Contrastive Learning from Extremely Augmented Skeleton Sequences for
Self-supervised Action Recognition
- URL: http://arxiv.org/abs/2112.03590v1
- Date: Tue, 7 Dec 2021 09:38:37 GMT
- Title: Contrastive Learning from Extremely Augmented Skeleton Sequences for
Self-supervised Action Recognition
- Authors: Tianyu Guo, Hong Liu, Zhan Chen, Mengyuan Liu, Tao Wang, Runwei Ding
- Abstract summary: 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.
Third, the Nearest Neighbors Mining (NNM) is proposed to further expand positive samples to make the abundant information mining process more reasonable.
- Score: 23.27198457894644
- License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
- Abstract: 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.
Related papers
- An Information Compensation Framework for Zero-Shot Skeleton-based Action Recognition [49.45660055499103]
Zero-shot human skeleton-based action recognition aims to construct a model that can recognize actions outside the categories seen during training.
Previous research has focused on aligning sequences' visual and semantic spatial distributions.
We introduce a new loss function sampling method to obtain a tight and robust representation.
arXiv Detail & Related papers (2024-06-02T06:53:01Z) - Unleashing Network Potentials for Semantic Scene Completion [50.95486458217653]
This paper proposes a novel SSC framework - Adrial Modality Modulation Network (AMMNet)
AMMNet introduces two core modules: a cross-modal modulation enabling the interdependence of gradient flows between modalities, and a customized adversarial training scheme leveraging dynamic gradient competition.
Extensive experimental results demonstrate that AMMNet outperforms state-of-the-art SSC methods by a large margin.
arXiv Detail & Related papers (2024-03-12T11:48:49Z) - Cross-Stream Contrastive Learning for Self-Supervised Skeleton-Based
Action Recognition [22.067143671631303]
Self-supervised skeleton-based action recognition enjoys a rapid growth along with the development of contrastive learning.
We propose a Cross-Stream Contrastive Learning framework for skeleton-based action Representation learning (CSCLR)
Specifically, the proposed CSCLR not only utilizes intra-stream contrast pairs, but introduces inter-stream contrast pairs as hard samples to formulate a better representation learning.
arXiv Detail & Related papers (2023-05-03T10:31:35Z) - Hierarchical Consistent Contrastive Learning for Skeleton-Based Action
Recognition with Growing Augmentations [33.68311764817763]
We propose a general hierarchical consistent contrastive learning framework (HiCLR) for skeleton-based action recognition.
Specifically, we first design a gradual growing augmentation policy to generate multiple ordered positive pairs.
Then, an asymmetric loss is proposed to enforce the hierarchical consistency via a directional clustering operation.
arXiv Detail & Related papers (2022-11-24T08:09:50Z) - Improving Contrastive Learning with Model Augmentation [123.05700988581806]
The sequential recommendation aims at predicting the next items in user behaviors, which can be solved by characterizing item relationships in sequences.
Due to the data sparsity and noise issues in sequences, a new self-supervised learning (SSL) paradigm is proposed to improve the performance.
arXiv Detail & Related papers (2022-03-25T06:12:58Z) - Few-Shot Fine-Grained Action Recognition via Bidirectional Attention and
Contrastive Meta-Learning [51.03781020616402]
Fine-grained action recognition is attracting increasing attention due to the emerging demand of specific action understanding in real-world applications.
We propose a few-shot fine-grained action recognition problem, aiming to recognize novel fine-grained actions with only few samples given for each class.
Although progress has been made in coarse-grained actions, existing few-shot recognition methods encounter two issues handling fine-grained actions.
arXiv Detail & Related papers (2021-08-15T02:21:01Z) - Augmented Skeleton Based Contrastive Action Learning with Momentum LSTM
for Unsupervised Action Recognition [16.22360992454675]
Action recognition via 3D skeleton data is an emerging important topic in these years.
In this paper, we for the first time propose a contrastive action learning paradigm named AS-CAL.
Our approach typically improves existing hand-crafted methods by 10-50% top-1 accuracy.
arXiv Detail & Related papers (2020-08-01T06:37:57Z) - Reparameterized Variational Divergence Minimization for Stable Imitation [57.06909373038396]
We study the extent to which variations in the choice of probabilistic divergence may yield more performant ILO algorithms.
We contribute a re parameterization trick for adversarial imitation learning to alleviate the challenges of the promising $f$-divergence minimization framework.
Empirically, we demonstrate that our design choices allow for ILO algorithms that outperform baseline approaches and more closely match expert performance in low-dimensional continuous-control tasks.
arXiv Detail & Related papers (2020-06-18T19:04:09Z) - MM-KTD: Multiple Model Kalman Temporal Differences for Reinforcement
Learning [36.14516028564416]
This paper proposes an innovative Multiple Model Kalman Temporal Difference (MM-KTD) framework to learn optimal control policies.
An active learning method is proposed to enhance the sampling efficiency of the system.
Experimental results show superiority of the MM-KTD framework in comparison to its state-of-the-art counterparts.
arXiv Detail & Related papers (2020-05-30T06:39:55Z) - Sequential Recommendation with Self-Attentive Multi-Adversarial Network [101.25533520688654]
We present a Multi-Factor Generative Adversarial Network (MFGAN) for explicitly modeling the effect of context information on sequential recommendation.
Our framework is flexible to incorporate multiple kinds of factor information, and is able to trace how each factor contributes to the recommendation decision over time.
arXiv Detail & Related papers (2020-05-21T12:28:59Z)
This list is automatically generated from the titles and abstracts of the papers in this site.
This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.