Litcius/Paper detail

STCA-SNN: self-attention-based temporal-channel joint attention for spiking neural networks

Xiyan Wu, Yong Song, Ya Zhou, Yurong Jiang, Yashuo Bai, Xinyi Li, Xin Yang

2023Frontiers in Neuroscience10 citationsDOIOpen Access PDF

Abstract

Spiking Neural Networks (SNNs) have shown great promise in processing spatio-temporal information compared to Artificial Neural Networks (ANNs). However, there remains a performance gap between SNNs and ANNs, which impedes the practical application of SNNs. With intrinsic event-triggered property and temporal dynamics, SNNs have the potential to effectively extract spatio-temporal features from event streams. To leverage the temporal potential of SNNs, we propose a self-attention-based temporal-channel joint attention SNN (STCA-SNN) with end-to-end training, which infers attention weights along both temporal and channel dimensions concurrently. It models global temporal and channel information correlations with self-attention, enabling the network to learn 'what' and 'when' to attend simultaneously. Our experimental results show that STCA-SNNs achieve better performance on N-MNIST (99.67%), CIFAR10-DVS (81.6%), and N-Caltech 101 (80.88%) compared with the state-of-the-art SNNs. Meanwhile, our ablation study demonstrates that STCA-SNNs improve the accuracy of event stream classification tasks.

Topics & Concepts

Spiking neural networkComputer scienceMNIST databaseArtificial intelligenceLeverage (statistics)Artificial neural networkPattern recognition (psychology)Machine learningAdvanced Memory and Neural ComputingNeural dynamics and brain functionNeural Networks and Reservoir Computing
STCA-SNN: self-attention-based temporal-channel joint attention for spiking neural networks | Litcius