AI Paper Atlas

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

Purify then Guide: Rethinking Domain Generalization for Multimodal Face Anti-Spoofing

Yingjie Ma, Xun Lin, Zitong Yu, Haonan Wang, Ruixin Zhang, Shouhong Ding, Xin Liu, Xiaochen Yuan, Weicheng Xie, Linlin Shen

ECCV 2026 · Label-efficient and robust learning › Domain adaptation and generalization · approach: Augmentation and mixture-of-experts generalization · 6 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 standard multi-head self-attention (ablation)Dense Adaptor · PS->CWHTER: 23.26 -> 25.85Hurt
Replace MHSA with Differential Attention (ablation)Dense Adaptor · PS->CWHTER: 25.85 -> 16.49Improved
Replace DA with MD2A (ablation)Dense Adaptor · PS->CWHTER: 16.49 -> 13.47Improved
Replace DA with MD2A (ablation)MoE Adaptor · PS->CWHTER: 12.72 -> 9.70Improved
Replace MHSA with MD2A (ablation)MoE Adaptor · PS->CWHTER: 12.83 -> 9.70Improved
Use label smoothing in alignment (ablation)MMDA · PS->CWHTER: 9.70 -> 9.17Improved
Use RS2 subspace alignment plus shared classifier instead of smooth alignment (ablation)MMDA · PS->CWHTER: 9.17 -> 8.88Improved
Increase U-DSA depth up to 7 layers (ablation)MMDA · PS->CWAUCImproved
Use MMDA over DADM, complete modalityMMDA · Protocol 1 averageHTER: 13.63 -> 4.00Improved
Use MMDA over DADM, missing modalityMMDA · Protocol 2 averageHTER: 21.66 -> 10.14Improved
Pair MD2A noise branch with same-domain samples instead of random or cross-domain (ablation)MD2A · residual varianceVar[R]: 7.48e-7 (random) -> 4.31e-7Improved
Same-domain pairing for decision variance (ablation)MD2A · decision stabilityVar[z]: 1.662e-3 (random) vs 1.672e-3 (same-domain)No clear effect

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