AI Paper Atlas

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

MM-OVSeg: Multimodal Optical-SAR Fusion for Open-Vocabulary Segmentation in Remote Sensing

Yimin Wei, Aoran Xiao, Hongruixuan Chen, Junshi Xia, Naoto Yokoya

CVPR 2026 · Vision-language and multimodal › Cross-modal learning · approach: Multi-modality image fusion

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 Cross-Modal Unification (SAR-RGB DINO alignment) to the full model (ablation)MM-OVSeg · DDHR-SK (cloudy)mIoU: 64.1 -> 73.1Improved
add Dual-Encoder Fusion on top of the optical-only baseline (ablation)MM-OVSeg · DDHR-SK (cloudy)mIoU: 55.0 -> 64.1Improved
use InfoNCE rather than MSE for the CMU alignment loss (ablation)MM-OVSeg CMU · DDHR-SK (cloudy)mIoU: 67.7 -> 73.1Improved
use InfoNCE rather than L1 for the CMU alignment loss (ablation)MM-OVSeg CMU · DDHR-SK (cloudy)mIoU: 69.0 -> 73.1Improved
any CMU alignment loss (MSE, L1) versus no CMU (ablation)MM-OVSeg · DDHR-SK (cloudy)mIoU: 64.1 -> 67.7 (MSE)Improved
add SAR input via multimodal fusion to an optical-only open-vocabulary modelMM-OVSeg vs GSNet · PIE-clean (clear sky)mIoU: 57.2 -> 59.7Improved
multimodal Optical-SAR fusion versus best unimodal methodMM-OVSeg vs GSNet · Six benchmarks (mean)mIoU: 45.6 -> 51.7Improved
multimodal fusion for cross-domain transferMM-OVSeg vs CAT-Seg · DDHR-SK to DDHR-CHmIoU: 27.8 -> 42.6Improved
fuse SAR for the unseen water class (ablation)MM-OVSeg · DDHR-SK (cloudy)IoU (Water): 19.1 -> 84.8Improved
add CMU alone without DEF effect on Forest class (removing CMU) (ablation)MM-OVSeg · DDHR-SK (cloudy)IoU (Forest): 57.2 -> 87.3Improved

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