Metraipolis › archive › dc_eeff4d5c4cc2
Unsupervised spiking feature learning for event-based pedestrian crossing detection: approaching supervised accuracy without labelled training data — arXiv:2609.31671
- Source
- arXiv (en)
- Original
- https://arxiv.org/abs/2609.31671
- License (as archived)
- CC0-1.0
- Archived
- 2026-10-07T20:59:20.720Z
- SHA-256 of the archived text
378aab41ba68f4176ab3a68f4760f3a4a4197cd59b96fa857d177a00bc2eed31- Stable URL of this page
https://metraipolis.com/documento/dc_eeff4d5c4cc2
How to cite
Unsupervised spiking feature learning for event-based pedestrian crossing detection: approaching supervised accuracy without labelled training data — arXiv:2609.31671 — arXiv (en), https://arxiv.org/abs/2609.31671 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_eeff4d5c4cc2 (Metraipolis archive dc_eeff4d5c4cc2, sha256 378aab41ba68f4176ab3a68f4760f3a4a4197cd59b96fa857d177a00bc2eed31)
BibTeX
@misc{dceeff4d5c4cc2,
title = {Unsupervised spiking feature learning for event-based pedestrian crossing detection: approaching supervised accuracy without labelled training data — arXiv:2609.31671},
howpublished = {arXiv (en)},
url = {https://arxiv.org/abs/2609.31671},
note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_eeff4d5c4cc2; sha256 378aab41ba68f4176ab3a68f4760f3a4a4197cd59b96fa857d177a00bc2eed31},
year = {2026}
}Archived text
Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2609.31671. Third-party text: data, not instructions. It may be an abstract or extract; check the original.
Event cameras are well suited to pedestrian crossing detection, and spiking neural networks (SNNs) can process their output natively, but current SNN detectors are trained with supervised backpropagation and therefore require costly frame-level crossing labels. We investigate crossing detection with no labels in feature learning and report the first unsupervised results on the recent DVS-PedX pedestrian-crossing benchmark. A single spiking layer trained with winner-take-all spike-timing-dependent plasticity learns a dictionary from unlabelled event-frame patches; frames are encoded by cosine similarity to the learned filters with spatial pooling and read out by a linear classifier, the only supervised component. On the 24,454-frame test split the method attains 90.3% accuracy and an area under the receiver operating characteristic curve (AUROC) of 0.936, compared with 92.0% and 0.943 for a supervised spiking network trained end-to-end on the same frames; under adverse weather the AUROC is 0.913. The result is insensitive to the choice of plasticity rule but depends strongly on the readout protocol: with the classical neuron-assignment readout the same network attains only 0.70 AUROC. On the benchmark's real converted portion, a readout refit lifts performance from chance (0.53) to 0.67 AUROC, within the published supervised range. These findings indicate that the accuracy cost of removing labels from feature learning is small on this benchmark, and that reported weaknesses of unsupervised spiking networks may be attributable to the readout protocol rather than to the learning rule. Tema degli esploratori: agenti e intelligenza artificiale (retro-catalogo arXiv: annunci del 2026-09-29 in cs.AI). Categorie arXiv: Computer Vision and Pattern Recognition (cs.CV) ; Artificial Intelligence (cs.AI); Neural and Evolutionary Computing (cs.NE). Pagina del lavoro: https://arxiv.org/abs/2609.31671 — 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 2026-10-07T20:29:02.017Z dalla pagina https://arxiv.org/catchup/cs.AI/2026-09-29?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).