AI Paper Atlas

Research map / Label-efficient and robust learning / Self-supervised and contrastive

Unleashing the Power of Image-Tabular Self-Supervised Learning via Breaking Cross-Tabular Barriers

Yibing Fu, Yunpeng Zhao, Zhitao Zeng, Cheng Chen, Yueming Jin

AAAI 2026 · Label-efficient and robust learning › Self-supervised and contrastive · approach: Data-efficient and robust self-supervision · 4 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
remove column-header semantic embedding (ablation)CITab · ADNIaccuracy: 0.654 -> 0.846Improved
remove column-header semantic embedding (ablation)CITab · AIBL / NACCaccuracy: 0.752 -> 0.817 (AIBL); 0.690 -> 0.728 (NACC)Improved
add image-tabular contrastive loss in pretraining (ablation)CITab · ADNIaccuracy: 0.735 -> 0.846Improved
add image-tabular matching loss (ablation)CITab · ADNIaccuracy: 0.799 -> 0.846Improved
add multi-modal SSL pretraining across cohorts (ablation)CITab · AIBLaccuracy: 0.756 -> 0.817Improved
add P-MoLin module (ablation)CITab · NACCaccuracy: 0.733 -> 0.728Hurt
add P-MoLin module (ablation)CITab · ADNIaccuracy: 0.823 -> 0.846Improved
use unified self-attention rather than cross-attention fusion (ablation)CITab · AIBLaccuracy: 0.744 -> 0.817Improved
use general BERT rather than BioBERT for headers (ablation)CITab · AIBLaccuracy: 0.736 -> 0.817Improved
increase P-MoLin experts from 5 to 6 (ablation)CITab · 3-cohort averageaccuracy: 0.797 -> 0.787Hurt

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