SynA-ResNet: Spike-driven ResNet Achieved through OR Residual Connection
This work addresses energy efficiency and computational overhead for deploying spiking neural networks on edge devices, representing an incremental improvement over existing residual SNN methods.
The authors tackled the problem of non-event-driven operations in deep residual spiking neural networks by proposing SynA-ResNet, which uses OR Residual Connection and Synergistic Attention to achieve natural pruning, resulting in as little as 0.8 spikes per neuron for classification and up to a 28-fold reduction in energy consumption compared to other models.
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.