Adaptive Transformers for Robust Few-shot Cross-domain Face Anti-spoofing
This addresses the challenge of appearance variations in face anti-spoofing across different sensors and scenes, but it is incremental as it builds on existing transformer methods.
The paper tackles the problem of robust cross-domain face anti-spoofing with few samples by proposing adaptive vision transformers, achieving competitive performance against state-of-the-art methods on benchmark datasets.
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 antispoofing. 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 for cross-domain face anti-spoofing using a few samples.