic in industry, and is widely used in diverse downstream user analysis tasks, such as user profiling and user preference prediction. With the rapid development of Internet service platforms, extremely long user behavior sequences have been accumulated. However, existing researches have little ability to model universal user representation based on lifelong sequences of user behavior since registration. In this study, we propose a novel framework called Lifelong User Representation Model (LURM) to tackle this challenge. Specifically, LURM consists of two cascaded sub-models: (i) Bag of Interests (BoI) encodes user behaviors in any time period into a sparse vector with super-high dimension (e.g.,105); (ii) Self-supervised Multi-anchor EncoderNetwork (SMEN) maps sequences of BoI features to multiple low-dimensional user representations by contrastive learning. SMEN achieves almost lossless dimensionality reduction, benefiting from a novel multi-anchor module which can learn different aspects of user preferences. Experiments on several benchmark datasets show that our approach outperforms state-of-the-art unsupervised representation methods in downstream tasks
Sound event detection (SED) has gained increasing attention with its wide application in surveillance, video indexing, etc. Existing models in SED mainly generate frame-level predictions, converting it into a sequence multi-label classification problem, which inevitably brings a trade-off between event boundary detection and audio tagging when using weakly labeled data to train the model. Besides, it needs post-processing and cannot be trained in an end-to-end way. This paper firstly presents the 1D Detection Transformer (1D-DETR), inspired by Detection Transformer. Furthermore, given the characteristics of SED, the audio query and a one-to-many matching strategy for fine-tuning the model are added to 1D-DETR to form the model of Sound Event Detection Transformer (SEDT), which generates event-level predictions, end-to-end detection. Experiments are conducted on the URBAN-SED dataset and the DCASE2019 Task4 dataset, and both experiments have achieved competitive results compared with SOTA models. The application of SEDT on SED shows that it can be used as a framework for one-dimensional signal detection and may be extended to other similar tasks.
Self-supervised learning (SSL) is a scalable way to learn general visual representations since it learns without labels. However, large-scale unlabeled datasets in the wild often have long-tailed label distributions, where we know little about the behavior of SSL. In this work, we systematically investigate self-supervised learning under dataset imbalance. First, we find out via extensive experiments that off-the-shelf self-supervised representations are already more robust to class imbalance than supervised representations. The performance gap between balanced and imbalanced pre-training with SSL is significantly smaller than the gap with supervised learning, across sample sizes, for both in-domain and, especially, out-of-domain evaluation. Second, towards understanding the robustness of SSL, we hypothesize that SSL learns richer features from frequent data: it may learn label-irrelevant-but-transferable features that help classify the rare classes and downstream tasks. In contrast, supervised learning has no incentive to learn features irrelevant to the labels from frequent examples. We validate this hypothesis with semi-synthetic experiments and theoretical analyses on a simplified setting. Third, inspired by the theoretical insights, we devise a re-weighted regularization technique that consistently improves the SSL representation quality on imbalanced datasets with several evaluation criteria, closing the small gap between balanced and imbalanced datasets with the same number of examples.
User representation is essential for providing high-quality commercial services in industry. Universal user representation has received many interests recently, with which we can be free from the cumbersome work of training a specific model for each downstream application. In this paper, we attempt to improve universal user representation from two points of views. First, a contrastive self-supervised learning paradigm is presented to guide the representation model training. It provides a unified framework that allows for long-term or short-term interest representation learning in a data-driven manner. Moreover, a novel multi-interest extraction module is presented. The module introduces an interest dictionary to capture principal interests of the given user, and then generate his/her interest-oriented representations via behavior aggregation. Experimental results demonstrate the effectiveness and applicability of the learned user representations.