Research map / Label-efficient and robust learning / Semi-supervised learning
A Pseudo-Label Optimization Method Based on Polar Coordinate Modeling and Prior Constraints
Yudi Wang, Hailan Shen, Yixiao Fu, Yuqi Li, Zeshi Lu, Zailiang Chen
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 KCP polar prior constraint module (ablation) | baseline (BSF-Net pretrained U-Net) · PROMISE12 20% labeled | Dice: 81.11 -> 85.13 | Improved |
| add KCP polar prior constraint module (ablation) | baseline · PROMISE12 20% labeled | 95HD: 5.47 -> 3.52 | Improved |
| add Shape-aware Weighting (SaW) (ablation) | baseline + KCP · PROMISE12 20% labeled | Dice: 85.13 -> 85.80 | Improved |
| add Shape-aware Weighting (SaW) (ablation) | baseline + KCP · PROMISE12 20% labeled | 95HD: 3.52 -> 3.23 | Improved |
| add Shape-aware Weighting (SaW) (ablation) | baseline + KCP · PROMISE12 20% labeled | ASD: 0.67 -> 0.68 | No clear effect |
| use APS pole instead of image center (ablation) | PMPC · PROMISE12 10% labeled | Dice: 77.29 -> 83.17 | Improved |
| use APS pole instead of foreground geometric center (ablation) | PMPC · PROMISE12 10% labeled | Dice: 78.85 -> 83.17 | Improved |
| use APS pole instead of foreground geometric center (ablation) | PMPC · PROMISE12 10% labeled | 95HD: 5.33 -> 3.52 | Improved |
| increase angular sampling density n from 12 to 36 (ablation) | PMPC · Female Pelvic 10% labeled | Dice: 81.86 -> 83.11 | Improved |
| increase angular sampling density n from 36 to 108 (ablation) | PMPC · Female Pelvic 10% labeled | Dice: 83.11 -> 83.13 | No clear effect |
| use PMPC instead of ABD | ABD · PROMISE12 20% labeled | Dice: 82.06 -> 85.80 | Improved |
| use PMPC instead of DCNet | DCNet · ACDC 10% labeled | 95HD: 1.28 -> 1.49 | Hurt |
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.
- UniMatch — UniMatch: Universal Matching from Atom to Task for Few-Shot Drug Discovery (ICLR 2025) · better on 2 of 2 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
- Enhancing Pseudo Label Quality for Semi-supervised Domain-Generalized Medical Image Segmentation (AAAI 2022 · similarity 0.84)
- MAPSeg: Unified Unsupervised Domain Adaptation for Heterogeneous Medical Image Segmentation Based on 3D Masked Autoencoding and Pseudo-Labeling (CVPR 2024 · similarity 0.82)
- Fully Data-Driven Pseudo Label Estimation for Pointly-Supervised Panoptic Segmentation (AAAI 2024 · similarity 0.82)
- Minding Fuzzy Regions: A Data-driven Alternating Learning Paradigm for Stable Lesion Segmentation (CVPR 2025 · similarity 0.81)
- Constructing and Exploring Intermediate Domains in Mixed Domain Semi-supervised Medical Image Segmentation (CVPR 2024 · similarity 0.81)
- Steady Progress Beats Stagnation: Mutual Aid of Foundation and Conventional Models in Mixed Domain Semi-Supervised Medical Image Segmentation (CVPR 2025 · similarity 0.81)
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.
