AI Paper Atlas

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

Adaptive Debiasing Tsallis Entropy for Test-Time Adaptation

Xiangyu Wu, Dongming Jiang, Feng Yu, Yueying Tian, Jiaqi Tang, Qing-Guo Chen, Yang Yang, Jianfeng Lu

ICLR 2026 · Label-efficient and robust learning › Test-time adaptation · approach: Pseudo-label test-time adaptation · 8 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 ADTE entropy (vs removing it) (ablation)ADTE (Templates) · ImageNet variants, ViT-B/16accuracy (%): 65.4 -> 66.5Improved
add ADTE entropy (ablation)ADTE (Templates) · ImageNet, ViT-B/16accuracy (%): 71.1 -> 71.8Improved
add ADTE entropy (ablation)ADTE (Templates) · 10 cross-domain datasets, ViT-B/16accuracy (%): 66.9 -> 69.0Improved
add ADTE entropy (ablation)ADTE (Templates) · ImageNet variants, ViT-L/14accuracy (%): 76.3 -> 77.0Improved
add ADTE entropy (ablation)ADTE (Templates) · 10 cross-domain datasets, ViT-L/14accuracy (%): 73.2 -> 74.8Improved
add logit adjustment (ablation)ADTE (Templates) · 10 cross-domain datasets, ViT-B/16accuracy (%): 68.8 -> 69.0Improved
add logit adjustment (ablation)ADTE (Templates) · ImageNet variants, ViT-B/16accuracy (%): 66.1 -> 66.5Improved
add logit adjustment (ablation)ADTE (Templates) · 10 cross-domain datasets, ViT-L/14accuracy (%): 74.1 -> 74.8Improved
use ADTE instead of Shannon entropy (SE-LA) (ablation)ADTE (Templates) · ImageNet, ViT-B/16accuracy (%): 71.0 -> 71.8Improved
use ADTE instead of fixed-q Tsallis entropy (q=0.5) (ablation)ADTE (Templates) · ImageNet-A, ViT-B/16accuracy (%): 64.8 -> 65.5Improved
increase memory bank size per class from 1 to 40 (ablation)ADTE (Templates) · ImageNet, ViT-B/16accuracy (%): 71.71 -> 71.86No clear effect
swap Min-Max normalization for Decimal Scaling (ablation)ADTE (Templates) · ImageNet, ViT-B/16accuracy (%): 71.8 -> 72.0No clear effect

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