Rethinking Deep Spiking Neural Networks: A Multi-Layer Perceptron Approach

By adopting deep convolution architectures, spiking neural networks (SNNs) have recently achieved competitive performances with their artificial counterparts in image classification, meanwhile with much lower computation cost due to event-driven and sparse activation. However, the multiplication-free inference (MFI) principle makes SNNs incompatible with attention or transformer mechanisms which have shown significant performance gains on high resolution vision tasks. Inspired from recent works on multi-layer perceptrons (MLPs), we explore an efficient spiking MLP design using batch normalization instead of layer normalization in both the token and the channel block to be compatible with MFI. We further strengthen the network’s local feature learning ability with a spiking patch encoding layer, which significantly improves the network performance. Based on these building blocks, we explore an optimal skip connection configuration and develop an efficient multi-stage spiking MLP network combining global receptive field and local feature extraction, achieving full spike-based computation. Without pre-training or other advanced SNN training techniques, the spiking MLP network achieves 66.39% top-1 accuracy on the ImageNet-1K dataset, surpassing the state-of-the-art directly trained spiking ResNet-34 by 2.67% under similar model capacity meanwhile with shorter simulation steps and much less computation cost. Another larger variant of the network achieves 68.84% top-1 accuracy, rivaling the spiking VGG-16 network with 4 times smaller model capacity. Our work demonstrates the effectiveness of an alternative deep SNN architecture combining both global and local learning abilities. More interestingly, finally we show a close resemblance of the trained receptive field of our network to cells in the cortex. Code will be publicly available.