AI Paper Atlas

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

Adaptive Transformers for Robust Few-Shot Cross-Domain Face Anti-Spoofing

Hsin-Ping Huang, Deqing Sun, Yaojie Liu, Wen-Sheng Chu, Taihong Xiao, Jinwei Yuan, Hartwig Adam, Ming-Hsuan Yang

ECCV 2022 · Label-efficient and robust learning › Domain adaptation and generalization · approach: Cross-domain few-shot with transformers · 108 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 CelebA-Spoof as extra source data0-shot SSDG · Protocol 1AUC: average improvement of 0.76 AUCImproved
replace SSDG backbone with ViT0-shot · Protocol 1/2AUC: +2.5 on M, +5.0 on C, +3.6 on O, +3.6 on W, +0.7 on C, +14.1 on S, -1.1 on IImproved
add triplet loss or adversarial learning to ViT (ablation)ViT · Protocol 1/2AUCNo clear effect
add 5-shot target samplesSSDG · Protocol 1/2AUC: average of 2.78 AUCImproved
add 5-shot target samplesViT · Protocol 1/2AUC: average of 0.77 AUCImproved
use adapters (ViTA) instead of SSDG5-shot · Protocol 1/2AUC: +1.45 M, +5.54 C, +0.51 O, +0.40 W, +0.35 C, +3.60 S, -0.57 IImproved
add FWT layers to adapters (ViTAF vs ViTA) (ablation)ViTA · Protocol 1AUC: +0.46 M, +0.72 C, +0.77 I, +0.29 OImproved
add FWT layers to adapters (ViTAF vs ViTA) (ablation)ViTA · Protocol 2AUC: improvements only for the S domain (+2.28)Mixed
use ensemble adapters with cosine loss instead of single adapter (ViTAF* vs ViTAF) (ablation)ViTAF · Protocol 1/2AUC: +0.32 M, +0.07 C, +0.30 I, +0.41 O, +0.27 W, +0.86 C, +0.90 SImproved
add adapters or FWT to ViT (ViTA, ViTF, ViTAF) (ablation)ViT · Protocol 1 (average of last eight checkpoints)AUCImproved
remove adapters from first four layers instead of last four (ablation)ViTAF* · Protocol 1TPR@FPR=1%Hurt

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