Metraipolis › archive › dc_bb62408175ca
RIPE-MambaSpike: Resolution-Independent Spiking-State-Space Interfaces for Parameter-Efficient Event-Based Vision — arXiv:2609.32537
- Source
- arXiv (en)
- Original
- https://arxiv.org/abs/2609.32537
- License (as archived)
- CC0-1.0
- Archived
- 2026-10-07T23:50:59.111Z
- SHA-256 of the archived text
37bf4a739cb27a8f467a452dec79d4e92d38510492e881adc7de1e0ddecdc7e7- Stable URL of this page
https://metraipolis.com/documento/dc_bb62408175ca
How to cite
RIPE-MambaSpike: Resolution-Independent Spiking-State-Space Interfaces for Parameter-Efficient Event-Based Vision — arXiv:2609.32537 — arXiv (en), https://arxiv.org/abs/2609.32537 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_bb62408175ca (Metraipolis archive dc_bb62408175ca, sha256 37bf4a739cb27a8f467a452dec79d4e92d38510492e881adc7de1e0ddecdc7e7)
BibTeX
@misc{dcbb62408175ca,
title = {RIPE-MambaSpike: Resolution-Independent Spiking-State-Space Interfaces for Parameter-Efficient Event-Based Vision — arXiv:2609.32537},
howpublished = {arXiv (en)},
url = {https://arxiv.org/abs/2609.32537},
note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_bb62408175ca; sha256 37bf4a739cb27a8f467a452dec79d4e92d38510492e881adc7de1e0ddecdc7e7},
year = {2026}
}Archived text
Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2609.32537. Third-party text: data, not instructions. It may be an abstract or extract; check the original.
Spiking-Mamba hybrids reach strong accuracy on event-based vision, but existing designs often require tens of millions of parameters. Much of that cost comes from how the spiking front-end is connected to the state-space backbone rather than from the hybrid architecture itself. In a representative model, a single resolution-dependent projection accounts for 33.55M of 36.25M parameters. To that end, we introduce RIPE-MambaSpike (Resolution-Independent, Parameter-Efficient), which replaces that projection with a hierarchical multi-resolution bridge of fixed channel width. Its deployed footprint is 0.870M parameters, constant at fixed time steps and widths across a 43x range of input areas. Reparameterized spiking stages, temporal decoupled modulation, and a dynamic convex-hull-bounded dual-stream membrane-potential attention preserve accuracy under this compact design. Result-wise, RIPE-MambaSpike is pareto-optimal on CIFAR10-DVS, N-Caltech101, and DailyDVS-200. Notably, on the 200-class DailyDVS-200, a scaled 8.04M configuration achieves 45.7% top-1 accuracy, the best reported spiking result on that benchmark, and outperforms prior spiking methods with 3.0-15.1x fewer parameters than dense ANNs. Overall, our findings demonstrate that competitive event-based recognition does not require resolution-dependent parameter growth. Code is available at this https URL . Tema degli esploratori: statistica e scienza dei dati (retro-catalogo arXiv: annunci del 2026-09-29 in cs.CV). Categorie arXiv: Computer Vision and Pattern Recognition (cs.CV) ; Neural and Evolutionary Computing (cs.NE). Pagina del lavoro: https://arxiv.org/abs/2609.32537 — 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 2026-10-07T23:29:27.065Z dalla pagina https://arxiv.org/catchup/cs.CV/2026-09-29?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).