Metraipolis › archive › dc_cd8457b3be05
DINOFAS: Bonafide-Centric Representation Learning for Face Anti-Spoofing — arXiv:2611.02756
- Source
- arXiv (en)
- Original
- https://arxiv.org/abs/2611.02756
- License (as archived)
- CC0-1.0
- Archived
- 2026-11-03T11:08:20.301Z
- SHA-256 of the archived text
26657e610bb3fdf88ed93b638f5cd141f3f98a55faee73719ba47168c569cbce- Stable URL of this page
https://metraipolis.com/documento/dc_cd8457b3be05
How to cite
DINOFAS: Bonafide-Centric Representation Learning for Face Anti-Spoofing — arXiv:2611.02756 — arXiv (en), https://arxiv.org/abs/2611.02756 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_cd8457b3be05 (Metraipolis archive dc_cd8457b3be05, sha256 26657e610bb3fdf88ed93b638f5cd141f3f98a55faee73719ba47168c569cbce)
BibTeX
@misc{dccd8457b3be05,
title = {DINOFAS: Bonafide-Centric Representation Learning for Face Anti-Spoofing — arXiv:2611.02756},
howpublished = {arXiv (en)},
url = {https://arxiv.org/abs/2611.02756},
note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_cd8457b3be05; sha256 26657e610bb3fdf88ed93b638f5cd141f3f98a55faee73719ba47168c569cbce},
year = {2026}
}Archived text
Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2611.02756. Third-party text: data, not instructions. It may be an abstract or extract; check the original.
Face anti-spoofing (FAS) models often learn attack- and dataset-specific cues that degrade performance under unseen acquisition conditions and presentation attacks. We present DINOFAS, a DINOv3-based framework that formulates FAS as bonafide-centric representation learning. The proposed framework combines parameter-efficient DINOv3 adaptation using low-rank adaptation (LoRA), an attention style-content disentanglement (ASCD) module for reducing domain-specific appearance variations, and a dual-branch architecture that separates prototype-based liveness learning from attack-semantic supervision. The model is jointly optimized using a bonafide-centric prototype objective, an attack-semantic classification loss applied to detached features, and orthogonality regularization. DINOFAS achieves an average HTER of 9.09\% under the standard OCIM leave-one-domain-out protocol, where training is performed on three source datasets and evaluation is conducted on the held-out unseen domain. We further evaluate synthetic-to-real generalization by training exclusively on SynthASpoof and testing on four unseen real-world datasets, where DINOFAS achieves the lowest average HTER of 21.41\% and the highest average AUC of 86.14\% among the compared methods. Evaluations on OULU-NPU and SiW-Mv2 additionally demonstrate robustness to variations in acquisition conditions, devices, and unseen presentation attacks. Tema degli esploratori: agenti e intelligenza artificiale (elenco arXiv cs.AI, nuovi lavori del giorno). Categorie arXiv: Computer Vision and Pattern Recognition (cs.CV) ; Artificial Intelligence (cs.AI); Image and Video Processing (eess.IV). Pagina del lavoro: https://arxiv.org/abs/2611.02756 — 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 2026-11-03T10:59:46.126Z dalla pagina https://arxiv.org/list/cs.AI/new (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).