AI Paper Atlas

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

Dynamic Logits Adjustment and Exploration for Test-Time Adaptation in Vision Language Models

Haoyan Wu, Yahao Liu, Yinjie Lei, Lixin Duan, Wen Li

CVPR 2026 · Label-efficient and robust learning › Test-time adaptation · approach: Pseudo-label test-time adaptation

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 Logits Adjustment to DPE-style baseline (ablation)DLAE (ViT-B/16) · Cross-dataset averagetop-1 accuracy: 69.40 -> 70.63Improved
add CGEC on top of DLA (ablation)DLAE (ViT-B/16) · Cross-dataset averagetop-1 accuracy: 70.63 -> 71.88Improved
add entropy adjustment in DLA training (ablation)DLAE (ViT-B/16) · Cross-dataset averagetop-1 accuracy: 69.40 -> 69.85Improved
add logits adjustment at inference (ablation)DLAE (ViT-B/16) · Cross-dataset averagetop-1 accuracy: 69.40 -> 70.39Improved
combine entropy and logits adjustment (ablation)DLAE (ViT-B/16) · Cross-dataset averagetop-1 accuracy: 70.39 -> 70.63Improved
add Semantic Consistency Filter to CGEC (ablation)DLAE (ViT-B/16) · Cross-dataset averagetop-1 accuracy: 70.63 -> 71.26Improved
add Temporal Consistency Filter to CGEC (ablation)DLAE (ViT-B/16) · Cross-dataset averagetop-1 accuracy: 70.63 -> 71.37Improved
add both SCF and TCF (ablation)DLAE (ViT-B/16) · Cross-dataset averagetop-1 accuracy: 70.63 -> 71.88Improved
vary alpha and beta (ablation)DLAE (ViT-B/16) · DTDtop-1 accuracy: 56.58 to 58.86No clear effect
vary eta from 0.002 to 0.05 (ablation)DLAE (ViT-B/16) · DTD, Aircraft, Carstop-1 accuracyNo clear effect
use DLAE instead of DPEDLAE (ViT-B/16) · ImageNet-A (ViT-B/16)top-1 accuracy: 59.63 -> 64.06Improved
use DLAE instead of SCA on ImageNet-RDLAE (ViT-B/16) · ImageNet-R (ViT-B/16)top-1 accuracy: 80.85 -> 80.43Hurt

Earlier methods this paper compares with

Named baselines from earlier accepted papers in this paper's results tables: better than 1 of 1 on most shared results.

Matched by method name in results tables read by AI. Authors' own tables tend to favour the newer method, and a comparison can be missed when a method is renamed.

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