arXiv：cs.AI· Francesco Panetta, Federico Di Valerio, Michela Proietti·· 20 小时前
基于显著性引导重放的深度脉冲神经网络持续学习
Saliency-Guided Replay for Continual Learning in Deep Spiking Neural Networks
AI 导读
研究将经验打包与重放（EPR）用于低延迟约束下的深度脉冲神经网络持续学习，通过 Spike Activation Maps（SAM）聚合时空注意力图，挑选信息量最大的图像块进行重放，而非存储完整图像。在 Split CIFAR10 和 Split CIFAR100 上，SAM 引导的 EPR 在紧张内存预算下改善了精度-内存权衡，且所需存储大幅减少。
正文
Abstract:Spiking Neural Networks (SNNs) are promising for energy-efficient neuromorphic computing, but they still suffer from catastrophic forgetting when learning tasks sequentially. This work investigates the integration of Experience Packing and Replay (EPR) as a memory-efficient continual learning strategy for deep SNNs under low-latency constraints. The proposed framework combines Batch Normalization Through Time stabilized VGG9 SNNs with Spike Activation Maps (SAM), which provide forward-only explanations based on spike activity. These explanations are temporally aggregated into spatial attention maps and used to select the most informative image patches for replay, instead of storing full images. Experiments on Split CIFAR10 and Split CIFAR100 show that SAM-guided EPR improves the accuracy-memory trade-off under tight memory budgets, and remains competitive while requiring substantially less storage.
| Comments: | Streaming Continual Learning Workshop. In post-proceeding of International Workshops of ECML PKDD 2026 |
| Subjects: | Machine Learning (cs.LG); Artificial Intelligence (cs.AI); Computer Vision and Pattern Recognition (cs.CV); Neural and Evolutionary Computing (cs.NE) |
| Cite as: | arXiv:2610.17998 [cs.LG] |
| (or arXiv:2610.17998v1 [cs.LG] for this version) | |
| https://doi.org/10.48550/arXiv.2610.17998 arXiv-issued DOI via DataCite (pending registration) |
Submission history
From: Federico Di Valerio [view email]
[v1]
Tue, 13 Oct 2026 08:58:28 UTC (591 KB)
来源：arXiv：cs.AI · arxiv.org