针对脉冲网络训练中时间步重要性不均的问题，提出选择性知识蒸馏方法。
Not All Timesteps Matter Equally: Selective Alignment Knowledge Distillation for Spiking Neural Networks
- 按错误程度动态选择需对齐的时间步，避免强制所有时间步一致
- 在静态图像和事件数据集上提升性能，最高准确率提高1.8%
- 适合需要高效脉冲神经网络的边缘设备应用
脉冲神经网络（SNN）具有类脑特性与高能效优势，但其性能仍落后于人工神经网络（ANN）。现有知识蒸馏方法通常在所有时间步上强制统一对齐，隐含假设每一步预测同等重要。实际上，SNN的输出随时间演变，中间步骤无需全部正确，只要最终聚合结果正确即可。因此，有效的蒸馏应仅对错误时间步提供修正指导，同时保留有用的时序动态。为此，本文提出选择性对齐知识蒸馏（SeAl-KD），通过等化错误时间步的竞争逻辑值，并基于置信度与时间步间相似性重加权时序对齐。在静态图像和脉冲事件数据集上的大量实验表明，该方法持续优于现有蒸馏方法。代码已开源。
原文摘要 · Abstract (English)
Spiking neural networks (SNNs), which are brain-inspired and spike-driven, achieve high energy efficiency. However, a performance gap between SNNs and artificial neural networks (ANNs) still remains. Knowledge distillation (KD) is commonly adopted to improve SNN performance, but existing methods typically enforce uniform alignment across all timesteps, either from a teacher network or through inter-temporal self-distillation, implicitly assuming that per-timestep predictions should be treated equally. In practice, SNN predictions vary and evolve over time, and intermediate timesteps need not all be individually correct even when the final aggregated output is correct. Under such conditions, effective distillation should not force every timestep toward the same supervision target, but instead provide corrective guidance to erroneous timesteps while preserving useful temporal dynamics. To address this issue, we propose Selective Alignment Knowledge Distillation (SeAl-KD), which selectively aligns class-level and temporal knowledge by equalizing competing logits at erroneous timesteps and reweighting temporal alignment based on confidence and inter-timestep similarity. Extensive experiments on static image and neuromorphic event-based datasets demonstrate consistent improvements over existing distillation methods. The code is available at https://github.com/KaiSUN1/SeAl
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。