AI Paper Atlas

Research map / Label-efficient and robust learning / Domain adaptation and generalization

Generative Domain Adaptation for Face Anti-Spoofing

Qianyu Zhou, Ke-Yue Zhang, Taiping Yao, Ran Yi, Kekai Sheng, Shouhong Ding, Lizhuang Ma

ECCV 2022 · Label-efficient and robust learning › Domain adaptation and generalization · approach: Feature alignment for unsupervised adaptation · 78 citations (OpenAlex)

Read the paperCheck your idea against 137,217 papers

AI-extracted. The measured effects below were read by AI from the paper's full text (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.

Measured effects reported in the paper

What was changedWhereMeasuredEffect
add neural statistic consistency (NSC) (ablation)source-trained FAS model · I&C&M to OAUC (%): 80.9 -> 84.9Improved
add NSC (ablation)source-trained FAS model · O&C&I to MHTER (%): 29.2 -> 20.0Improved
add NSC (ablation)source-trained FAS model · O&M&I to CHTER (%): 32.7 -> 28.7Improved
add dual-level semantic consistency (DSC) on top of NSC (ablation)GDA · O&M&I to CHTER (%): 28.7 -> 14.4Improved
add DSC on top of NSC (ablation)GDA · O&C&I to MAUC (%): 89.0 -> 92.0Improved
add DSC on top of NSC (ablation)GDA · I&C&M to OHTER (%): 21.1 -> 16.5Improved
add intra-domain spectrum mixup (SpecMix) (ablation)GDA with NSC+DSC · O&C&I to MHTER (%): 14.1 -> 9.2Improved
add SpecMix (ablation)GDA with NSC+DSC · O&M&I to CHTER (%): 14.4 -> 12.2Improved
add SpecMix (ablation)GDA with NSC+DSC · O&C&M to IAUC (%): 91.5 -> 96.0Improved
add SpecMix (ablation)GDA with NSC+DSC · I&C&M to OHTER (%): 16.5 -> 14.4Improved
raise SpecMix eta from 0.1 to 0.5 during training (ablation)GDA · O&C&I to MAUC (%): 98.0 -> 97.2No clear effect
raise SpecMix eta from 0.1 to 0.4 at inference (ablation)GDA on Idiap Replay-Attack · Replay-AttackHTER (%): 0 -> 0No clear effect

Closest papers by meaning

Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.

Open scime draft

Get the next scime Dispatch and a monthly field update

Free. We send a confirmation link first; every email has a one-click unsubscribe. Privacy