From Lightweight CNNs to SpikeNets: Benchmarking Accuracy-Energy Tradeoffs with Pruned Spiking SqueezeNet

TL;DR

This paper benchmarks lightweight spiking neural networks converted from CNNs, demonstrating significant energy efficiency gains and competitive accuracy, and introduces a pruned SqueezeNet variant that further reduces energy consumption for edge applications.

Contribution

It provides the first systematic benchmark of lightweight CNN-to-SNN conversion, evaluates multiple architectures, and proposes a structured pruning method to optimize energy efficiency and accuracy.

Findings

SNNs achieve up to 15.7x higher energy efficiency than CNNs.

SqueezeNet-based SNNs outperform other lightweight SNNs.

Pruning reduces energy consumption by 88.1% with minimal accuracy loss.

Abstract

Spiking Neural Networks (SNNs) are increasingly studied as energy-efficient alternatives to Convolutional Neural Networks (CNNs), particularly for edge intelligence. However, prior work has largely emphasized large-scale models, leaving the design and evaluation of lightweight CNN-to-SNN pipelines underexplored. In this paper, we present the first systematic benchmark of lightweight SNNs obtained by converting compact CNN architectures into spiking networks, where activations are modeled with Leaky-Integrate-and-Fire (LIF) neurons and trained using surrogate gradient descent under a unified setup. We construct spiking variants of ShuffleNet, SqueezeNet, MnasNet, and MixNet, and evaluate them on CIFAR-10, CIFAR-100, and TinyImageNet, measuring accuracy, F1-score, parameter count, computational complexity, and energy consumption. Our results show that SNNs can achieve up to 15.7x higher energy efficiency than their CNN counterparts while retaining competitive accuracy. Among these, the SNN variant of SqueezeNet consistently outperforms other lightweight SNNs. To further optimize this model, we apply a structured pruning strategy that removes entire redundant modules, yielding a pruned architecture, SNN-SqueezeNet-P. This pruned model improves CIFAR-10 accuracy by 6% and reduces parameters by 19% compared to the original SNN-SqueezeNet. Crucially, it narrows the gap with CNN-SqueezeNet, achieving nearly the same accuracy (only 1% lower) but with an 88.1% reduction in energy consumption due to sparse spike-driven computations. Together, these findings establish lightweight SNNs as practical, low-power alternatives for edge deployment, highlighting a viable path toward deploying high-performance, low-power intelligence on the edge.