用传统图像训练的模型，帮脉冲神经网络提升性能。
Cross Knowledge Distillation between Artificial and Spiking Neural Networks
- 跨模态跨架构知识蒸馏，让脉冲网络学传统模型的本领。
- 在N-Caltech101和CEP-DVS上准确率超现有方法。
- 适合想提升脉冲神经网络性能的研究者参考。
脉冲神经网络（SNN）因生物合理性、事件驱动特性和节能优势，在计算机视觉领域展现出巨大潜力。然而，受限于标注的事件数据集较少以及架构不成熟，其性能仍逊于人工神经网络（ANN）。为提升SNN在最优数据格式——动态视觉传感器（DVS）数据上的表现，本文探索利用RGB图像和高性能ANN进行知识蒸馏。针对跨模态与跨架构挑战，提出交叉知识蒸馏（CKD）方法：通过语义相似性与滑动替换缓解跨模态问题，采用间接分阶段蒸馏解决跨架构差异。在主流类脑数据集N-Caltech101和CEP-DVS上验证，实验结果表明该方法优于当前最先进方法。代码将开源。
原文摘要 · Abstract (English)
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
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。