Meta-Teacher For Face Anti-Spoofing

TL;DR

This paper introduces a Meta-Teacher framework for face anti-spoofing that trains a meta-teacher to supervise detectors more effectively, leading to improved detection performance by learning intrinsic spoofing cues.

Contribution

The novel Meta-Teacher FAS method trains a meta-teacher via bi-level optimization to enhance supervision of PA detectors, surpassing handcrafted labels and existing teacher-student models.

Findings

Meta-Teacher outperforms handcrafted labels in supervision quality.

Significant performance improvements on five FAS benchmarks.

Meta-Teacher provides richer spoofing cues for better detection.

Abstract

Face anti-spoofing (FAS) secures face recognition from presentation attacks (PAs). Existing FAS methods usually supervise PA detectors with handcrafted binary or pixel-wise labels. However, handcrafted labels may are not the most adequate way to supervise PA detectors learning sufficient and intrinsic spoofing cues. Instead of using the handcrafted labels, we propose a novel Meta-Teacher FAS (MT-FAS) method to train a meta-teacher for supervising PA detectors more effectively. The meta-teacher is trained in a bi-level optimization manner to learn the ability to supervise the PA detectors learning rich spoofing cues. The bi-level optimization contains two key components: 1) a lower-level training in which the meta-teacher supervises the detector's learning process on the training set; and 2) a higher-level training in which the meta-teacher's teaching performance is optimized by minimizing the detector's validation loss. Our meta-teacher differs significantly from existing teacher-student models because the meta-teacher is explicitly trained for better teaching the detector (student), whereas existing teachers are trained for outstanding accuracy neglecting teaching ability. Extensive experiments on five FAS benchmarks show that with the proposed MT-FAS, the trained meta-teacher 1) provides better-suited supervision than both handcrafted labels and existing teacher-student models; and 2) significantly improves the performances of PA detectors.