AI Paper Atlas

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

Towards Stable Test-time Adaptation in Dynamic Wild World

Shuaicheng Niu, Jiaxiang Wu, Yifan Zhang, Zhiquan Wen, Yaofo Chen, Peilin Zhao, Mingkui Tan

ICLR 2023 · Label-efficient and robust learning › Test-time adaptation · approach: Pseudo-label test-time adaptation · 64 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
use SAR instead of EATAResNet50-GN · ImageNet-C, severity 5, online imbalanced label shiftsaccuracy (%): 31.6 -> 37.2Improved
use SAR instead of EATAVitBase-LN · ImageNet-C, severity 5, online imbalanced label shiftsaccuracy (%): 49.9% vs. 58.0%Improved
use SAR instead of EATAResNet50-GN · ImageNet-C, mixed corruption types, severity 5accuracy (%): 38.1 -> 38.3Improved
add batch-agnostic group or layer normalization instead of batch normalizationonline test-time adaptation · ImageNet-C, mixed shifts, small batches, and imbalanced label shiftsstabilityImproved
add reliable entropy filtering (ablation)pure entropy minimization on ResNet50-GN · ImageNet-C, severity 5, online imbalanced label shiftsaverage accuracy (%): 24.6%->31.7%Improved
add reliable entropy filtering (ablation)pure entropy minimization on VitBase-LN · ImageNet-C, severity 5, online imbalanced label shiftsaverage accuracy (%): 47.6%\rightarrow 53.1%Improved
add sharpness-aware minimization to reliable entropy (ablation)ResNet50-GN · ImageNet-C, severity 5, online imbalanced label shiftsaverage accuracy (%): 31.7%->37.0%Improved
add sharpness-aware minimization to reliable entropy (ablation)VitBase-LN · ImageNet-C, shot noise, severity 5accuracy (%): 35.7%\rightarrow 47.6%Improved
add model recovery to reliable entropy plus sharpness-aware minimization (ablation)VitBase-LN · ImageNet-C, severity 5, online imbalanced label shiftsaverage accuracy (%): 54.5%\rightarrow 58.2%Improved
add model recovery to reliable entropy plus sharpness-aware minimization (ablation)ResNet50-GN · ImageNet-C, severity 5, online imbalanced label shiftsaverage accuracy (%): 37.0 -> 37.0No clear effect
use large-threshold gradient clipping instead of SAR (ablation)online test-time adaptation · ImageNet-C, shot noise, severity 5accuracyHurt
use small-threshold gradient clipping instead of SAR (ablation)online test-time adaptation · ImageNet-C, shot noise, severity 5accuracyNo clear effect

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