Differential Coding for Training-Free ANN-to-SNN Conversion

Zihan Huang, Wei Fang, Tong Bu, Peng Xue, Zecheng Hao, Wenxuan Liu, Yuanhong Tang, Zhaofei Yu, Tiejun Huang
Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:25235-25264, 2025.

Abstract

Spiking Neural Networks (SNNs) exhibit significant potential due to their low energy consumption. Converting Artificial Neural Networks (ANNs) to SNNs is an efficient way to achieve high-performance SNNs. However, many conversion methods are based on rate coding, which requires numerous spikes and longer time-steps compared to directly trained SNNs, leading to increased energy consumption and latency. This article introduces differential coding for ANN-to-SNN conversion, a novel coding scheme that reduces spike counts and energy consumption by transmitting changes in rate information rather than rates directly, and explores its application across various layers. Additionally, the threshold iteration method is proposed to optimize thresholds based on activation distribution when converting Rectified Linear Units (ReLUs) to spiking neurons. Experimental results on various Convolutional Neural Networks (CNNs) and Transformers demonstrate that the proposed differential coding significantly improves accuracy while reducing energy consumption, particularly when combined with the threshold iteration method, achieving state-of-the-art performance. The source codes of the proposed method are available at https://github.com/h-z-h-cell/ANN-to-SNN-DCGS.

Cite this Paper

BibTeX
@InProceedings{pmlr-v267-huang25i, title = {Differential Coding for Training-Free {ANN}-to-{SNN} Conversion}, author = {Huang, Zihan and Fang, Wei and Bu, Tong and Xue, Peng and Hao, Zecheng and Liu, Wenxuan and Tang, Yuanhong and Yu, Zhaofei and Huang, Tiejun}, booktitle = {Proceedings of the 42nd International Conference on Machine Learning}, pages = {25235--25264}, year = {2025}, editor = {Singh, Aarti and Fazel, Maryam and Hsu, Daniel and Lacoste-Julien, Simon and Berkenkamp, Felix and Maharaj, Tegan and Wagstaff, Kiri and Zhu, Jerry}, volume = {267}, series = {Proceedings of Machine Learning Research}, month = {13--19 Jul}, publisher = {PMLR}, pdf = {https://raw.githubusercontent.com/mlresearch/v267/main/assets/huang25i/huang25i.pdf}, url = {https://proceedings.mlr.press/v267/huang25i.html}, abstract = {Spiking Neural Networks (SNNs) exhibit significant potential due to their low energy consumption. Converting Artificial Neural Networks (ANNs) to SNNs is an efficient way to achieve high-performance SNNs. However, many conversion methods are based on rate coding, which requires numerous spikes and longer time-steps compared to directly trained SNNs, leading to increased energy consumption and latency. This article introduces differential coding for ANN-to-SNN conversion, a novel coding scheme that reduces spike counts and energy consumption by transmitting changes in rate information rather than rates directly, and explores its application across various layers. Additionally, the threshold iteration method is proposed to optimize thresholds based on activation distribution when converting Rectified Linear Units (ReLUs) to spiking neurons. Experimental results on various Convolutional Neural Networks (CNNs) and Transformers demonstrate that the proposed differential coding significantly improves accuracy while reducing energy consumption, particularly when combined with the threshold iteration method, achieving state-of-the-art performance. The source codes of the proposed method are available at https://github.com/h-z-h-cell/ANN-to-SNN-DCGS.} }
Endnote
%0 Conference Paper %T Differential Coding for Training-Free ANN-to-SNN Conversion %A Zihan Huang %A Wei Fang %A Tong Bu %A Peng Xue %A Zecheng Hao %A Wenxuan Liu %A Yuanhong Tang %A Zhaofei Yu %A Tiejun Huang %B Proceedings of the 42nd International Conference on Machine Learning %C Proceedings of Machine Learning Research %D 2025 %E Aarti Singh %E Maryam Fazel %E Daniel Hsu %E Simon Lacoste-Julien %E Felix Berkenkamp %E Tegan Maharaj %E Kiri Wagstaff %E Jerry Zhu %F pmlr-v267-huang25i %I PMLR %P 25235--25264 %U https://proceedings.mlr.press/v267/huang25i.html %V 267 %X Spiking Neural Networks (SNNs) exhibit significant potential due to their low energy consumption. Converting Artificial Neural Networks (ANNs) to SNNs is an efficient way to achieve high-performance SNNs. However, many conversion methods are based on rate coding, which requires numerous spikes and longer time-steps compared to directly trained SNNs, leading to increased energy consumption and latency. This article introduces differential coding for ANN-to-SNN conversion, a novel coding scheme that reduces spike counts and energy consumption by transmitting changes in rate information rather than rates directly, and explores its application across various layers. Additionally, the threshold iteration method is proposed to optimize thresholds based on activation distribution when converting Rectified Linear Units (ReLUs) to spiking neurons. Experimental results on various Convolutional Neural Networks (CNNs) and Transformers demonstrate that the proposed differential coding significantly improves accuracy while reducing energy consumption, particularly when combined with the threshold iteration method, achieving state-of-the-art performance. The source codes of the proposed method are available at https://github.com/h-z-h-cell/ANN-to-SNN-DCGS.
APA
Huang, Z., Fang, W., Bu, T., Xue, P., Hao, Z., Liu, W., Tang, Y., Yu, Z. & Huang, T.. (2025). Differential Coding for Training-Free ANN-to-SNN Conversion. Proceedings of the 42nd International Conference on Machine Learning, in Proceedings of Machine Learning Research 267:25235-25264 Available from https://proceedings.mlr.press/v267/huang25i.html.

Related Material