AI Paper Atlas

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

Multi-Task Test-time Adaptation via Gradient Consensus and Plasticity Constraint

Zhong Ye, Yu Hu, Zhenguo Yang

AAAI 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 gradient consensus plus plasticity constraint to M-TENT (ablation)M-TENT · PlantData (avg of 6 shifts)Mean I&O F1: 90.52 -> 91.57Improved
add gradient consensus plus plasticity constraint to M-TENT (ablation)M-TENT · CelebA (avg of 6 shifts)Mean I&O F1: 93.35 -> 93.37No clear effect
add only one of the two modules (ablation)M-TENT · PlantData (avg of 6 shifts)Mean I&O F1: 90.52 -> 90.66 / 90.57No clear effect
add both modules, average across datasets (ablation)M-TENT · PlantData and CelebAAverage Mean I&O across datasets: 91.94 -> 92.47Improved
use CoCo-MT-TTA instead of M-TENTmulti-task TTA · PlantData Gaussian noiseMean I&O F1: 92.17 -> 93.12Improved
use CoCo-MT-TTA instead of EATAmulti-task TTA · PlantData Impulse noiseMean I&O F1: 88.99 -> 87.25Hurt
use CoCo-MT-TTA instead of EATAmulti-task TTA · PlantData ContrastMean I&O F1: 77.85 -> 77.52No clear effect
apply test-time adaptation (M-TENT) without ID constraintmulti-task model · PlantDataF1 on ID samplesHurt
use ActMAD adaptationmulti-task model · PlantDataMean I&O F1: 75.55 -> 34.44Hurt

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