AI Paper Atlas

Research map / Label-efficient and robust learning / Recognition and long-tail

CelebA-Spoof: Large-Scale Face Anti-Spoofing Dataset with Rich Annotations

Yuanhan Zhang, ZhenFei Yin, Yidong Li, Guojun Yin, Junjie Yan, Jing Shao, Ziwei Liu

ECCV 2020 · Label-efficient and robust learning › Recognition and long-tail · approach: Fair and quality-aware face recognition · 245 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 semantic attribute supervision to live/spoof classification (ablation)baseline ResNet-18 · CelebA-SpoofACER (%): 3.8 -> 2.85Improved
use semantic attributes alone instead of live/spoof label (ablation)baseline · CelebA-SpoofACER (%): 3.8 -> 4.17Hurt
add spoof type attribute supervision (ablation)AENetC,S · CelebA-SpoofAPCER (%): 5.31 -> 4.62Improved
add face attribute supervision (ablation)AENetC,S · CelebA-SpoofBPCER (%): 1.37 -> 1.09Improved
add illumination supervision (ablation)AENetC,S · CelebA-SpoofACER (%): 2.99 -> 2.85Improved
add depth map supervision as auxiliary (ablation)baseline · CelebA-SpoofACER (%): 3.8 -> 3.26Improved
use depth map alone for classification (ablation)baseline · CelebA-SpoofACER (%): 3.8 -> 4.51Hurt
add depth map to AENetC,G (ablation)AENetC,G · CelebA-SpoofACER (%): 3.55 -> 3.26Improved
add reflection map to AENetC,G (ablation)AENetC,G · CelebA-SpoofACER (%): 3.59 -> 3.26Improved
add both semantic and geometric supervisionAENetC,S,G · CelebA-Spoof cross-domain Protocol 1ACER (%): 4.11 -> 3.09Improved
add geometric supervision to baselineAENetC,G · Protocol 2 sensorACER (%): 5.05 -> 5.31Hurt
train on CelebA-Spoof instead of SiWAENetC,S,G · CASIA-MFSDHTER (%): 27.6 -> 11.9Improved

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