Paper Detail

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

Francesco Panetta, Federico Di Valerio, Michela Proietti

arxiv Score 18.0

Published 2026-10-13 · First seen 2026-10-14

Research Track A · General AI

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.

Workflow Status

Review status
pending
Role
unreviewed
Read priority
now
Vote
Not set.
Saved
no
Collections
Not filed yet.
Next action
Not filled yet.

Reading Brief

No structured notes yet. Add `summary_sections`, `why_relevant`, `claim_impact`, or `next_action` in `papers.jsonl` to enrich this view.

Why It Surfaced

No ranking explanation is available yet.

Tags

No tags.

BibTeX

@article{panetta2026saliency,
  title = {Saliency-Guided Replay for Continual Learning in Deep Spiking Neural Networks},
  author = {Francesco Panetta and Federico Di Valerio and Michela Proietti},
  year = {2026},
  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 expla},
  url = {https://arxiv.org/abs/2610.17998},
  keywords = {cs.LG, cs.AI, cs.CV, cs.NE},
  eprint = {2610.17998},
  archiveprefix = {arXiv},
}

Metadata

{}