SASG-DA: Sparse-Aware Semantic-Guided Diffusion Augmentation For Myoelectric Gesture Recognition

TL;DR

This paper introduces SASG-DA, a diffusion-based data augmentation method for sEMG gesture recognition that improves model generalization by generating faithful and diverse samples through semantic guidance and sparse-aware sampling.

Contribution

The paper proposes a novel diffusion-based augmentation method with semantic guidance and sparse-aware sampling to enhance sEMG gesture recognition performance.

Findings

Outperforms existing augmentation methods on benchmark datasets.

Significantly reduces overfitting in deep learning models.

Improves recognition accuracy and generalization in sEMG-based systems.

Abstract

Surface electromyography (sEMG)-based gesture recognition plays a critical role in human-machine interaction (HMI), particularly for rehabilitation and prosthetic control. However, sEMG-based systems often suffer from the scarcity of informative training data, leading to overfitting and poor generalization in deep learning models. Data augmentation offers a promising approach to increasing the size and diversity of training data, where faithfulness and diversity are two critical factors to effectiveness. However, promoting untargeted diversity can result in redundant samples with limited utility. To address these challenges, we propose a novel diffusion-based data augmentation approach, Sparse-Aware Semantic-Guided Diffusion Augmentation (SASG-DA). To enhance generation faithfulness, we introduce the Semantic Representation Guidance (SRG) mechanism by leveraging fine-grained, task-aware semantic representations as generation conditions. To enable flexible and diverse sample generation, we propose a Gaussian Modeling Semantic Sampling (GMSS) strategy, which models the semantic representation distribution and allows stochastic sampling to produce both faithful and diverse samples. To enhance targeted diversity, we further introduce a Sparse-Aware Semantic Sampling strategy to explicitly explore underrepresented regions, improving distribution coverage and sample utility. Extensive experiments on benchmark sEMG datasets, Ninapro DB2, DB4, and DB7, demonstrate that SASG-DA significantly outperforms existing augmentation methods. Overall, our proposed data augmentation approach effectively mitigates overfitting and improves recognition performance and generalization by offering both faithful and diverse samples.