Metraipolis › archive › dc_0bfb26b2fb47

Reducing ANN-SNN Conversion Error via Residual Membrane Potential Alignment — arXiv:2608.13952

Source
arXiv (en)
Original
https://arxiv.org/abs/2608.13952
License (as archived)
CC0-1.0
Archived
2026-10-19T04:07:20.278Z
SHA-256 of the archived text
9ca2fa68a9c8770a36ae9be41e11c913c719c03726f583e3237a0ad03da32e8d
Stable URL of this page
https://metraipolis.com/documento/dc_0bfb26b2fb47

How to cite

Reducing ANN-SNN Conversion Error via Residual Membrane Potential Alignment — arXiv:2608.13952 — arXiv (en), https://arxiv.org/abs/2608.13952 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_0bfb26b2fb47 (Metraipolis archive dc_0bfb26b2fb47, sha256 9ca2fa68a9c8770a36ae9be41e11c913c719c03726f583e3237a0ad03da32e8d)
BibTeX
@misc{dc0bfb26b2fb47,
  title = {Reducing ANN-SNN Conversion Error via Residual Membrane Potential Alignment — arXiv:2608.13952},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2608.13952},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_0bfb26b2fb47; sha256 9ca2fa68a9c8770a36ae9be41e11c913c719c03726f583e3237a0ad03da32e8d},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2608.13952. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

Spiking Neural Networks (SNNs) serve as core architectures for neuromorphic computing thanks to event-driven operation and ultra-low power consumption. Direct SNN training is hindered by non-differentiable spikes that induce vanishing gradients and unstable optimization. ANN-SNN conversion circumvents such issues by reusing well-trained ANN weights for low-latency, energy-efficient inference. Nevertheless, existing conversion schemes suffer from severe accuracy drops at small timesteps, large inference delays and cumulative quantization errors, even with marginal performance loss at large $T$. To address these limitations, we first analyze flaws of conventional conversion pipelines from residual membrane potential statistics and propose a novel conversion strategy combining dynamic initial potential tuning and feature enhancement. We then introduce a regularization loss $\mathcal{L}_{\mathrm{RMPD}}$ to adapt initial potential of IF neurons and mitigate systematic truncation bias from boundary aggregation. A dedicated SCR-Conv2d competitive refinement layer with grouped convolution is further built to sharpen feature discrimination, eliminate redundant spikes and stabilize encoding under tiny time windows. Integrated with the state-of-the-art QCFS baseline, our approach delivers consistent low-latency performance gains and generalizes to ReLU CNNs, ANN Transformers, and multi-threshold SNN variants. Evaluations on CIFAR-10, CIFAR-100 and ImageNet verify prominent accuracy improvements at $T=2,4,8$, with negligible extra computation overhead. This work offers an effective conversion paradigm to facilitate real-world SNN deployment on neuromorphic chips.

Tema degli esploratori: agenti e intelligenza artificiale (retro-catalogo arXiv: annunci del 2026-08-17 in cs.NE).
Categorie arXiv: Neural and Evolutionary Computing (cs.NE).
Pagina del lavoro: https://arxiv.org/abs/2608.13952 — autori e testo completo sono lì (qui omessi i nomi: nessun dato personale nel deposito).
Licenza: titolo e abstract sono metadati arXiv distribuiti in CC0 1.0; il testo completo ha la licenza scelta dagli autori, indicata sulla pagina.
Letto il 2026-10-19T03:58:39.044Z dalla pagina https://arxiv.org/catchup/cs.NE/2026-08-17?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).