Research map / Label-efficient and robust learning / Semi-supervised learning
Conflict-Based Cross-View Consistency for Semi-Supervised Semantic Segmentation
Zicheng Wang, Zhen Zhao, Xiaoxia Xing, Dong Xu, Xiangyu Kong, Luping Zhou
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 |
|---|---|---|---|
| Use CCVC instead of the strongest listed baseline | ResNet-101 segmentation model · PASCAL VOC 2012 original, 1/16 (92) | mIoU: 68.0 -> 70.2 | Improved |
| Use CCVC instead of the strongest listed baseline | ResNet-101 segmentation model · PASCAL VOC 2012 original, 1/8 (183) | mIoU: 72.0 -> 74.4 | Improved |
| Use CCVC instead of the strongest listed baseline | ResNet-101 segmentation model · PASCAL VOC 2012 original, 1/4 (366) | mIoU: 76.6 -> 77.4 | Improved |
| Use CCVC instead of the strongest listed baseline | ResNet-101 segmentation model · PASCAL VOC 2012 original, 1/2 (732) | mIoU: 78.4 -> 79.1 | Improved |
| Use CCVC instead of the strongest listed baseline | ResNet-101 segmentation model · PASCAL VOC 2012 original, Full (1464) | mIoU: 80.0 -> 80.5 | Improved |
| Use CCVC instead of the strongest listed baseline | ResNet-50 segmentation model · PASCAL VOC 2012 blended, 1/16 (662) | mIoU: 72.8 -> 74.5 | Improved |
| Use CCVC instead of the strongest listed baseline | ResNet-50 segmentation model · PASCAL VOC 2012 blended, 1/8 (1323) | mIoU: 75.7 -> 76.1 | Improved |
| Use CCVC instead of the strongest listed baseline | ResNet-50 segmentation model · PASCAL VOC 2012 blended, 1/4 (2646) | mIoU: 76.4 -> 76.4 | No clear effect |
| Use CCVC instead of the strongest listed baseline | ResNet-101 segmentation model · PASCAL VOC 2012 blended, 1/16 (662) | mIoU: 75.5 -> 77.2 | Improved |
| Use CCVC instead of the strongest listed baseline | ResNet-101 segmentation model · PASCAL VOC 2012 blended, 1/8 (1323) | mIoU: 78.2 -> 78.4 | Improved |
| Use CCVC instead of the strongest listed baseline | ResNet-101 segmentation model · PASCAL VOC 2012 blended, 1/4 (2646) | mIoU: 78.7 -> 79.0 | Improved |
| Use CCVC instead of the strongest listed baseline | ResNet-50 segmentation model · Cityscapes, 1/16 (186) | mIoU: 71.2 -> 74.9 | 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.
- ReCo — ReCo: Retrieve and Co-segment for Zero-shot Transfer (NeurIPS 2022) · better on 1 of 1 shared result
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
- Semi-Supervised Semantic Segmentation With Cross-Consistency Training (CVPR 2020 · similarity 0.93)
- Semi-Supervised Semantic Segmentation With Cross Pseudo Supervision (CVPR 2021 · similarity 0.91)
- CFCG: Semi-Supervised Semantic Segmentation via Cross-Fusion and Contour Guidance Supervision (ICCV 2023 · similarity 0.90)
- ScaleMatch: Multi-scale Consistency Enhancement for Semi-supervised Semantic Segmentation (AAAI 2025 · similarity 0.90)
- Relaxed Class-consensus Consistency for Semi-supervised Semantic Segmentation (AAAI 2025 · similarity 0.89)
- Improving Semi-Supervised Semantic Segmentation with Sliced-Wasserstein Feature Alignment and Uniformity (CVPR 2025 · similarity 0.89)
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.
