AI Paper Atlas

Research map / Vision-language and multimodal / Cross-modal learning

FAMDR: Feature-Aligned Multimodal Denoising for Reliable Diagnostic Reconciliation in Medical Imaging

Xun Liang, Zhiying Li, Hongxun Jiang

AAAI 2026 · Vision-language and multimodal › Cross-modal learning · approach: Medical multimodal fusion · 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 CAMAL discrepancy-aware alignment (ablation)FAMDR · Extended MIMIC-CXRF1: 0.73 -> 0.83 (-12% without)Improved
add CAMAL discrepancy-aware alignment (ablation)FAMDR · Extended MIMIC-CXRIoU: 0.45 -> 0.59 (-24% without)Improved
add CAMAL discrepancy-aware alignment (ablation)FAMDR · Extended MIMIC-CXRECE: 0.11 -> 0.08 (+38% without)Improved
add X-MRA retrieval augmentation (ablation)FAMDR · Extended MIMIC-CXRF1: 0.78 -> 0.83 (-6% without)Improved
add X-MRA retrieval augmentation (ablation)FAMDR · Extended MIMIC-CXRECE: 0.10 -> 0.08 (+25% without)Improved
add MCUQ uncertainty quantification (ablation)FAMDR · Extended MIMIC-CXRECE: 0.12 -> 0.08 (+50% without)Improved
add MCUQ uncertainty quantification (ablation)FAMDR · Extended MIMIC-CXRF1: 0.80 -> 0.83 (-4% without)Improved
use G-CLAM adaptive residual learning instead of cosine similarity (ablation)FAMDR · Extended MIMIC-CXRIoU: 0.49 -> 0.59 (-17% with cosine)Improved
use G-CLAM adaptive residual learning instead of cosine similarity (ablation)FAMDR · Extended MIMIC-CXRF1: 0.75 -> 0.83 (-10% with cosine)Improved
set alignment loss weight lambda to 0.5 rather than 0.1 (ablation)FAMDR · Extended MIMIC-CXRF1: 0.76 -> 0.83Improved
raise alignment loss weight lambda from 0.5 to 1.0 (ablation)FAMDR · Extended MIMIC-CXRF1: 0.83 -> 0.73Hurt
raise retrieval weight beta from 1.0 to 2.0 (ablation)FAMDR · Extended MIMIC-CXRF1: 0.83 -> 0.77Hurt

Earlier methods this paper compares with

Named baselines from earlier accepted papers in this paper's results tables: better than 2 of 2 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