AI Paper Atlas

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

Difference-Aware Decision Learning for Multimodal Image Fusion

Hao Pan, Jian Dai, Yuan Sun, Zhenwen Ren, Xingfeng Li

ICML 2026 · Vision-language and multimodal › Cross-modal learning · approach: Multimodal fusion with missing modalities

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 MDA and CDG decision modules (ablation)IDEAL · MSRSSD: 46.00 -> 50.93Improved
add MDA and CDG decision modules (ablation)IDEAL · M3FDSD: 30.98 -> 40.31Improved
add Modal Difference Attention (MDA) module (ablation)IDEAL · M3FDSD: 34.56 -> 40.31Improved
add gradient fidelity risk (ablation)IDEAL · M3FDSCD: 1.05 -> 1.52Improved
add gradient fidelity risk (ablation)IDEAL · MSRSSF: 10.81 -> 12.62Improved
add pixel intensity risk (ablation)IDEAL · M3FDSD: 35.93 -> 40.31Improved
add pixel intensity risk (ablation)IDEAL · FMBSCD: 1.62 -> 1.63No clear effect
use observation-conditioned decisions vs strongest SCD baselineIDEAL · M3FDSCD: 1.7170 -> 1.5238Hurt
use IDEAL fusion as input to detectorIDEAL · MSRS detectionmAP@[0.5:0.95]: 66.9 -> 67.5Improved
use IDEAL fusion for detection mAP@0.5IDEAL · MSRS detectionmAP@0.5: 93.3 -> 93.0No clear effect
compare IDEAL vs CDDFuse efficiencyIDEAL · MSRSGFLOPs: 220.92 -> 1.00Improved
compare IDEAL vs GIFNet on FMB average gradientIDEAL · FMBAG: 4.9269 -> 4.7895Hurt

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