Consistency Regularization for Deep Face Anti-Spoofing

doi:10.1109/TIFS.2023.3235581

Consistency Regularization for Deep Face Anti-Spoofing

2023-01-01

17

OA

AI

DOI：10.1109/TIFS.2023.3235581

Original

Original request for help

Save

Abstract

En 中文

Face anti-spoofing (FAS) plays a crucial role in securing face recognition systems. Empirically, given an image, a model with more consistent output on different views (i.e., augmentations) of this image usually performs better. Motivated by this exciting observation, we conjecture that encouraging feature consistency of different views may be a promising way to boost FAS models. In this paper, we explore this way thoroughly by enhancing both Embedding-level and Prediction-level Consistency Regularization (EPCR) in FAS. Specifically, at the embedding level, we design a dense similarity loss to maximize the similarities between all positions of two intermediate feature maps in a self-supervised fashion; while at the prediction level, we optimize the mean square error between the predictions of two views. Notably, our EPCR is free of annotations and can directly integrate into semi-supervised learning schemes. Considering different application scenarios, we further design five diverse semi-supervised protocols to measure semi-supervised FAS techniques. We conduct extensive experiments to show that EPCR can significantly improve the performance of several supervised and semi-supervised tasks on benchmark datasets.

Keywords:

Face recognition

Faces

Task analysis

Training

Benchmark testing

Supervised learning

Protocols

Face anti-spoofing

consistency regularization

semi-supervised learning

Consistency Regularization for Deep Face Anti-Spoofing

Abstract

Journal

Organization