AI Paper Atlas

Research map / Continual learning / Domain and prompt-based

Rehearsal-Free Domain Continual Face Anti-Spoofing: Generalize More and Forget Less

Rizhao Cai, Yawen Cui, Zhi Li, Zitong Yu, Haoliang Li, Yongjian Hu, Alex Kot

ICCV 2023 · Continual learning › Domain and prompt-based · approach: Domain-incremental learning with memory · 37 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
replace linear ViT-Adapter with convolutional (DCDCA-family) adapters (ablation)ViT-Adapter · DCL-FAS Protocol-1mAGA: 58.72 -> 78.70Improved
use ViT-Adapter instead of ResNet18 (ablation)finetuning · DCL-FAS Protocol-1mAA: 83.02 -> 86.72Improved
add learnable dynamic central-difference ratio (DCDCA) over fixed theta=0.7 (CDCA) (ablation)ViT-CDCA · DCL-FAS Protocol-1mAGA: 77.01 -> 78.70Improved
add learnable dynamic central-difference ratio (DCDCA) over fixed theta=0.7 (CDCA) (ablation)ViT-CDCA · DCL-FAS Protocol-2mAGA: 74.48 -> 78.09Improved
add central difference (CDCA) over plain convolution adapter (ConvA) (ablation)ViT-ConvA · DCL-FAS Protocol-1mAA: 93.29 -> 93.06No clear effect
add PPCR instead of plain finetuning (ablation)ViT-DCDCA · DCL-FAS Protocol-1mAGA: 78.70 -> 82.06Improved
add PPCR instead of plain finetuning (ablation)ViT-DCDCA · DCL-FAS Protocol-1mABT: -3.59 -> -3.29Improved
add PPCR instead of plain finetuning (ablation)ViT-ConvA · DCL-FAS Protocol-1mAA: 93.29 -> 93.04No clear effect
add proxy prototypes to contrastive regularization (PPCR vs CR) (ablation)ViT-DCDCA · DCL-FAS Protocol-1mABT: -3.57 -> -3.48Improved
add proxy prototypes to contrastive regularization (PPCR vs CR) (ablation)ViT-DCDCA · DCL-FAS Protocol-2mAGA: 80.31 -> 80.08No clear effect
PPCR instead of EWC/LWF regularizationViT-DCDCA · DCL-FAS Protocol-1mAGA: 78.41 (EWC), 78.68 (LWF) -> 82.06Improved
PPCR instead of EWC/LWF regularizationViT-DCDCA · DCL-FAS Protocol-1mABT: -0.163 (EWC), -0.97 (LWF) vs -3.48Hurt

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