Deep spiking neural networks (SNNs) have drawn much attention in recent years because of their low power consumption, biological rationality and event-driven property. However, state-of-the-art deep SNNs (including Spikformer and Spikingformer) suffer from a critical challenge related to the imprecise gradient backpropagation. This problem arises from the improper design of downsampling modules in these networks, and greatly hampering the overall model performance. In this paper, we propose ConvBN-MaxPooling-LIF (CML), an improved downsampling with precise gradient backpropagation. We prove that CML can effectively overcome the imprecision of gradient backpropagation from a theoretical perspective. In addition, we evaluate CML on ImageNet, CIFAR10, CIFAR100, CIFAR10-DVS, DVS128-Gesture datasets, and show state-of-the-art performance on all these datasets with significantly enhanced performances compared with Spikingformer. For instance, our model achieves 77.64 $\%$ on ImageNet, 96.04 $\%$ on CIFAR10, 81.4$\%$ on CIFAR10-DVS, with + 1.79$\%$ on ImageNet, +1.54$\%$ on CIFAR100 compared with Spikingformer.

翻译：深度脉冲神经网络（SNNs）因其低功耗、生物合理性和事件驱动特性，近年来受到广泛关注。然而，当前最先进的深度SNNs（包括Spikformer和Spikingformer）面临一个关键挑战——梯度反向传播不精确问题。该问题源于这些网络中下采样模块设计不当，严重制约了模型整体性能。本文提出ConvBN-MaxPooling-LIF（CML）——一种具有精确梯度反向传播的改进下采样方法。我们从理论角度证明CML能有效克服梯度反向传播的不精确性。此外，我们在ImageNet、CIFAR10、CIFAR100、CIFAR10-DVS、DVS128-Gesture数据集上评估CML，结果显示该模型在所有数据集上均达到最优性能，相较于Spikingformer显著提升。例如，我们的模型在ImageNet上达到77.64%，在CIFAR10上达到96.04%，在CIFAR10-DVS上达到81.4%，较Spikingformer在ImageNet上提升1.79%，在CIFAR100上提升1.54%。