AI Paper Atlas

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

Back to Source: Open-Set Continual Test-Time Adaptation via Domain Compensation

Yingkai Yang, Chaoqi Chen, Hui Huang

CVPR 2026 · Label-efficient and robust learning › Test-time adaptation · approach: Pseudo-label test-time adaptation · 1 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 structural regularizer (R) (ablation)DOCO w/o S.O · ImageNet-C OCTTA (kappa 0.5)H-score (%): 64.0 -> 67.6Improved
add sample splitting and OOD propagation (S, O) (ablation)DOCO w/o R · ImageNet-C OCTTA (kappa 0.5)H-score (%): 64.0 -> 68.5Improved
add structural regularizer on top of S and O (ablation)DOCO · ImageNet-C OCTTA (kappa 0.5)H-score (%): 68.5 -> 70.1Improved
add OOD propagation (O) (ablation)DOCO w/o O · ImageNet-C OCTTA (kappa 0.5)H-score (%): 65.9 -> 70.1Improved
add sample splitting (S) alone (ablation)prompt-based statistical alignment · ImageNet-C OCTTA (kappa 0.5)H-score (%): 64.0 -> 65.1Improved
add S, O and R modules (ablation)norm-based baseline · ImageNet-C OCTTA (kappa 0.5)H-score (%): 60.7 -> 68.1Improved
use prompt learning instead of norm-layer updates (ablation)DOCO full · ImageNet-C OCTTA (kappa 0.5)H-score (%): 68.1 -> 70.1Improved
add structural regularizer in small-batch regime (ablation)DOCO · ImageNet-C OCTTA (kappa 0.5)H-score (%)Improved
increase number of prompts L without raising beta (ablation)DOCO · ImageNet-C OCTTA (kappa 0.5)H-score (%)Hurt
use DOCO instead of source model in closed-setSource model · Closed-set CTTA averageACC (%): 36.9 -> 43.1Improved
use DOCO instead of best baseline on OCTTADPCore · LAION-C OCTTAH-score (%): 30.3 -> 32.7Improved
reduce OOD ratio to 0.1 (ablation)DOCO · ImageNet-C OCTTAH-score (%): 70.1 -> 69.2No 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