Due to the binary spike signals making converting the traditional high-power multiply-accumulation (MAC) into a low-power accumulation (AC) available, the brain-inspired Spiking Neural Networks (SNNs) are gaining more and more attention. However, the binary spike propagation of the Full-Spike Neural Networks (FSNN) with limited time steps is prone to significant information loss. To improve performance, several state-of-the-art SNN models trained from scratch inevitably bring many non-spike operations. The non-spike operations cause additional computational consumption and may not be deployed on some neuromorphic hardware where only spike operation is allowed. To train a large-scale FSNN with high performance, this paper proposes a novel Dual-Stream Training (DST) method which adds a detachable Auxiliary Accumulation Pathway (AAP) to the full spiking residual networks. The accumulation in AAP could compensate for the information loss during the forward and backward of full spike propagation, and facilitate the training of the FSNN. In the test phase, the AAP could be removed and only the FSNN remained. This not only keeps the lower energy consumption but also makes our model easy to deploy. Moreover, for some cases where the non-spike operations are available, the APP could also be retained in test inference and improve feature discrimination by introducing a little non-spike consumption. Extensive experiments on ImageNet, DVS Gesture, and CIFAR10-DVS datasets demonstrate the effectiveness of DST.

翻译：由于二元脉冲信号使传统高功耗的乘累加运算（MAC）可转化为低功耗的累加运算（AC），受大脑启发的脉冲神经网络（SNNs）正获得越来越多的关注。然而，在全脉冲神经网络（FSNN）中，有限时间步下的二元脉冲传播极易导致显著的信息损失。为提升性能，若干从零训练的最先进SNN模型不可避免地引入了大量非脉冲运算。这些非脉冲运算不仅带来额外的计算消耗，还可能无法部署在仅允许脉冲运算的神经形态硬件上。为训练高性能的大规模FSNN，本文提出一种新颖的双流训练（DST）方法，该方法在全脉冲残差网络上添加了一个可拆卸的辅助累积通路（AAP）。AAP中的累积运算可补偿全脉冲传播前向与反向过程中的信息损失，从而促进FSNN的训练。在测试阶段，可移除AAP，仅保留FSNN。这不仅保持了更低的能耗，还使我们的模型易于部署。此外，对于允许非脉冲运算的场景，AAP可在测试推理中保留，通过引入少量非脉冲消耗来提升特征判别能力。在ImageNet、DVS Gesture和CIFAR10-DVS数据集上的大量实验证明了DST方法的有效性。