AI Paper Atlas

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

Bridging Domain Expertise and Generalization for Performance Estimation

Shuxuan Li, Zhilin Zhao, Quyu Kong, Wei-Shi Zheng

CVPR 2026 · Label-efficient and robust learning › Test-time adaptation · approach: Robust optimization for distribution shift · 0 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 dynamic test-time temperature calibration (ablation)FRAP (CLIP) · Average over 18 datasetsMAE (%): 8.20 -> 6.53Improved
use learned test-time temperature instead of fixed 0.05 (ablation)FRAP (CLIP) · Average over 18 datasetsMAE (%): 8.19 -> 6.53Improved
use learned test-time temperature instead of fixed 0.01 (ablation)FRAP (CLIP) · Average over 18 datasetsMAE (%): 6.61 -> 6.53Improved
use test-time calibration instead of raw CLIP similarity (ablation)FRAP (CLIP) · CIFAR-10ECE: 0.590 -> 0.128Improved
use test-time calibration instead of raw CLIP similarity (ablation)FRAP (CLIP) · MNISTECE: 0.027 -> 0.073Hurt
use fixed tau=0.01 instead of test-time calibration (ablation)FRAP (CLIP) · Several datasetsECEMixed
add confidence-weighted fusion of foundation and base predictions (ablation)FRAP · ImageNet natural shiftDelta SAS vs base model: improvement in 100.0% of experiments, mean 0.249Improved
add confidence-weighted fusion over CLIP alone (ablation)FRAP · ImageNet natural shiftDelta SAS vs CLIP: improvement 98.6%, mean 0.486Improved
add confidence-weighted fusion under synthetic corruption (ablation)FRAP · ImageNet synthetic shiftDelta SAS vs base model: improvement 64.4%, mean 0.102Improved
use FRAP fusion instead of CLIP pseudo-labels as ground truth (ablation)FRAP (CLIP) · Average over 18 datasetsMAE (%): 10.32 -> 6.53Improved
use FRAP fusion instead of SigLIP pseudo-labels as ground truth (ablation)FRAP (SigLIP) · Average over 18 datasetsMAE (%): 9.21 -> 7.32Improved
use fixed-temperature calibration instead of TTC with SigLIP (ablation)FRAP (SigLIP) · Average over 18 datasetsMAE (%): 7.32 -> 5.65Hurt

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