AI Paper Atlas

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

Synchronizing Task Behavior: Aligning Multiple Tasks during Test-Time Training

Wooseong Jeong, Jegyeong Cho, Youngho Yoon, Kuk-Jin Yoon

ICCV 2025 · 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 Task Behavior Synchronizer (TBS) (ablation)S4T · Taskonomy to NYUD-v2Delta_TTT: +0.00 -> +26.16Improved
add Task Behavior Synchronizer (TBS) (ablation)S4T · Taskonomy to PASCAL-ContextDelta_TTT: +0.00 -> +28.32Improved
add task-specific projection to TBS (ablation)S4T · Taskonomy to NYUD-v2Delta_TTT: +26.16 -> +33.79Improved
add task-specific projection to TBS (ablation)S4T · Taskonomy to PASCAL-ContextDelta_TTT: +28.32 -> +32.27Improved
add feature masking (ablation)S4T · Taskonomy to NYUD-v2Delta_TTT: +33.79 -> +34.94Improved
add feature masking (ablation)S4T · Taskonomy to PASCAL-ContextDelta_TTT: +32.27 -> +34.20Improved
use image reconstruction as auxiliary task instead of task labels (ablation)S4T · Taskonomy to NYUD-v2Delta_TTT: +34.94 -> +26.76Hurt
use same masking across all tasks instead of random masking (ablation)S4T · Taskonomy to NYUD-v2Delta_TTT: +32.76 -> +34.94Improved
use same masking across all tasks instead of non-overlapping masking (ablation)S4T · Taskonomy to NYUD-v2Delta_TTT: +32.56 -> +34.94Improved
use same masking across all tasks instead of hiding specific tasks (ablation)S4T · Taskonomy to NYUD-v2Delta_TTT: +33.06 -> +34.94Improved
raise masking ratio to about 0.7-0.8 (ablation)S4T · Taskonomy to NYUD-v2Delta_TTTImproved
apply S4T when adapting from NYUD-v2 to TaskonomyS4T · NYUD-v2 to TaskonomyDelta_TTT: +2.13Mixed

Earlier methods this paper compares with

Named baselines from earlier accepted papers in this paper's results tables: better than 5 of 5 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