AI Paper Atlas

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

Towards Data-Centric Face Anti-spoofing: Improving Cross-Domain Generalization via Physics-Based Data Synthesis

Rizhao Cai, Cecelia Soh, Zitong Yu, Haoliang Li, Wenhan Yang, Alex Chichung Kot

IJCV 2024 · Label-efficient and robust learning › Domain adaptation and generalization · approach: Augmentation and mixture-of-experts generalization · 27 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
replace traditional augmentation with FAS-AugViT-Convpass · MICO averageHTER (%): 11.53 -> 8.93Improved
add Con loss and SARE to FAS-AugViT-Convpass · MICO averageHTER (%): 8.93 -> 7.39Improved
replace traditional augmentation with FAS-AugResNet-18 · O&M&I to CHTER (%): 18.00 -> 21.50Hurt
add supervised contrastive loss on real faces (ablation)ViT-Convpass · I&C&M to OHTER (%): 8.31 -> 7.43Improved
add SARE loss (ablation)ViT-Convpass · I&C&M to OHTER (%): 8.31 -> 7.81Improved
add both Con loss and SARE (ablation)ViT-Convpass · I&C&M to OHTER (%): 8.31 -> 6.77Improved
add extra real-face data (SiW, ROSE-YOUTU) with traditional augmentationViT-Convpass&TA · C&I&O to MHTER (%): 13.33 -> 24.03Hurt
add FAS-Aug, Con and SARE when extra real faces are usedViT-Convpass · C&I&O+SY to MHTER (%): 24.03 -> 6.92Improved
replace traditional augmentation with FAS-AugSSDG-R* · C&M&I to OHTER (%): 16.73 -> 15.25Improved
replace traditional augmentation with FAS-AugSSAN-R* · C&M&I to OHTER (%): 16.92 -> 13.79Improved
replace traditional augmentation with FAS-AugFLIP-MCL* · C&M&I to OHTER (%): 8.69 -> 7.41Improved
combine FAS-Aug with traditional augmentationViT-ConvPass · I&C&M to OHTER (%): 10.74 -> 6.71Improved

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