AI Paper Atlas

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

Towards Unsupervised Multi-modal Semantic Segmentation

Haitian Zhang, Thai Nguyen, Xiangyuan Wang, Mohan Liu, Addison Wang

ECCV 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
naively fuse depth with RGBSTEGO · NYU-Depth-v2 (ViT-S/16)mIoU: 28.8 -> 25.3Hurt
naively fuse depth with RGBEAGLE · NYU-Depth-v2 (ViT-S/16)mIoU: 27.4 -> 20.1Hurt
replace STEGO RGB-only with UniM2 depth fusionSTEGO · NYU-Depth-v2 (ViT-B/16)mIoU: 31.7 -> 38.1Improved
replace STEGO RGB-only with UniM2 thermal fusionSTEGO · MFNet (ViT-B/16)mIoU: 35.9 -> 45.7Improved
add CMCS and MSN to baseline (ablation)UniM2 baseline · NYU-Depth-v2 (ViT-S/16)mIoU: 25.0 -> 31.3Improved
add CMH (Cross-modal Harmonizer) (ablation)UniM2 (CMCS + MSN) · NYU-Depth-v2 (ViT-S/16)mIoU: 31.3 -> 36.9Improved
add MSN feature refinement before fusion (ablation)UniM2 (CMCS + CMH) · NYU-Depth-v2 (ViT-S/16)mIoU: 34.2 -> 36.9Improved
anchor on RGB only instead of no anchors (ablation)UniM2 · NYU-Depth-v2 (ViT-S/16)mIoU: 19.8 -> 36.9Improved
anchor on RGB only instead of Depth only (ablation)UniM2 · NYU-Depth-v2 (ViT-S/16)mIoU: 27.6 -> 36.9Improved
use Conv fusion instead of Sum fusion (ablation)UniM2 · NYU-Depth-v2 (ViT-S/16)mIoU: 33.0 -> 36.9Improved
use Conv fusion instead of Max fusion (ablation)UniM2 · NYU-Depth-v2 (ViT-S/16)mIoU: 30.5 -> 36.9Improved
use UniM2 instead of STEGO with four modalitiesSTEGO · MCubeS (ViT-S/16, INAD)mIoU: 18.3 -> 20.7Improved

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