用脉冲神经网络实现低功耗行人属性识别
SNN-PAR: Energy Efficient Pedestrian Attribute Recognition via Spiking Neural Networks
- 将图像转为脉冲信号，通过脉冲Transformer高效提取特征
- 在三个主流数据集上达成更高准确率，能耗显著降低
- 适合边缘设备部署，对能效敏感的智能监控场景
基于人工神经网络的行人属性识别（PAR）近年来得到广泛关注，但能耗仍较高。为此，本文提出一种基于脉冲神经网络（SNN）的低功耗属性识别框架。首先采用脉冲分词模块将行人图像转换为脉冲特征表示，随后输入脉冲Transformer骨干网络进行高效特征提取，再通过前馈网络完成属性识别。除常用二元交叉熵损失外，还引入人工神经网络到脉冲Transformer的知识蒸馏，提升识别精度。在三个主流PAR基准数据集上的大量实验充分验证了所提SNN-PAR框架的有效性。代码已开源于https://github.com/Event-AHU/OpenPAR。
原文摘要 · Abstract (English)
Artificial neural network based Pedestrian Attribute Recognition (PAR) has been widely studied in recent years, despite many progresses, however, the energy consumption is still high. To address this issue, in this paper, we propose a Spiking Neural Network (SNN) based framework for energy-efficient attribute recognition. Specifically, we first adopt a spiking tokenizer module to transform the given pedestrian image into spiking feature representations. Then, the output will be fed into the spiking Transformer backbone networks for energy-efficient feature extraction. We feed the enhanced spiking features into a set of feed-forward networks for pedestrian attribute recognition. In addition to the widely used binary cross-entropy loss function, we also exploit knowledge distillation from the artificial neural network to the spiking Transformer network for more accurate attribute recognition. Extensive experiments on three widely used PAR benchmark datasets fully validated the effectiveness of our proposed SNN-PAR framework. The source code of this paper is released on \url{https://github.com/Event-AHU/OpenPAR}.
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。