Research map / Label-efficient and robust learning / Semi-supervised learning
Beyond Random Sampling: Distribution-Aware Alignment for Semi-Supervised Medical Image Segmentation
Weihao Yan, Yeqiang Qian, Yi Dong, Ming Yang
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 three-branch Copy-Paste (ablation) | UniV2 baseline · BUSI 1/16 | DSC: 74.62 -> 75.58 | Improved |
| add three-branch Copy-Paste (ablation) | UniV2 baseline · BUSI 1/8 | DSC: 77.45 -> 77.35 | No clear effect |
| add Semantic Memory Bank (ablation) | Copy-Paste baseline · BUSI 1/16 | DSC: 75.58 -> 77.35 | Improved |
| add progressive activation schedule (ablation) | CP + MB · BUSI 1/16 | DSC: 77.35 -> 78.06 | Improved |
| add Distribution-Aware Sample Selection (ablation) | MCP · BUSI 1/16 | DSC: 78.06 -> 79.80 | Improved |
| add Sample Selection alone (no MCP) (ablation) | UniV2 baseline · BUSI 1/16 | DSC: 74.62 -> 78.06 | Improved |
| replace random sampling with our SS | AdaMix · BUSI 1/16 | DSC: 58.6 -> 65.1 | Improved |
| replace random sampling with our SS | SynFoc · BUSI 1/16 | DSC: 71.3 -> 76.8 | Improved |
| replace random sampling with our SS | ABD · BUSI 1/16 | DSC: 71.0 -> 73.3 | Improved |
| replace random sampling with our SS | RCP · BUSI 1/4 | ASD: 38.6 -> 41.0 | Hurt |
| use Density-K-Center instead of K-Means (ablation) | Patch-Four selection · BUSI 1/16 | DSC: 75.8 -> 78.1 | Improved |
| use four intermediate layers instead of last layer (ablation) | Patch K-Center selection · BUSI 1/16 | DSC: 78.1 -> 78.7 | Improved |
Closest papers by meaning
- DyCON: Dynamic Uncertainty-aware Consistency and Contrastive Learning for Semi-supervised Medical Image Segmentation (CVPR 2025 · similarity 0.89)
- Semi-supervised TEE Segmentation via Interacting with SAM Equipped with Noise-Resilient Prompting (AAAI 2024 · similarity 0.88)
- GapMatch: Bridging Instance and Model Perturbations for Enhanced Semi-Supervised Medical Image Segmentation (AAAI 2025 · similarity 0.88)
- SGTC: Semantic-Guided Triplet Co-training for Sparsely Annotated Semi-Supervised Medical Image Segmentation (AAAI 2025 · similarity 0.88)
- Annotation Ambiguity Aware Semi-Supervised Medical Image Segmentation (CVPR 2025 · similarity 0.88)
- Steady Progress Beats Stagnation: Mutual Aid of Foundation and Conventional Models in Mixed Domain Semi-Supervised Medical Image Segmentation (CVPR 2025 · similarity 0.88)
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.
