Papers › FeatherNets: Convolutional Neural Networks as Light as Feather for Face Anti-spoofing
FeatherNets: Convolutional Neural Networks as Light as Feather for Face Anti-spoofing
Peng Zhang, Fuhao Zou, Zhiwen Wu, Nengli Dai, Skarpness Mark, Michael Fu, Juan Zhao, Kai Li
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).
Code
Repository list and official/mentioned flags are the archive's, frozen 2025-07-28. Reachability, where shown, is from one Syntology probe window (2026-09-16 to 2026-09-18); repositories not probed show nothing. GitHub stars are not tracked.
Code Syntology ran Syntology
Not run by Syntology. Nothing on this page verifies that the listed code works.
Tasks
Results from the paper archive 2025-07-28
| Task | Dataset | Model | Metric | Value | Rank at snapshot | Leaderboard | Report |
|---|---|---|---|---|---|---|---|
| Face Anti-Spoofing | CelebA-Spoof-Enroll5 | FeatherNet | AUC | 97.1 | #5 of 5 | Archive leaderboard | report |
| Face Anti-Spoofing | SiW (Protocol 3) | FeatherNet | ACER | 31.1 | #6 of 7 | Archive leaderboard | report |
| Face Anti-Spoofing | SiW-Enroll5 | FeatherNet | AUC | 98.9 | #3 of 5 | Archive leaderboard | report |
Ranks are positions in the archive's leaderboards as they stood at the 2025-07-28 snapshot. Results published since then are not among these rows, so a rank here is not a current standing.
Methods
Introduced by this paper: Streaming Module
Report a problem or propose a change · a person checks every report against the paper or source before anything changes; decisions are listed on /corrections