AI Paper Atlas

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

Self-Domain Adaptation for Face Anti-Spoofing

Jingjing Wang, Jingyi Zhang, Ying Bian, Youyi Cai, Chunmao Wang, Shiliang Pu

AAAI 2021 · Label-efficient and robust learning › Domain adaptation and generalization · approach: Foundation-model domain generalization · 104 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
Use self-domain adaptation with a meta-learned adaptor and unlabeled test-domain updates instead of RFMface anti-spoofing · O&C&I to MHTER (%): 13.8 -> 15.4Hurt
Use self-domain adaptation with a meta-learned adaptor and unlabeled test-domain updates instead of RFMface anti-spoofing · O&M&I to CHTER (%): 20.2 -> 24.5Hurt
Use self-domain adaptation with a meta-learned adaptor and unlabeled test-domain updates instead of RFMface anti-spoofing · O&C&M to IHTER (%): 17.3 -> 15.6Improved
Use self-domain adaptation with a meta-learned adaptor and unlabeled test-domain updates instead of RFMface anti-spoofing · I&C&M to OHTER (%): 16.4 -> 23.1Hurt
Add reconstruction loss to the adaptor objective (ablation)self-domain adaptation · O&C&I to MHTER (%): 18.8 -> 15.4Improved
Add orthogonality loss to the adaptor objective (ablation)self-domain adaptation · O&M&I to CHTER (%): 29.9 -> 24.5Improved
Add entropy loss to the adaptor objective (ablation)self-domain adaptation · O&C&M to IHTER (%): 26.2 -> 16.4Improved
Add meta-learning adaptor initialization during training (ablation)self-domain adaptation · O&C&I to MHTER (%): 23.5 -> 15.4Improved
Optimize the adaptor on unlabeled test-domain data at inference (ablation)self-domain adaptation · O&M&I to CHTER (%): 32.9 -> 24.5Improved

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