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
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 changed | Where | Measured | Effect |
|---|---|---|---|
| add source-oriented regularization (SR) to self-training (ablation) | SDA-FAS · O&M&I→C | HTER (%): 8.89 -> 6.67 | Improved |
| add source-oriented regularization (SR) to self-training (ablation) | SDA-FAS · I&C&M→O | HTER (%): 14.68 -> 9.44 | Improved |
| add contrastive domain alignment (CDA) (ablation) | SDA-FAS · O&M&I→C | HTER (%): 6.67 -> 4.44 | Improved |
| add contrastive domain alignment (CDA) (ablation) | SDA-FAS · I&C&M→O | HTER (%): 9.44 -> 7.50 | Improved |
| add target self-supervised exploration (TSE) (ablation) | SDA-FAS · O&M&I→C | HTER (%): 4.44 -> 2.40 | Improved |
| add target self-supervised exploration (TSE) (ablation) | SDA-FAS · I&C&M→O | HTER (%): 7.50 -> 5.07 | Improved |
| add target self-supervised exploration (TSE) (ablation) | SDA-FAS · M&C&O→CA (3D mask) | HTER (%): 20.52 -> 11.27 | Improved |
| use SDA-FAS instead of SHOT | SFDA · I&C&M→O | HTER (%): 13.33 -> 6.52 | Improved |
| use SDA-FAS instead of Lv et al. self-training adaptation | SFDA · multi-source cross-dataset average | HTER reduction after adaptation: 1.9% -> 12.7% | Improved |
| adapt with only 10% of target training data (ablation) | SDA-FAS · O&M&I→C | HTER (%): 20.00 -> 10.56 | Improved |
| adapt with 50% instead of 10% of target data (ablation) | SDA-FAS · O&M&I→C | HTER (%): 10.56 -> 5.37 | Improved |
| use only 5% spoof faces (all live) for adaptation (ablation) | SDA-FAS · O&M&I→C | HTER (%): 20.00 -> 11.29 | Improved |
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.
- TENT — Tent: Fully Test-Time Adaptation by Entropy Minimization (ICLR 2021) · better on 4 of 4 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
- Source-Free Domain Adaptation With Domain Generalized Pretraining for Face Anti-Spoofing (TPAMI 2024 · similarity 0.96)
- Self-Domain Adaptation for Face Anti-Spoofing (AAAI 2021 · similarity 0.93)
- Gradient Alignment for Cross-Domain Face Anti-Spoofing (CVPR 2024 · similarity 0.90)
- Domain-Hallucinated Updating for Multi-Domain Face Anti-spoofing (AAAI 2024 · similarity 0.90)
- Optimal Transport-Guided Source-Free Adaptation for Face Anti-Spoofing (CVPR 2025 · similarity 0.89)
- Test-Time Domain Generalization for Face Anti-Spoofing (CVPR 2024 · similarity 0.88)
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.
