Temporal Misalignment in ANN-SNN Conversion and Its Mitigation via Probabilistic Spiking Neurons

TL;DR

This paper identifies temporal misalignment in ANN-SNN conversion and proposes probabilistic spiking neurons to improve performance, achieving state-of-the-art results on multiple datasets and architectures.

Contribution

It introduces biologically plausible probabilistic spiking neurons to mitigate temporal misalignment in ANN-SNN conversion, enhancing accuracy and efficiency.

Findings

Improved performance on CIFAR-10/100, CIFAR10-DVS, and ImageNet datasets.

State-of-the-art results across various architectures.

Theoretical and empirical validation of the proposed method.

Abstract

Spiking Neural Networks (SNNs) offer a more energy-efficient alternative to Artificial Neural Networks (ANNs) by mimicking biological neural principles, establishing them as a promising approach to mitigate the increasing energy demands of large-scale neural models. However, fully harnessing the capabilities of SNNs remains challenging due to their discrete signal processing and temporal dynamics. ANN-SNN conversion has emerged as a practical approach, enabling SNNs to achieve competitive performance on complex machine learning tasks. In this work, we identify a phenomenon in the ANN-SNN conversion framework, termed temporal misalignment, in which random spike rearrangement across SNN layers leads to performance improvements. Based on this observation, we introduce biologically plausible two-phase probabilistic (TPP) spiking neurons, further enhancing the conversion process. We demonstrate the advantages of our proposed method both theoretically and empirically through comprehensive experiments on CIFAR-10/100, CIFAR10-DVS, and ImageNet across a variety of architectures, achieving state-of-the-art results.