Research map / Detection and segmentation / Weakly supervised detection and segmentation
Out-of-Candidate Rectification for Weakly Supervised Semantic Segmentation
Read the paperCheck your idea against 108,967 papers
AI-extracted summary. Written by AI from the paper's title only (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 OCR to AffinityNet | AffinityNet · PASCAL VOC 2012 val | mIoU: +3.2 | Helped |
| Add OCR to SEAM | SEAM · PASCAL VOC 2012 val | mIoU: +3.3 | Helped |
| Add OCR to MCTformer | MCTformer · PASCAL VOC 2012 val | mIoU: +0.8 | Helped |
| Add OCR to AffinityNet | AffinityNet · PASCAL VOC 2012 test | mIoU: +1.5 | Helped |
| Add OCR to SEAM | SEAM · PASCAL VOC 2012 test | mIoU: +2.7 | Helped |
| Add OCR to MCTformer | MCTformer · PASCAL VOC 2012 test | mIoU: +0.4 | Helped |
| Add OCR to AffinityNet | AffinityNet · MS COCO 2014 val | mIoU: +1.0 | Helped |
| Add OCR to SEAM | SEAM · MS COCO 2014 val | mIoU: +1.3 | Helped |
| Add OCR to MCTformer | MCTformer · MS COCO 2014 val | mIoU: +0.5 | Helped |
| Use all tag labels in the IC group rather than filtering useless candidate classes (ablation) | OCR+SEAM · PASCAL VOC 2012 val | mIoU: 64.5 -> 63.4 | Hurt |
| Use only the anchor class in the IC group (ablation) | OCR+SEAM · PASCAL VOC 2012 val | mIoU: 64.5 -> 67.2 | Helped |
| Adaptively select IC classes using prior and posterior correlation (ablation) | OCR+SEAM · PASCAL VOC 2012 val | mIoU: 64.5 -> 67.8 | Helped |
Closest papers by meaning
- Reliability Does Matter: An End-to-End Weakly Supervised Semantic Segmentation Approach (AAAI 2020 · similarity 0.90)
- Weakly Supervised Semantic Segmentation Using Out-of-Distribution Data (CVPR 2022 · similarity 0.90)
- Separate and Conquer: Decoupling Co-occurrence via Decomposition and Representation for Weakly Supervised Semantic Segmentation (CVPR 2024 · similarity 0.88)
- Progressive Feature Self-Reinforcement for Weakly Supervised Semantic Segmentation (AAAI 2024 · similarity 0.88)
- Weakly Supervised Semantic Segmentation via Progressive Confidence Region Expansion (CVPR 2025 · similarity 0.88)
- DuPL: Dual Student with Trustworthy Progressive Learning for Robust Weakly Supervised Semantic Segmentation (CVPR 2024 · 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.