SNN-PAR: Energy Efficient Pedestrian Attribute Recognition via Spiking Neural Networks

TL;DR

This paper introduces SNN-PAR, a novel energy-efficient pedestrian attribute recognition framework using spiking neural networks with a spiking tokenizer and Transformer backbone, validated on benchmark datasets.

Contribution

It proposes a new SNN-based PAR framework with a spiking tokenizer and Transformer backbone, incorporating knowledge distillation for improved accuracy.

Findings

Effective energy savings demonstrated on benchmarks.

Improved attribute recognition accuracy.

Validated on three widely used datasets.

Abstract

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}.