Adaptive Calibration: A Unified Conversion Framework of Spiking Neural Networks
Proceedings of the AAAI Conference on Artificial Intelligence · 11.04.2025 · 39 (2) · 1583-1591
DOI: 10.1609/aaai.v39i2.32150 ↗Kurz gefasst
Fachartikel in der Zeitschrift Proceedings of the AAAI Conference on Artificial Intelligence, online erschienen am 11.04.2025. Verfasst von Ziqing Wang und 4 weiteren Autor:innen. Die Arbeit wurde bisher 8-mal zitiert (Crossref).
Abstract (Originalsprache)
Spiking Neural Networks (SNNs) are seen as an energy-efficient alternative to traditional Artificial Neural Networks (ANNs), but the performance gap remains a challenge. While this gap is narrowing through ANN-to-SNN conversion, substantial computational resources are still needed, and the energy efficiency of converted SNNs cannot be ensured. To address this, we present a unified training-free conversion framework that significantly enhances both the performance and efficiency of converted SNNs. Inspired by the biological nervous system, we propose a novel Adaptive-Firing Neuron Model (AdaFire), which dynamically adjusts firing patterns across different layers to substantially reduce the Unevenness Error - the primary source of error of converted SNNs within limited inference timesteps. We further introduce two efficiency-enhancing techniques: the Sensitivity Spike Compression (SSC) technique for reducing spike operations, and the Input-aware Adaptive Timesteps (IAT) technique for decreasing latency. These methods collectively enable our approach to achieve state-of-the-art performance with significant energy savings of up to 70.1%, 60.3%, and 43.1% on CIFAR-10, CIFAR-100, and ImageNet datasets, respectively. Extensive experiments across 2D, 3D, event-driven classification tasks, object detection, and segmentation tasks, demonstrate the effectiveness of our method in various domains.
Zitieren
APA
Wang, Z., Fang, Y., Cao, J., Ren, H., & Xu, R. (2025). Adaptive Calibration: A Unified Conversion Framework of Spiking Neural Networks. Proceedings of the AAAI Conference on Artificial Intelligence, 39(2), 1583-1591. https://doi.org/10.1609/aaai.v39i2.32150
Vancouver
Wang Z, Fang Y, Cao J, Ren H, Xu R. Adaptive Calibration: A Unified Conversion Framework of Spiking Neural Networks. Proceedings of the AAAI Conference on Artificial Intelligence. 2025;39(2):1583-1591. doi:10.1609/aaai.v39i2.32150
BibTeX
@article{Wang2025,
author = {Wang, Ziqing and Fang, Yuetong and Cao, Jiahang and Ren, Hongwei and Xu, Renjing},
title = {Adaptive Calibration: A Unified Conversion Framework of Spiking Neural Networks},
journal = {Proceedings of the AAAI Conference on Artificial Intelligence},
year = {2025},
volume = {39},
number = {2},
pages = {1583--1591},
doi = {10.1609/aaai.v39i2.32150}
}
EUVIMED