Research map / Vision-language and multimodal / Cross-modal learning
Uni-Encoder Meets Multi-Encoders: Representation Before Fusion for Brain Tumor Segmentation with Missing Modalities
Peibo Song, Xiaotian Xue, Jinshuo Zhang, Zihao Wang, Jinhua Liu, Shujun Fu, Fangxun Bao, Si Yong Yeo
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 changed | Where | Measured | Effect |
|---|---|---|---|
| add masked self-supervised pretraining to the Uni-Encoder (with Multi-E) (ablation) | UniME · BraTS 2023 | mean DSC (%): 81.22 -> 83.49 | Improved |
| add Multi-Encoders to pretrained Uni-Encoder (ablation) | UniME · BraTS 2023 | mean DSC (%): 82.45 -> 83.49 | Improved |
| add pretrained Uni-Encoder to Multi-Encoders (ablation) | UniME · BraTS 2023 | mean DSC (%): 78.90 -> 83.49 | Improved |
| add Multi-Encoders to a scratch Uni-Encoder (ablation) | UniME · BraTS 2023 | mean DSC (%): 77.25 -> 81.22 | Improved |
| scale Uni-Encoder from small to base (ablation) | UniME · BraTS 2023 | mean DSC (%): 80.00 -> 83.49 | Improved |
| scale Uni-Encoder from base to large (ablation) | UniME · BraTS 2023 | mean DSC (%): 83.49 -> 83.22 | No clear effect |
| use patch masking ratio 75% instead of 25% (ablation) | UniME · BraTS 2023 | mean DSC (%): 82.82 -> 83.49 | Improved |
| use patch masking ratio 75% instead of 87.5% (ablation) | UniME · BraTS 2023 | mean DSC (%): 82.96 -> 83.49 | Improved |
| add 4 register tokens instead of none (ablation) | UniME · BraTS 2023 | mean DSC (%): 82.64 -> 83.49 | Improved |
| use 4 register tokens instead of 8 (ablation) | UniME · BraTS 2023 | mean DSC (%): 82.93 -> 83.49 | Improved |
| use LLRD with rate 0.75 instead of freezing Uni-Encoder (ablation) | UniME · BraTS 2023 | mean DSC (%): 82.20 -> 83.49 | Improved |
| use LLRD rate 0.75 instead of 1.00 (ablation) | UniME · BraTS 2023 | mean DSC (%): 82.94 -> 83.49 | Improved |
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.
- M3AE — M3AE: Multimodal Representation Learning for Brain Tumor Segmentation with Missing Modalities (AAAI 2023) · better on 6 of 6 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
- Semantic-guided Masked Mutual Learning for Multi-modal Brain Tumor Segmentation with Arbitrary Missing Modalities (AAAI 2025 · similarity 0.89)
- UniMRSeg: Unified Modality-Relax Segmentation via Hierarchical Self-Supervised Compensation (NeurIPS 2025 · similarity 0.89)
- TMFormer: Token Merging Transformer for Brain Tumor Segmentation with Missing Modalities (AAAI 2024 · similarity 0.88)
- Incomplete Multi-modal Brain Tumor Segmentation via Learnable Sorting State Space Model (CVPR 2025 · similarity 0.88)
- Federated Modality-Specific Encoders and Multimodal Anchors for Personalized Brain Tumor Segmentation (AAAI 2024 · similarity 0.87)
- KMD: Koopman Multi-modality Decomposition for Generalized Brain Tumor Segmentation under Incomplete Modalities (CVPR 2025 · similarity 0.87)
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.
