Look Locally Infer Globally: A Generalizable Face Anti-Spoofing Approach
This addresses generalization issues in face anti-spoofing for security applications, but it is incremental as it builds on existing local and self-supervised approaches.
The paper tackles the problem of face anti-spoofing methods overfitting to known spoof types by proposing a self-supervised framework that learns local discriminative cues, achieving 65% TDR at 2% FDR on a dataset with 13 unknown spoof types and maintaining computational efficiency (<4 ms).
State-of-the-art spoof detection methods tend to overfit to the spoof types seen during training and fail to generalize to unknown spoof types. Given that face anti-spoofing is inherently a local task, we propose a face anti-spoofing framework, namely Self-Supervised Regional Fully Convolutional Network (SSR-FCN), that is trained to learn local discriminative cues from a face image in a self-supervised manner. The proposed framework improves generalizability while maintaining the computational efficiency of holistic face anti-spoofing approaches (< 4 ms on a Nvidia GTX 1080Ti GPU). The proposed method is interpretable since it localizes which parts of the face are labeled as spoofs. Experimental results show that SSR-FCN can achieve TDR = 65% @ 2.0% FDR when evaluated on a dataset comprising of 13 different spoof types under unknown attacks while achieving competitive performances under standard benchmark datasets (Oulu-NPU, CASIA-MFSD, and Replay-Attack).