Quantization Meets Spikes: Lossless Conversion in the First Timestep via Polarity Multi-Spike Mapping

TL;DR

This paper introduces Polarity Multi-Spike Mapping, a novel method for nearly lossless ANN-to-SNN conversion at a single timestep, achieving high accuracy and energy efficiency by analyzing and mitigating quantization information loss.

Contribution

The paper presents the first analysis of quantization-induced information loss via entropy and proposes PMSM with hyperparameter tuning for ultra-low latency conversion.

Findings

Achieves 98.5% accuracy on CIFAR-10 with one timestep

Reduces energy consumption by over 5x on VGG-16

Sets new benchmarks for one-timestep ANN-to-SNN conversion

Abstract

Spiking neural networks (SNNs) offer advantages in computational efficiency via event-driven computing, compared to traditional artificial neural networks (ANNs). While direct training methods tackle the challenge of non-differentiable activation mechanisms in SNNs, they often suffer from high computational and energy costs during training. As a result, ANN-to-SNN conversion approach still remains a valuable and practical alternative. These conversion-based methods aim to leverage the discrete output produced by the quantization layer to obtain SNNs with low latency. Although the theoretical minimum latency is one timestep, existing conversion methods have struggled to realize such ultra-low latency without accuracy loss. Moreover, current quantization approaches often discard negative-value information following batch normalization and are highly sensitive to the hyperparameter configuration, leading to degraded performance. In this work, we, for the first time, analyze the information loss introduced by quantization layers through the lens of information entropy. Building on our analysis, we introduce Polarity Multi-Spike Mapping (PMSM) and a hyperparameter adjustment strategy tailored for the quantization layer. Our method achieves nearly lossless ANN-to-SNN conversion at the extremity, i.e., the first timestep, while also leveraging the temporal dynamics of SNNs across multiple timesteps to maintain stable performance on complex tasks. Experimental results show that our PMSM achieves state-of-the-art accuracies of 98.5% on CIFAR-10, 89.3% on CIFAR-100 and 81.6% on ImageNet with only one timestep on ViT-S architecture, establishing a new benchmark for efficient conversion. In addition, our method reduces energy consumption by over 5x under VGG-16 on CIFAR-10 and CIFAR-100, compared to the baseline method.