.png){kind=icon}
返回
Consistency Regularization for Deep Face Anti-Spoofing
.png){kind=icon}
OA
AI
DOI：10.1109/TIFS.2023.3235581.png)
.png){kind=icon}
原文求助.png){kind=icon}
分享.png){kind=icon}
收藏
摘要
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.
Keyword:
Face recognition
Faces
Task analysis
Training
Benchmark testing
Supervised learning
Protocols
Face anti-spoofing
consistency regularization
semi-supervised learning
期刊
IF:
8
论文数:
5.3K
被引数:
2.3W
机构
引用论文
Guanosine 5´-O-(3-Thiotriphosphate) and Cations Regulate Melatonin Receptors, and Melatonin Inhibits Cyclic AMP Production in the Spinal Cord.png)
Neurosignals
NeurosignalsIF0
PREAI
分享收藏分享收藏
查看更多内容