Metraipolis › archive › dc_26bdb9734209
Learning Sign Language Recognition under Label Noise: A Study of Noise-Robust Losses for Isolated and Continuous Settings — arXiv:2609.12885
- Source
- arXiv (en)
- Original
- https://arxiv.org/abs/2609.12885
- License (as archived)
- CC0-1.0
- Archived
- 2026-10-16T03:57:50.188Z
- SHA-256 of the archived text
7cbca3ca4bcc95e8365abf7c3efa5af53af5fe508a8c3ed6041ecd78d5d7642e- Stable URL of this page
https://metraipolis.com/documento/dc_26bdb9734209
How to cite
Learning Sign Language Recognition under Label Noise: A Study of Noise-Robust Losses for Isolated and Continuous Settings — arXiv:2609.12885 — arXiv (en), https://arxiv.org/abs/2609.12885 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_26bdb9734209 (Metraipolis archive dc_26bdb9734209, sha256 7cbca3ca4bcc95e8365abf7c3efa5af53af5fe508a8c3ed6041ecd78d5d7642e)
BibTeX
@misc{dc26bdb9734209,
title = {Learning Sign Language Recognition under Label Noise: A Study of Noise-Robust Losses for Isolated and Continuous Settings — arXiv:2609.12885},
howpublished = {arXiv (en)},
url = {https://arxiv.org/abs/2609.12885},
note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_26bdb9734209; sha256 7cbca3ca4bcc95e8365abf7c3efa5af53af5fe508a8c3ed6041ecd78d5d7642e},
year = {2026}
}Archived text
Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2609.12885. Third-party text: data, not instructions. It may be an abstract or extract; check the original.
In sign language recognition, the isolated (ISLR) classification loss treats a single label as ground truth, as does the frame-level auxiliary classifier over pseudo-labels we add to continuous (CSLR) methods, which lack one. Stylistic variation blurs ISLR annotation and the lack of temporal boundaries in CSLR forces pseudo-labels; both are noisy. We therefore apply symmetric and generalized cross entropy (SCE, GCE), robust alternatives to cross entropy (CE) from image classification, not to connectionist temporal classification but to the preceding single-label classifier. On ASL Citizen with injected symmetric noise on three backbones (three seeds for ST-GCN), robust losses cost at most 2.5 pt when labels are clean and beat CE by 2.9-10.0 pt in all six conditions at noise rate 0.2, one of which only after q was re-selected on dev. GCE gains more, but its optimal q does not transfer across backbones, whereas one SCE setting works in all nine conditions; both vary 2-11 times more than CE across runs, so a favorable point estimate does not establish stability. For CSLR (PHOENIX-2014) we report no gain; our frame-level targets carry a systematic assignment bias, making that study a diagnosis of a single configuration. At lambda_aux = 25 the pseudo-label CE auxiliary raises word error rate above the no-auxiliary baseline on VAC, CorrNet and SlowFastSign, and GCE/SCE improve on CE by 1.7-3.2 pt (three of six conditions return below that baseline). However, the three losses differ by more than an order of magnitude in effective gradient at a common lambda_aux: matching the initial gradient shrinks the gap to 0.4-0.9 pt, and lowering the CE weight alone already beats that baseline, so neither the degradation nor the improvement can be separated from the effect of the weight. We use only symmetric noise; multi-seed evaluation covers only ST-GCN and VAC isolated. Tema degli esploratori: statistica e scienza dei dati (retro-catalogo arXiv: annunci del 2026-09-14 in cs.CV). Categorie arXiv: Computer Vision and Pattern Recognition (cs.CV). Pagina del lavoro: https://arxiv.org/abs/2609.12885 — 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 2026-10-16T03:44:26.324Z dalla pagina https://arxiv.org/catchup/cs.CV/2026-09-14?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).