SynA-ResNet: Spike-driven ResNet Achieved through OR Residual Connection

TL;DR

This paper introduces SynA-ResNet, a spike-driven residual neural network that employs OR Residual Connection and a Synergistic Attention module to enhance feature extraction, reduce redundancy, and achieve high accuracy with low energy consumption.

Contribution

The paper proposes a novel training paradigm with OR Residual Connection and SynA module, enabling deep residual SNNs to naturally prune shortcuts and improve efficiency.

Findings

Achieved single-sample classification with as low as 0.8 spikes per neuron.

Demonstrated higher accuracy compared to other residual SNNs.

Realized up to 28-fold reduction in energy consumption.

Abstract

Spiking Neural Networks (SNNs) have garnered substantial attention in brain-like computing for their biological fidelity and the capacity to execute energy-efficient spike-driven operations. As the demand for heightened performance in SNNs surges, the trend towards training deeper networks becomes imperative, while residual learning stands as a pivotal method for training deep neural networks. In our investigation, we identified that the SEW-ResNet, a prominent representative of deep residual spiking neural networks, incorporates non-event-driven operations. To rectify this, we propose a novel training paradigm that first accumulates a large amount of redundant information through OR Residual Connection (ORRC), and then filters out the redundant information using the Synergistic Attention (SynA) module, which promotes feature extraction in the backbone while suppressing the influence of noise and useless features in the shortcuts. When integrating SynA into the network, we observed the phenomenon of "natural pruning", where after training, some or all of the shortcuts in the network naturally drop out without affecting the model's classification accuracy. This significantly reduces computational overhead and makes it more suitable for deployment on edge devices. Experimental results on various public datasets confirmed that the SynA-ResNet achieved single-sample classification with as little as 0.8 spikes per neuron. Moreover, when compared to other residual SNN models, it exhibited higher accuracy and up to a 28-fold reduction in energy consumption.