Adaptive Transformers for Robust Few-Shot Cross-Domain Face Anti-Spoofing
Abstract
While recent face anti-spoofing methods perform well under the intra-domain setups, an effective approach needs to account for much larger appearance variations of images acquired in complex scenes with different sensors for robust performance. In this paper, we present adaptive vision transformers (ViT) for robust cross-domain face anti-spoofing. Specifically, we adopt ViT as a backbone to exploit its strength to account for long-range dependencies among pixels. We further introduce the ensemble adapters module and feature-wise transformation layers in the ViT to adapt to different domains for robust performance with a few samples. Experiments on several benchmark datasets show that the proposed models achieve both robust and competitive performance against the state-of-the-art methods.
Cite
Text
Huang et al. "Adaptive Transformers for Robust Few-Shot Cross-Domain Face Anti-Spoofing." Proceedings of the European Conference on Computer Vision (ECCV), 2022. doi:10.1007/978-3-031-19778-9_3Markdown
[Huang et al. "Adaptive Transformers for Robust Few-Shot Cross-Domain Face Anti-Spoofing." Proceedings of the European Conference on Computer Vision (ECCV), 2022.](https://mlanthology.org/eccv/2022/huang2022eccv-adaptive/) doi:10.1007/978-3-031-19778-9_3BibTeX
@inproceedings{huang2022eccv-adaptive,
title = {{Adaptive Transformers for Robust Few-Shot Cross-Domain Face Anti-Spoofing}},
author = {Huang, Hsin-Ping and Sun, Deqing and Liu, Yaojie and Chu, Wen-Sheng and Xiao, Taihong and Yuan, Jinwei and Adam, Hartwig and Yang, Ming-Hsuan},
booktitle = {Proceedings of the European Conference on Computer Vision (ECCV)},
year = {2022},
doi = {10.1007/978-3-031-19778-9_3},
url = {https://mlanthology.org/eccv/2022/huang2022eccv-adaptive/}
}