AI Paper Atlas

Research map / Label-efficient and robust learning / Semi-supervised learning

Towards Multimodal Domain Generalization with Few Labels

Hongzhao Li, Hao Dong, Hualei Wan, Shupan Li, Mingliang Xu, Muhammad Haris Khan

CVPR 2026 · Label-efficient and robust learning › Semi-supervised learning · approach: Holistic semi-supervised pipelines · 3 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 CDCR, DAR and CMPA to the weakly supervised baseline (ablation)SSMDG baseline · HAC, 5 labels per classtop-1 accuracy (%): 45.39 -> 60.77Improved
add CMPA on top of CDCR + DAR (ablation)SSMDG framework · HAC, 5 labels per classtop-1 accuracy (%): 58.64 -> 60.77Improved
add CDCR and DAR together instead of either alone (ablation)SSMDG framework · HAC, 5 labels per classtop-1 accuracy (%): 54.76 / 54.89 -> 58.64Improved
anchor consensus on fused prediction supported by one modality instead of averaging modality predictions (ablation)CDCR · HAC, 5 labels per classtop-1 accuracy (%): 58.26 -> 60.77Improved
use fused-anchored consensus instead of requiring all views to agree (ablation)CDCR · HAC, 5 labels per classtop-1 accuracy (%): 59.16 -> 60.77Improved
use generalized cross-entropy instead of standard cross-entropy on non-consensus samples (ablation)DAR · HAC, 5 labels per classtop-1 accuracy (%): 58.32 -> 60.77Improved
apply DAR to both weak and strong views instead of one (ablation)DAR · HAC, 5 labels per classtop-1 accuracy (%): 60.42 / 60.73 -> 60.77Improved
add cross-domain prototype alignment (ablation)CMPA · HAC, 5 labels per classtop-1 accuracy (%): 58.34 -> 60.77Improved
add cross-modal translation to prototype alignment (ablation)CMPA · HAC, 5 labels per classtop-1 accuracy (%): 60.75 -> 60.77Improved
align both weak and strong views instead of one (ablation)CMPA · HAC, 5 labels per classtop-1 accuracy (%): 59.38 -> 60.77Improved
synthesize missing video via cross-modal translation instead of zero-filling (ablation)SSMDG framework at test time · HAC, 5% labels per classtop-1 accuracy (%): 28.27 -> 35.86Improved
synthesize missing audio via cross-modal translation instead of zero-filling (ablation)SSMDG framework at test time · HAC, 5% labels per classtop-1 accuracy (%): 52.45 -> 55.03Improved

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