AI Paper Atlas

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

Reducing Unimodal Bias in Multi-Modal Semantic Segmentation with Multi-Scale Functional Entropy Regularization

Xu Zheng, Yuanhuiyi Lyu, Lutao Jiang, Danda Pani Paudel, Luc Van Gool, Xuming Hu

ICCV 2025 · Vision-language and multimodal › Cross-modal learning · approach: Multimodal fusion with missing modalities · 9 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 prediction-level functional-entropy regularization R_p to supervised loss (ablation)Ours (multi-modal segmentation) · MUSESmean mIoU: 42.60 -> 50.02Improved
add prediction-level regularization R_p (ablation)Ours (multi-modal segmentation) · MUSES (event only)mIoU: 6.48 -> 29.44Improved
add prediction-level regularization R_p (ablation)Ours (multi-modal segmentation) · MUSES (frame only)mIoU: 60.63 -> 59.63Hurt
add multi-scale feature-level regularization R_f on top of R_p (ablation)Ours (multi-modal segmentation) · MUSESmean mIoU: 50.02 -> 50.44Improved
add both regularizers (R_p and R_f) (ablation)Ours (multi-modal segmentation) · MUSESmean accuracy: 52.53 -> 61.48Improved
vary lambda_p from 0.0 to 0.3 (ablation)Ours (R_p weight) · MUSESmean mIoU: 48.48 -> 49.89Improved
increase lambda_p from 0.3 to 0.7 (ablation)Ours (R_p weight) · MUSESmean mIoU: 49.89 -> 48.55Hurt
add feature regularization weight lambda_f = 0.02 (ablation)Ours (R_f weight) · MUSESmean mIoU: 49.89 -> 50.44Improved
increase lambda_f from 0.02 to 0.06 (ablation)Ours (R_f weight) · MUSESmean mIoU: 50.44 -> 50.03Hurt
use the original VQA functional-entropy regularization directly instead of the multi-scale one (ablation)Ours (regularization design) · MUSESmIoU: 50.44 -> 42.89Hurt
add regularization terms (training cost) (ablation)Ours · Training on 8 H100 GPUstraining time (hours): 2.462 -> 2.476No clear effect
replace MAGIC with the proposed regularized modelMAGIC · DELIVER (four modalities)mean mIoU: 40.49 -> 48.05Improved

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