AI Paper Atlas

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

CHARM: Collaborative Harmonization Across Arbitrary Modalities for Modality-Agnostic Semantic Segmentation

Lekang Wen, Jing Xiao, Liang Liao, Jiajun Chen, Mi Wang

AAAI 2026 · Vision-language and multimodal › Cross-modal learning · approach: Multi-modality image fusion · 2 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 CoL (fusion via MPU-less collaborative learning) to addition fusion (ablation)CHARM (MiT-B0) · DELIVER ablationAverage mIoU: 33.95 -> 41.53Improved
add MPU to CoL (ablation)CHARM (MiT-B0) · DELIVER ablationLast-1 mIoU: 3.28 -> 15.89Improved
add InE (with MPU removed variant d vs b) on top of CoL (ablation)CHARM (MiT-B0) · DELIVER ablationLast-1 mIoU: 3.28 -> 24.40Improved
add MPU to CoL+InE (ablation)CHARM (MiT-B0) · DELIVER ablationAverage mIoU: 48.76 -> 50.97Improved
add MPU and CoL, Top-1 mIoU (ablation)CHARM (MiT-B0) · DELIVER ablationTop-1 mIoU: 63.17 -> 64.03No clear effect
add CoL without MPU to addition fusion (ablation)CHARM (MiT-B0) · MUSES ablationLast-1 mIoU: 2.26 -> 0.81Hurt
use softmin instead of softmax sampling in InE (ablation)CHARM (MiT-B0) · DELIVER sampling ablationAverage mIoU: 46.80 -> 50.97Improved
use softmin instead of uniform sampling in InE (ablation)CHARM (MiT-B0) · DELIVER sampling ablationLast-1 mIoU: 23.36 -> 26.47Improved
use softmin instead of softmax sampling in InE (ablation)CHARM (MiT-B0) · DELIVER sampling ablationTop-1 mIoU: 64.03 -> 64.04No clear effect
replace MPU with explicit KL alignment (ablation)CHARM · feature visualizationfeature activationsHurt
CHARM vs MAGIC on fragile-modal worst combinationCHARM (MiT-B2) · DELIVERLast-1 mIoU: 0.27 -> 28.76Improved
CHARM vs MAGIC on MCubeS average (MiT-B0)CHARM (MiT-B0) · MCubeSTop-1 mIoU: 47.85 -> 48.24No clear effect

Later papers that compared with this method

2 later accepted papers report Charm as a baseline in their results tables; 1 of them report a better number on most of the results they share with it.

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