FeatherNets: Convolutional Neural Networks as Light as Feather for Face Anti-spoofing
This addresses the need for efficient and high-performance face anti-spoofing systems, with incremental improvements in reducing complexity while maintaining accuracy.
The paper tackles face anti-spoofing by proposing FeatherNets, an extremely lightweight CNN architecture, which achieves a baseline of 0.00168 ACER with only 0.35M parameters and 83M FLOPS, and a fusion method that improves performance to 0.0013 ACER in a challenge.
Face Anti-spoofing gains increased attentions recently in both academic and industrial fields. With the emergence of various CNN based solutions, the multi-modal(RGB, depth and IR) methods based CNN showed better performance than single modal classifiers. However, there is a need for improving the performance and reducing the complexity. Therefore, an extreme light network architecture(FeatherNet A/B) is proposed with a streaming module which fixes the weakness of Global Average Pooling and uses less parameters. Our single FeatherNet trained by depth image only, provides a higher baseline with 0.00168 ACER, 0.35M parameters and 83M FLOPS. Furthermore, a novel fusion procedure with ``ensemble + cascade'' structure is presented to satisfy the performance preferred use cases. Meanwhile, the MMFD dataset is collected to provide more attacks and diversity to gain better generalization. We use the fusion method in the Face Anti-spoofing Attack Detection Challenge@CVPR2019 and got the result of 0.0013(ACER), 0.999(TPR@FPR=10e-2), 0.998(TPR@FPR=10e-3) and 0.9814(TPR@FPR=10e-4).