Differential Coding for Training-Free ANN-to-SNN Conversion
Fuente:
arXiv
Saved in:
| Main Authors: | , , , , , , , , |
|---|---|
| Format: | Preprint |
| Published: |
2025
|
| Subjects: | |
| Online Access: | |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866918085724733440 |
|---|---|
| author | Huang, Zihan Fang, Wei Bu, Tong Xue, Peng Hao, Zecheng Liu, Wenxuan Tang, Yuanhong Yu, Zhaofei Huang, Tiejun |
| author_facet | Huang, Zihan Fang, Wei Bu, Tong Xue, Peng Hao, Zecheng Liu, Wenxuan Tang, Yuanhong Yu, Zhaofei Huang, Tiejun |
| contents | 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. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2503_00301 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | Differential Coding for Training-Free ANN-to-SNN Conversion Huang, Zihan Fang, Wei Bu, Tong Xue, Peng Hao, Zecheng Liu, Wenxuan Tang, Yuanhong Yu, Zhaofei Huang, Tiejun Computer Vision and Pattern Recognition 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. |
| title | Differential Coding for Training-Free ANN-to-SNN Conversion |
| topic | Computer Vision and Pattern Recognition |
| url | https://arxiv.org/abs/2503.00301 |