SkeletonX: Data-Efficient Skeleton-based Action Recognition via Cross-sample Feature Aggregation
- URL: http://arxiv.org/abs/2504.11749v1
- Date: Wed, 16 Apr 2025 04:01:42 GMT
- Title: SkeletonX: Data-Efficient Skeleton-based Action Recognition via Cross-sample Feature Aggregation
- Authors: Zongye Zhang, Wenrui Cai, Qingjie Liu, Yunhong Wang,
- Abstract summary: This paper studies one-shot and limited-scale learning settings to enable efficient adaptation with minimal data.<n>We present SkeletonX, a lightweight training pipeline that integrates seamlessly with existing GCN-based skeleton action recognizers.<n>It surpasses previous state-of-the-art methods in the one-shot setting, with only 1/10 of the parameters and much fewer FLOPs.
- Score: 34.65359766672547
- License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
- Abstract: While current skeleton action recognition models demonstrate impressive performance on large-scale datasets, their adaptation to new application scenarios remains challenging. These challenges are particularly pronounced when facing new action categories, diverse performers, and varied skeleton layouts, leading to significant performance degeneration. Additionally, the high cost and difficulty of collecting skeleton data make large-scale data collection impractical. This paper studies one-shot and limited-scale learning settings to enable efficient adaptation with minimal data. Existing approaches often overlook the rich mutual information between labeled samples, resulting in sub-optimal performance in low-data scenarios. To boost the utility of labeled data, we identify the variability among performers and the commonality within each action as two key attributes. We present SkeletonX, a lightweight training pipeline that integrates seamlessly with existing GCN-based skeleton action recognizers, promoting effective training under limited labeled data. First, we propose a tailored sample pair construction strategy on two key attributes to form and aggregate sample pairs. Next, we develop a concise and effective feature aggregation module to process these pairs. Extensive experiments are conducted on NTU RGB+D, NTU RGB+D 120, and PKU-MMD with various GCN backbones, demonstrating that the pipeline effectively improves performance when trained from scratch with limited data. Moreover, it surpasses previous state-of-the-art methods in the one-shot setting, with only 1/10 of the parameters and much fewer FLOPs. The code and data are available at: https://github.com/zzysteve/SkeletonX
Related papers
- Adaptive Dataset Quantization [2.0105434963031463]
We introduce a versatile framework for dataset compression, namely Adaptive dataset Quantization (ADQ)<n>We propose a novel adaptive sampling strategy through the evaluation of generated bins' representativeness score, diversity score and importance score.<n>Our method not only exhibits superior generalization capability across different architectures, but also attains state-of-the-art results, surpassing DQ by average 3% on various datasets.
arXiv Detail & Related papers (2024-12-22T07:08:29Z) - USDRL: Unified Skeleton-Based Dense Representation Learning with Multi-Grained Feature Decorrelation [24.90512145836643]
We introduce a Unified Skeleton-based Dense Representation Learning framework based on feature decorrelation.<n>We show that our approach significantly outperforms the current state-of-the-art (SOTA) approaches.
arXiv Detail & Related papers (2024-12-12T12:20:27Z) - How Hard is this Test Set? NLI Characterization by Exploiting Training Dynamics [49.9329723199239]
We propose a method for the automated creation of a challenging test set without relying on the manual construction of artificial and unrealistic examples.
We categorize the test set of popular NLI datasets into three difficulty levels by leveraging methods that exploit training dynamics.
When our characterization method is applied to the training set, models trained with only a fraction of the data achieve comparable performance to those trained on the full dataset.
arXiv Detail & Related papers (2024-10-04T13:39:21Z) - One-Shot Action Recognition via Multi-Scale Spatial-Temporal Skeleton
Matching [77.6989219290789]
One-shot skeleton action recognition aims to learn a skeleton action recognition model with a single training sample.
This paper presents a novel one-shot skeleton action recognition technique that handles skeleton action recognition via multi-scale spatial-temporal feature matching.
arXiv Detail & Related papers (2023-07-14T11:52:10Z) - ScoreMix: A Scalable Augmentation Strategy for Training GANs with
Limited Data [93.06336507035486]
Generative Adversarial Networks (GANs) typically suffer from overfitting when limited training data is available.
We present ScoreMix, a novel and scalable data augmentation approach for various image synthesis tasks.
arXiv Detail & Related papers (2022-10-27T02:55:15Z) - Learning from Temporal Spatial Cubism for Cross-Dataset Skeleton-based
Action Recognition [88.34182299496074]
Action labels are only available on a source dataset, but unavailable on a target dataset in the training stage.
We utilize a self-supervision scheme to reduce the domain shift between two skeleton-based action datasets.
By segmenting and permuting temporal segments or human body parts, we design two self-supervised learning classification tasks.
arXiv Detail & Related papers (2022-07-17T07:05:39Z) - AdaSGN: Adapting Joint Number and Model Size for Efficient
Skeleton-Based Action Recognition [45.6728814296272]
Existing methods for skeleton-based action recognition mainly focus on improving the recognition accuracy.
A novel approach, called AdaSGN, is proposed in this paper, which can reduce the computational cost of the inference process.
arXiv Detail & Related papers (2021-03-22T12:36:39Z) - Omni-supervised Facial Expression Recognition via Distilled Data [120.11782405714234]
We propose omni-supervised learning to exploit reliable samples in a large amount of unlabeled data for network training.
We experimentally verify that the new dataset can significantly improve the ability of the learned FER model.
To tackle this, we propose to apply a dataset distillation strategy to compress the created dataset into several informative class-wise images.
arXiv Detail & Related papers (2020-05-18T09:36:51Z) - Convolutional Tensor-Train LSTM for Spatio-temporal Learning [116.24172387469994]
We propose a higher-order LSTM model that can efficiently learn long-term correlations in the video sequence.
This is accomplished through a novel tensor train module that performs prediction by combining convolutional features across time.
Our results achieve state-of-the-art performance-art in a wide range of applications and datasets.
arXiv Detail & Related papers (2020-02-21T05:00:01Z)
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.