AI Paper Atlas

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

Source-Free Domain Adaptation with Contrastive Domain Alignment and Self-Supervised Exploration for Face Anti-Spoofing

Yuchen Liu, Yabo Chen, Wenrui Dai, Mengran Gou, Chun-Ting Huang, Hongkai Xiong

ECCV 2022 · Label-efficient and robust learning › Domain adaptation and generalization · approach: Source-free domain adaptation · 54 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 source-oriented regularization (SR) to self-training (ablation)SDA-FAS · O&M&I→CHTER (%): 8.89 -> 6.67Improved
add source-oriented regularization (SR) to self-training (ablation)SDA-FAS · I&C&M→OHTER (%): 14.68 -> 9.44Improved
add contrastive domain alignment (CDA) (ablation)SDA-FAS · O&M&I→CHTER (%): 6.67 -> 4.44Improved
add contrastive domain alignment (CDA) (ablation)SDA-FAS · I&C&M→OHTER (%): 9.44 -> 7.50Improved
add target self-supervised exploration (TSE) (ablation)SDA-FAS · O&M&I→CHTER (%): 4.44 -> 2.40Improved
add target self-supervised exploration (TSE) (ablation)SDA-FAS · I&C&M→OHTER (%): 7.50 -> 5.07Improved
add target self-supervised exploration (TSE) (ablation)SDA-FAS · M&C&O→CA (3D mask)HTER (%): 20.52 -> 11.27Improved
use SDA-FAS instead of SHOTSFDA · I&C&M→OHTER (%): 13.33 -> 6.52Improved
use SDA-FAS instead of Lv et al. self-training adaptationSFDA · multi-source cross-dataset averageHTER reduction after adaptation: 1.9% -> 12.7%Improved
adapt with only 10% of target training data (ablation)SDA-FAS · O&M&I→CHTER (%): 20.00 -> 10.56Improved
adapt with 50% instead of 10% of target data (ablation)SDA-FAS · O&M&I→CHTER (%): 10.56 -> 5.37Improved
use only 5% spoof faces (all live) for adaptation (ablation)SDA-FAS · O&M&I→CHTER (%): 20.00 -> 11.29Improved

Earlier methods this paper compares with

Named baselines from earlier accepted papers in this paper's results tables: better than 1 of 1 on most shared results.

Matched by method name in results tables read by AI. Authors' own tables tend to favour the newer method, and a comparison can be missed when a method is renamed.

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