AI Paper Atlas

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

AMDANet: Attention-Driven Multi-Perspective Discrepancy Alignment for RGB-Infrared Image Fusion and Segmentation

Haifeng Zhong, Fan Tang, Zhuo Chen, Hyung Jin Chang, Yixing Gao

ICCV 2025 · Vision-language and multimodal › Cross-modal learning · approach: Multi-modality image fusion · 12 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 Feature Discrepancy Alignment Module (FDAM) (ablation)AMDANet · MFNetmIoU: 58.6 -> 62.1Improved
add Semantic Consistency Inference (SCI) (ablation)AMDANet · MFNetmIoU: 58.1 -> 62.1Improved
add Mutual Feature Mask Learning (MFML) (ablation)AMDANet · MFNetmIoU: 59.7 -> 62.1Improved
add all three modules vs none (ablation)AMDANet · MFNetmIoU: 53.1 -> 62.1Improved
add consistency regularization loss Lcr (ablation)AMDANet · FMBmIoU: 61.6 -> 64.8Improved
add salient information loss Lsi (ablation)AMDANet · FMBmIoU: 60.5 -> 64.8Improved
add consistency color loss Lco (ablation)AMDANet · FMBmIoU: 62.3 -> 64.8Improved
AMDANet vs lightweight SeAFusion in costAMDANet · FMB complexityFLOPs (G): 13.06 -> 119.02Hurt
AMDANet vs MRFS on PST900 (poor image quality)AMDANet · PST900mIoU: 86.9 -> 88.5Improved

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