Integer Binary-Range Alignment Neuron for Spiking Neural Networks

TL;DR

This paper introduces a novel spiking neuron model that significantly enhances information capacity and performance of SNNs, achieving state-of-the-art results on image classification and object detection benchmarks with improved energy efficiency.

Contribution

The paper proposes the Integer Binary-Range Alignment Leaky Integrate-and-Fire neuron, enabling exponential information expansion with minimal energy increase, surpassing previous SNNs and matching or exceeding ANNs.

Findings

Achieves 74.19% accuracy on ImageNet

Surpasses previous SNNs in COCO object detection

Improves energy efficiency by 6.3 times

Abstract

Spiking Neural Networks (SNNs) are noted for their brain-like computation and energy efficiency, but their performance lags behind Artificial Neural Networks (ANNs) in tasks like image classification and object detection due to the limited representational capacity. To address this, we propose a novel spiking neuron, Integer Binary-Range Alignment Leaky Integrate-and-Fire to exponentially expand the information expression capacity of spiking neurons with only a slight energy increase. This is achieved through Integer Binary Leaky Integrate-and-Fire and range alignment strategy. The Integer Binary Leaky Integrate-and-Fire allows integer value activation during training and maintains spike-driven dynamics with binary conversion expands virtual timesteps during inference. The range alignment strategy is designed to solve the spike activation limitation problem where neurons fail to activate high integer values. Experiments show our method outperforms previous SNNs, achieving 74.19% accuracy on ImageNet and 66.2% mAP@50 and 49.1% mAP@50:95 on COCO, surpassing previous bests with the same architecture by +3.45% and +1.6% and +1.8%, respectively. Notably, our SNNs match or exceed ANNs' performance with the same architecture, and the energy efficiency is improved by 6.3${\times}$.