Cross Knowledge Distillation between Artificial and Spiking Neural Networks
This work addresses the problem of limited performance in SNNs for computer vision applications, offering an incremental improvement through knowledge distillation techniques.
The paper tackles the performance gap between Spiking Neural Networks (SNNs) and Artificial Neural Networks (ANNs) on neuromorphic datasets by proposing cross knowledge distillation (CKD) to leverage RGB data and ANNs, achieving state-of-the-art results on N-Caltech101 and CEP-DVS datasets.
Recently, Spiking Neural Networks (SNNs) have demonstrated rich potential in computer vision domain due to their high biological plausibility, event-driven characteristic and energy-saving efficiency. Still, limited annotated event-based datasets and immature SNN architectures result in their performance inferior to that of Artificial Neural Networks (ANNs). To enhance the performance of SNNs on their optimal data format, DVS data, we explore using RGB data and well-performing ANNs to implement knowledge distillation. In this case, solving cross-modality and cross-architecture challenges is necessary. In this paper, we propose cross knowledge distillation (CKD), which not only leverages semantic similarity and sliding replacement to mitigate the cross-modality challenge, but also uses an indirect phased knowledge distillation to mitigate the cross-architecture challenge. We validated our method on main-stream neuromorphic datasets, including N-Caltech101 and CEP-DVS. The experimental results show that our method outperforms current State-of-the-Art methods. The code will be available at https://github.com/ShawnYE618/CKD