MCAE: Masked Contrastive Autoencoder for Face Anti-Spoofing
Author:
Preprint
Abstract
Face anti-spoofing (FAS) method performs well under the intra-domain setups. But cross-domain performance of the model is not satisfying. Domain generalization method has been used to align the feature from different domain extracted by convolutional neural network (CNN) backbone. However, the improvement is limited. Recently, the Vision Transformer (ViT) model has performed well on various visual tasks. But ViT model relies heavily on pre-training of large-scale dataset, which cannot be satisfied by existing FAS datasets. In this paper, taking the FAS task as an example, we propose Masked Contrastive Autoencoder (MCAE) method to solve this problem using only limited data. Meanwhile in order for a feature extractor to extract common features in live samples from different domains, we combine Masked Image Model (MIM) with supervised contrastive learning to train our model.Some intriguing design principles are summarized for performing MIM pre-training for downstream tasks.We also provide insightful analysis for our method from an information theory perspective. Experimental results show our approach has good performance on extensive public datasets and outperforms the state-of-the-art methods.Keywords
All Related Versions
This publication has 11 references indexed in Scilit:
- Adaptive Transformers for Robust Few-shot Cross-domain Face Anti-spoofing2022
- Vitranspad: Video Transformer Using Convolution And Self-Attention For Face Presentation Attack Detection2022
- Representation learning from noisy user-tagged data for sentiment classificationInternational Journal of Machine Learning and Cybernetics, 2022
- Masked Autoencoders Are Scalable Vision Learners2022
- NAS-FAS: Static-Dynamic Central Difference Network Search for Face Anti-SpoofingIEEE Transactions on Pattern Analysis and Machine Intelligence, 2020
- Cross-Domain Face Presentation Attack Detection via Multi-Domain Disentangled Representation Learning2020
- BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding2019
- Joint Face Detection and Alignment Using Multitask Cascaded Convolutional NetworksIEEE Signal Processing Letters, 2016
- Secure Face Unlock: Spoof Detection on SmartphonesIEEE Transactions on Information Forensics and Security, 2016
- Face Spoof Detection With Image Distortion AnalysisIEEE Transactions on Information Forensics and Security, 2015