Rehearsal-Free and Efficient Continual Learning for Cross-Domain Face Anti-Spoofing
IEEE Transactions on Pattern Analysis and Machine Intelligence · 2025-12 · 47 (12) · 11348-11365
DOI: 10.1109/tpami.2025.3601053 ↗Kurz gefasst
Fachartikel in der Zeitschrift IEEE Transactions on Pattern Analysis and Machine Intelligence, 2025-12. Verfasst von Rizhao Cai und 5 weiteren Autor:innen. Die Arbeit wurde bisher 16-mal zitiert (Crossref) und nennt 85 Literaturangaben. Gefördert von: National Natural Science Foundation of China, CCF-Tencent Rhino-Bird Open Research Fund, NTU-PKU Joint Research Institute.
Abstract (Originalsprache)
Face Anti-Spoofing (FAS) is constantly challenged by new attack types and mediums, and thus it is crucial for a FAS model to not only mitigate Catastrophic Forgetting (CF) of previously learned spoofing knowledge on the training data during continual learning but also enhance the model's generalization ability to potential spoofing attacks. In this paper, we first highlight that current strategies for catastrophic forgetting are not well-suited to the imperceptible nature of spoofing information in FAS and lack the focus on improving generalization capability. Then, the instance-wise dynamic central difference convolutional adapter module with the weighted ensemble strategy for Vision Transformer (ViT) is proposed for efficiently fine-tuning with low-shot data by extracting generalized spoofing texture information. Furthermore, we find that catastrophic forgetting in FAS can be reflected through the inconsistent attention matrices of ViT between different continual sessions, as the attention matrices embody relationships of spoofing clues between different patch tokens. Hence, we introduce attention consistency regularization by learning and reusing attention matrices to alleviate catastrophic forgetting. Finally, we devise new protocols and conduct extensive experiments to validate the superior performance of alleviating catastrophic forgetting and generalization on unseen domains.
Förderung
- National Natural Science Foundation of China
- CCF-Tencent Rhino-Bird Open Research Fund
- NTU-PKU Joint Research Institute
- Guangdong Provincial Key Laboratory
- Guangdong Research Team for Communication and Sensing Integrated with Intelligent Computing
- Science and Technology Development Fund of Macau
- Medical Science and Technology Foundation of Guangdong Province
- Basic and Applied Basic Research Foundation of Guangdong Province
Zitieren
APA
Cai, R., Cui, Y., Yu, Z., Lin, X., Chen, C., & Kot, A. (2025). Rehearsal-Free and Efficient Continual Learning for Cross-Domain Face Anti-Spoofing. IEEE Transactions on Pattern Analysis and Machine Intelligence, 47(12), 11348-11365. https://doi.org/10.1109/tpami.2025.3601053
Vancouver
Cai R, Cui Y, Yu Z, Lin X, Chen C, Kot A. Rehearsal-Free and Efficient Continual Learning for Cross-Domain Face Anti-Spoofing. IEEE Transactions on Pattern Analysis and Machine Intelligence. 2025;47(12):11348-11365. doi:10.1109/tpami.2025.3601053
BibTeX
@article{Cai2025,
author = {Cai, Rizhao and Cui, Yawen and Yu, Zitong and Lin, Xun and Chen, Changsheng and Kot, Alex},
title = {Rehearsal-Free and Efficient Continual Learning for Cross-Domain Face Anti-Spoofing},
journal = {IEEE Transactions on Pattern Analysis and Machine Intelligence},
year = {2025},
volume = {47},
number = {12},
pages = {11348--11365},
doi = {10.1109/tpami.2025.3601053}
}
EUVIMED