AI Paper Atlas

Research map / Label-efficient and robust learning / Test-time adaptation

TRAM: Finetuning-Free Test-Time Adaptation for Generalized Face Anti-Spoofing with Only a Few Bonafide Samples

Wang QIRUI, SI-QI LIU

ECCV 2026 · Label-efficient and robust learning › Test-time adaptation · approach: Test-time adaptation of vision-language models

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 I2CL relation modeling to the FLIP-IT baseline (ablation)TRAM · Protocol 2 (avg)HTER (%): 3.05 -> 1.70Improved
add Consensus Attention Regularization (CAR) (ablation)TRAM (I2CL) · Protocol 2 (avg)HTER (%): 1.70 -> 1.32Improved
add Fine-grained Relation Prompt Learning (FRPL) (ablation)TRAM (I2CL+CAR) · Protocol 2 (avg)HTER (%): 1.32 -> 0.81Improved
replace Siamese fusion with standard cross-attention (ablation)TRAM relation encoder · Protocol 2 (avg)HTER (%): 3.66 -> 2.80Improved
add anchor-input difference in query and key (RCA Q/K) (ablation)cross-attention encoder · Protocol 2 (avg)HTER (%): 2.80 -> 2.04Improved
add mask-aware temperature modulation to RCA (ablation)RCA · Protocol 2 (avg)HTER (%): 2.04 -> 1.70Improved
use Q-difference only versus Q/K difference (ablation)RCA · Protocol 2 (avg)HTER (%): 2.40 -> 2.04Improved
use intensity-based instead of semantic anchor selection (ablation)TRAM · Protocol 2 (avg)HTER (%): 0.97 -> 0.81No clear effect
increase number of bonafide anchor shots beyond 5 (ablation)TRAM · ICM->OAUCNo clear effect
give BUDoPT five target bonafide samples in trainingBUDoPT · Protocol 2 (avg)HTER (%): 0.91 -> 0.96No clear effect
use TRAM finetuning-free relation modeling instead of OTAfinetuning-free TTA · Protocol 2 (avg)HTER (%): 3.21 -> 0.81Improved

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