Research map / Label-efficient and robust learning / Semi-supervised learning
SemiContour: A Semi-Supervised Learning Approach for Contour Detection
Zizhao Zhang, Fuyong Xing, Xiaoshuang Shi, Lin Yang
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 |
|---|---|---|---|
| Incorporate unlabeled image patches to guide structured-random-forest node splitting | SemiContour · BSDS500, 3 labeled images | AP: SemiContour AP .776; SE-Var with 3 labeled images AP .74 | Improved |
| Use 3 labeled images rather than 200 (ablation) | SemiContour · BSDS500 | ODS: .728 -> .736 | No clear effect |
| Use 10 labeled images rather than 3 (ablation) | SemiContour · BSDS500 | ODS: .728 -> .732 | Improved |
| Use 20 labeled images rather than 3 (ablation) | SemiContour · BSDS500 | ODS: .728 -> .734 | Improved |
| Use 50 labeled images rather than 3 (ablation) | SemiContour · BSDS500 | ODS: .728 -> .736 | Improved |
| Use target-domain unlabeled data in cross-dataset training | SemiContour · NYUD/BSDS cross-dataset | OIS: .74 -> .75 | Improved |
| Use target-domain unlabeled data in cross-dataset training | SemiContour · BSDS/NYUD cross-dataset | ODS: .64 -> .65 | Improved |
| Replace the original contour detector with SemiContour-Seg post-processing | SemiContour · BSDS500 | ODS: ODS .73 -> .74; OIS .75 -> .77; AP .78 -> .76 | Mixed |
| Use fast sparse coding instead of iterative sparse-coding algorithms | SemiContour · Contour detection experiments | contour detection accuracy | No clear effect |
Closest papers by meaning
- Contour Detection in Unstructured 3D Point Clouds (CVPR 2016 · similarity 0.85)
- CFCG: Semi-Supervised Semantic Segmentation via Cross-Fusion and Contour Guidance Supervision (ICCV 2023 · similarity 0.85)
- Semi-supervised 3D Object Detection with PatchTeacher and PillarMix (AAAI 2024 · similarity 0.85)
- Sparse Semi-DETR: Sparse Learnable Queries for Semi-Supervised Object Detection (CVPR 2024 · similarity 0.84)
- GraphCL: Graph-based Clustering for Semi-Supervised Medical Image Segmentation (ICML 2025 · similarity 0.83)
- RWMS: Reliable Weighted Multi-Phase for Semi-supervised Segmentation (AAAI 2024 · similarity 0.83)
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.
