Inference-Scale Complexity in ANN-SNN Conversion for High-Performance and Low-Power Applications

TL;DR

This paper introduces an efficient ANN-SNN conversion framework focusing on inference scale complexity, enabling low-power, high-performance neural network deployment in various computer vision tasks with minimal performance loss.

Contribution

The authors propose a novel conversion framework with a local threshold balancing algorithm and delayed evaluation strategy, improving efficiency and scalability of SNNs from pre-trained ANNs.

Findings

Outperforms existing conversion methods in accuracy and efficiency

Demonstrates significant energy savings in SNNs over traditional ANNs

Applicable to multiple computer vision tasks with negligible performance loss

Abstract

Spiking Neural Networks (SNNs) have emerged as a promising substitute for Artificial Neural Networks (ANNs) due to their advantages of fast inference and low power consumption. However, the lack of efficient training algorithms has hindered their widespread adoption. Even efficient ANN-SNN conversion methods necessitate quantized training of ANNs to enhance the effectiveness of the conversion, incurring additional training costs. To address these challenges, we propose an efficient ANN-SNN conversion framework with only inference scale complexity. The conversion framework includes a local threshold balancing algorithm, which enables efficient calculation of the optimal thresholds and fine-grained adjustment of the threshold value by channel-wise scaling. We also introduce an effective delayed evaluation strategy to mitigate the influence of the spike propagation delays. We demonstrate the scalability of our framework in typical computer vision tasks: image classification, semantic segmentation, object detection, and video classification. Our algorithm outperforms existing methods, highlighting its practical applicability and efficiency. Moreover, we have evaluated the energy consumption of the converted SNNs, demonstrating their superior low-power advantage compared to conventional ANNs. This approach simplifies the deployment of SNNs by leveraging open-source pre-trained ANN models, enabling fast, low-power inference with negligible performance reduction. Code is available at https://github.com/putshua/Inference-scale-ANN-SNN.