Bi-Spectrum Distillation: Addressing Spectral Mismatch in ANN-SNN Knowledge Transfer

Yuxuan Zhang; Yuhang Sun; Wen Yao; Yue Deng; Hongjue Li

AAAI 2026technical0 citations

Bi-Spectrum Distillation: Addressing Spectral Mismatch in ANN-SNN Knowledge Transfer

Yuxuan Zhang, Yuhang Sun, Wen Yao, Yue Deng, Hongjue Li

Abstract

Knowledge distillation from Artificial Neural Networks (ANNs) to Spiking Neural Networks (SNNs) is a prominent training paradigm. However, its efficacy is fundamentally limited by a spectral mismatch: SNNs, with their intrinsic low-pass filtering characteristics, struggle to learn high-frequency details from their ANN teachers, creating a bottleneck in knowledge transfer at both the feature and logit levels. To address this, we propose Bi-Spectrum Distillation (BSD), a novel framework that mitigates the mismatch from two complementary perspectives. First, at the feature level, our Spectral Residual Distillation (SRD) enhances the student SNN

BibTeX

@inproceedings{aaai2026_bispectrumdistil,
  title = {Bi-Spectrum Distillation: Addressing Spectral Mismatch in ANN-SNN Knowledge Transfer},
  author = {Yuxuan Zhang and Yuhang Sun and Wen Yao and Yue Deng and Hongjue Li},
  booktitle = {AAAI 2026},
  year = {2026}
}