轻量Transformer模型提升肌电信号手势识别准确率
WaveFormer: A Lightweight Transformer Model for sEMG-based Gesture Recognition
- 用可学习小波变换融合时频域特征，提升特征提取能力
- 仅310万参数，95%准确率超越更大模型
- 量化后推理延迟仅6.75毫秒，适合嵌入式部署
人机交互在假肢与机器人控制中借助表面肌电（sEMG）信号的手势识别取得进展。然而，产生几乎相同肌肉信号的相似手势分类仍具挑战，常导致识别准确率下降。传统sEMG手势识别深度学习模型体积大、计算开销高，限制了在资源受限嵌入式系统中的部署。本文提出WaveFormer，一种专为sEMG手势识别设计的轻量级Transformer架构。模型通过新型可学习小波变换融合时域与频域特征，增强特征表达。其中，包含深度可分离卷积的多级小波分解模块（WaveletConv），兼顾效率与紧凑性。模型仅含310万参数，在EPN612数据集上达到95%分类准确率，优于更大规模模型。此外，在配备Intel CPU的笔记本上进行INT8量化后，实现6.75毫秒实时推理延迟。
原文摘要 · Abstract (English)
Human-machine interaction, particularly in prosthetic and robotic control, has seen progress with gesture recognition via surface electromyographic (sEMG) signals.However, classifying similar gestures that produce nearly identical muscle signals remains a challenge, often reducing classification accuracy. Traditional deep learning models for sEMG gesture recognition are large and computationally expensive, limiting their deployment on resource-constrained embedded systems. In this work, we propose WaveFormer, a lightweight transformer-based architecture tailored for sEMG gesture recognition. Our model integrates time-domain and frequency-domain features through a novel learnable wavelet transform, enhancing feature extraction. In particular, the WaveletConv module, a multi-level wavelet decomposition layer with depthwise separable convolution, ensures both efficiency and compactness. With just 3.1 million parameters, WaveFormer achieves 95% classification accuracy on the EPN612 dataset, outperforming larger models. Furthermore, when profiled on a laptop equipped with an Intel CPU, INT8 quantization achieves real-time deployment with a 6.75 ms inference latency.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。