AI Paper Atlas

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

Towards a Universal 3D Medical Multi-modality Generalization via Learning Personalized Invariant Representation

Zhaorui Tan, Xi Yang, Tan Pan, Tianyi Liu, Chen Jiang, Xin Guo, Qiufeng Wang, Anh Nguyen, Yuan Qi, Kaizhu Huang, Yuan Cheng

ICCV 2025 · Vision-language and multimodal › Cross-modal learning · approach: Medical multimodal fusion · 4 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 the learnable prior O to equivariance + invariance constraints (ablation)PUIR · AutoPET-II segmentationDice: 42.42 -> 48.20Improved
Add prior O to contrastive + decomposition + equivariance (ablation)PUIR · AutoPET-II segmentationDice: 40.85 -> 46.31Improved
Add prior O to contrastive + decomposition + invariance (ablation)PUIR · AutoPET-II segmentationDice: 44.34 -> 44.42No clear effect
Add invariance to equivariance without prior O (ablation)PUIR · AutoPET-II segmentationDice: 44.34 -> 42.42Hurt
Add invariance after O to equivariance + O (ablation)PUIR · AutoPET-II segmentationDice: 46.31 -> 48.20Improved
Use PUIR pre-training in SwinUNETR instead of prior SSL pre-trainingSwinUNETR · AutoPET-II segmentationDice: 44.06 -> 48.20Improved
Use PUIR pre-training instead of training from scratchSwinUNETR · AutoPET-II segmentationDice: 43.45 -> 48.20Improved
Use PUIR instead of MS-SPADE for one-to-all modality transferMS-SPADE · BRATS23PSNR: 26.4225 -> 35.4378Improved
Use 96^3 instead of 192^3 volumes (ablation)PUIR · BRATS23PSNR: 35.4378 -> 33.7418No clear effect
Use PUIR pre-training instead of SwinUNETR pre-training for 3 missing modalitiesSwinUNETR pre-training · BRATS18 enhancing tumorDice: 55.79 -> 60.19Improved
Use PUIR instead of mmFormer on full modality enhancing tumormmFormer · BRATS18 enhancing tumorDice: 79.91 -> 70.64Hurt
Use PUIR instead of SwinUNETR for NAC-PET to CT translationSwinUNETR · HNSCCSSIM: 0.5853 -> 0.6939Improved

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