AI Paper Atlas

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

Multi-modal Test-time Adaptation via Adaptive Probabilistic Gaussian Calibration

Jinglin Xu, Yi Li, Chuxiong Sun, Xiao Xu, Jiangmeng Li, Fanjiang Xu

CVPR 2026 · Label-efficient and robust learning › Test-time adaptation · approach: Pseudo-label test-time adaptation · 0 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 asymmetry rectification (AR) alone (ablation)AdaPGC base · Kinetics50-C (video), average accuracyaccuracy: 63.81 -> 65.09Improved
add fused logits (FL) alone (ablation)AdaPGC base · Kinetics50-C (video), average accuracyaccuracy: 63.81 -> 63.57No clear effect
add prediction alignment (PA) alone (ablation)AdaPGC base · Kinetics50-C (video), average accuracyaccuracy: 63.81 -> 63.94No clear effect
add FL and PA together (canonical-GDA-like setting) (ablation)AdaPGC base · Kinetics50-C (video), average accuracyaccuracy: 63.81 -> 64.9Improved
add asymmetry rectification on top of FL and PA (ablation)AdaPGC (FL+PA) · Kinetics50-C (video), average accuracyaccuracy: 64.9 -> 66.08Improved
add all three components FL, PA, AR (ablation)AdaPGC base · Kinetics50-C (video), average accuracyaccuracy: 63.81 -> 66.08Improved
add FL alone (ablation)AdaPGC base · Kinetics50-C (audio), average accuracyaccuracy: 71.88 -> 72.27Improved
add AR alone (ablation)AdaPGC base · Kinetics50-C (audio), average accuracyaccuracy: 71.88 -> 72.25Improved
add AR on top of FL and PA (ablation)AdaPGC (FL+PA) · Kinetics50-C (audio), average accuracyaccuracy: 72.90 -> 73.19Improved
add all three components (ablation)AdaPGC base · Kinetics50-C (audio), average accuracyaccuracy: 71.88 -> 73.19Improved
vary lambda, w_c and w_g (ablation)AdaPGC · Kinetics50-CaccuracyNo clear effect
apply Tent test-time adaptationCAV-MAE source · VGGSound-C (corrupted audio)average accuracy: 25.6 -> 4.5Hurt

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