Efficient ANN-SNN Conversion with Error Compensation Learning

TL;DR

This paper introduces an error compensation learning framework for ANN-to-SNN conversion, significantly reducing accuracy loss and inference time, enabling practical low-power, real-time neural network applications.

Contribution

The paper proposes novel techniques including learnable threshold clipping, dual-threshold neurons, and optimized membrane potential initialization for improved ANN-to-SNN conversion accuracy.

Findings

Achieves 94.75% accuracy on CIFAR-10 with only 2 time steps

Reduces inference time significantly compared to existing methods

Maintains high accuracy with ultra-low latency

Abstract

Artificial neural networks (ANNs) have demonstrated outstanding performance in numerous tasks, but deployment in resource-constrained environments remains a challenge due to their high computational and memory requirements. Spiking neural networks (SNNs) operate through discrete spike events and offer superior energy efficiency, providing a bio-inspired alternative. However, current ANN-to-SNN conversion often results in significant accuracy loss and increased inference time due to conversion errors such as clipping, quantization, and uneven activation. This paper proposes a novel ANN-to-SNN conversion framework based on error compensation learning. We introduce a learnable threshold clipping function, dual-threshold neurons, and an optimized membrane potential initialization strategy to mitigate the conversion error. Together, these techniques address the clipping error through adaptive thresholds, dynamically reduce the quantization error through dual-threshold neurons, and minimize the non-uniformity error by effectively managing the membrane potential. Experimental results on CIFAR-10, CIFAR-100, ImageNet datasets show that our method achieves high-precision and ultra-low latency among existing conversion methods. Using only two time steps, our method significantly reduces the inference time while maintains competitive accuracy of 94.75% on CIFAR-10 dataset under ResNet-18 structure. This research promotes the practical application of SNNs on low-power hardware, making efficient real-time processing possible.