DTA: Dual Temporal-channel-wise Attention for Spiking Neural Networks

Spiking Neural Networks (SNNs) present a more energy-efficient alternative to Artificial Neural Networks (ANNs) by harnessing spatio-temporal dynamics and event-driven spikes. Effective utilization of temporal information is crucial for SNNs, leading to the exploration of attention mechanisms to enhance this capability. Conventional at-tention operations either apply identical operation or em-ploy non-identical operations across target dimensions. We identify that these approaches provide distinct perspec-tives on temporal information. To leverage the strengths of both operations, we propose a novel Dual Temporal-channel-wise Attention (DTA) mechanism that integrates both identical/non-identical attention strategies. To the best of our knowledge, this is the first attempt to concen-trate on both the correlation and dependency of temporal-channel using both identical and non-identical attention op-erations. Experimental results demonstrate that the DTA mechanism achieves state-of-the-art performance on both static datasets (CIFAR10, CIFAR100, ImageN et-1k) and dy-namic dataset (CIFAR10-DVS), elevating spike representation and capturing complex temporal-channel relationship. We open-source our code: https://github.com/MnJnKIM/DTa-snn.