mlsanityData to 14 Oct 2026

Saliency-Guided Replay for Continual Learning in Deep Spiking Neural Networks

arXiv 2610.17998 ↗First posted 13 Oct 2026cs.LG cs.AI cs.CVcited by 0

Not on the map. Why?

Abstract (arXiv)

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.

Key facts. No citing papers in the map yet (data through 14 Oct 2026). Builds on 17 of its 29 references that are in the map. First posted on arXiv 13 Oct 2026.

Builds on

17 of 29 references.

References · 17

  1. 2016Grad-CAM: Visual Explanations from Deep Networks via Gradient-based Localizationcited by 6,733
  2. 2013Visualizing and Understanding Convolutional Networkscited by 2,290
  3. 2018Experience Replay for Continual Learningcited by 1,095
  4. 2020Dark Experience for General Continual Learning: a Strong, Simple Baselinecited by 911
  5. 2019Surrogate Gradient Learning in Spiking Neural Networkscited by 626
  6. 2018Deep Learning in Spiking Neural Networkscited by 263
  7. 2018Going Deeper in Spiking Neural Networks: VGG and Residual Architecturescited by 245
  8. 2020Revisiting Batch Normalization for Training Low-latency Deep Spiking Neural Networks from Scratchcited by 80
  9. 2020Remembering for the Right Reasons: Explanations Reduce Catastrophic Forgettingcited by 34
  10. 2021Visual Explanations from Spiking Neural Networks using Interspike Intervalscited by 27
  11. 2017ASP: Learning to Forget with Adaptive Synaptic Plasticity in Spiking Neural Networkscited by 16
  12. 2021Saliency Guided Experience Packing for Replay in Continual Learningcited by 15
5 more
  1. 2022Bayesian Continual Learning via Spiking Neural Networkscited by 13
  2. 2024Continual Learning with Neuromorphic Computing: Foundations, Methods, and Emerging Applicationscited by 8
  3. 2024Compressed Latent Replays for Lightweight Continual Learning on Spiking Neural Networkscited by 3
  4. 2022Saliency-Augmented Memory Completion for Continual Learningcited by 2
  5. 2025CIP-Net: Continual Interpretable Prototype-based Networkcited by 1

Built on by

Not cited yet.