Look Locally Infer Globally: A Generalizable Face Anti-Spoofing Approach
| Autor: | Debayan Deb, Anil K. Jain |
|---|---|
| Jazyk: | angličtina |
| Rok vydání: | 2020 |
| Předmět: |
FOS: Computer and information sciences
021110 strategic defence & security studies Computer Networks and Communications business.industry Computer science media_common.quotation_subject Computer Vision and Pattern Recognition (cs.CV) Feature extraction 0211 other engineering and technologies Computer Science - Computer Vision and Pattern Recognition 02 engineering and technology Overfitting Machine learning computer.software_genre Facial recognition system Presentation Discriminative model Face (geometry) Benchmark (computing) Artificial intelligence Safety Risk Reliability and Quality business computer media_common |
| Popis: | 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). |
| Databáze: | OpenAIRE |
| Externí odkaz: |
|