AI Paper Atlas

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

RL-U2Net: A Dual-Branch UNet with Reinforcement Learning-Assisted Multimodal Feature Fusion for Accurate 3D Whole-Heart Segmentation

Jierui Qu, Jianchun Zhao

AAAI 2026 · Vision-language and multimodal › Cross-modal learning · approach: Medical multimodal fusion · 1 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 cross-modal attention (CMA) to the dual-branch model (ablation)RL-U2Net · MM-WHS 2017 MRIDice: 0.612 -> 0.870Improved
add cross-modal attention (CMA) (ablation)RL-U2Net · MM-WHS 2017 CTDice: 0.884 -> 0.931Improved
add RL-XAlign module (ablation)RL-U2Net · MM-WHS 2017 CTDice: 0.909 -> 0.931Improved
add RL-XAlign module (ablation)RL-U2Net · MM-WHS 2017 MRIDice: 0.837 -> 0.870Improved
add auxiliary alignment loss (ablation)RL-U2Net · MM-WHS 2017 CTDice: 0.912 -> 0.931Improved
add auxiliary alignment loss (ablation)RL-U2Net · MM-WHS 2017 MRIDice: 0.834 -> 0.870Improved
add adaptive gradient weight distributor (AGWD) (ablation)RL-U2Net · MM-WHS 2017 CTDice: 0.885 -> 0.931Improved
add AGWD (ablation)RL-U2Net · MM-WHS 2017 MRIDice: 0.768 -> 0.870Improved
use RL-U2Net instead of HRMedSegMM-WHS 2017 CT · MM-WHS 2017 CTaverage Dice: 0.921 -> 0.931Improved
use RL-U2Net instead of nnformerMM-WHS 2017 CT · MM-WHS 2017 CTHD95 (mm): 12.174 -> 11.471Improved

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