Research map / Detection and segmentation / Weakly supervised detection and segmentation
Boundary-Enhanced Co-Training 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 co-training between two networks for uncertain pixels (ablation) | WSSS segmentation with IRN pseudo-labels · PASCAL VOC 2012 val | mIoU: 66.2 -> 68.2 | Helped |
| add boundary construction and boundary-weighted loss (ablation) | COT with IRN pseudo-labels · PASCAL VOC 2012 val | mIoU: 68.2 -> 70.9 | Helped |
| add label refinement at inference (ablation) | BECO with IRN pseudo-labels · PASCAL VOC 2012 val | mIoU: 70.9 -> 72.1 | Helped |
| use BECO training instead of a baseline network | WSSS segmentation with ReCAM pseudo-labels · PASCAL VOC 2012 val | mIoU: 67.1 -> 71.9 | Helped |
| use BECO training instead of a baseline network | WSSS segmentation with AMN pseudo-labels · PASCAL VOC 2012 val | mIoU: 67.9 -> 73.0 | Helped |
| use co-training without boundary enhancement (ablation) | MiT-B2 segmentation model · PASCAL VOC 2012 val | mIoU: 69.0 -> 71.0 | Helped |
| add boundary enhancement to COT (ablation) | MiT-B2 segmentation model · PASCAL VOC 2012 val | mIoU: 71.0 -> 73.0 | Helped |
| add label refinement at inference (ablation) | BECO with MiT-B2 · PASCAL VOC 2012 val | mIoU: 73.0 -> 73.7 | Helped |
| apply BECO instead of training an independent single network (ablation) | WSSS segmentation with IRN pseudo-labels · PASCAL VOC 2012 val (single network) | mIoU: 65.1 -> 70.2 | Helped |
| use BECO rather than IRN pseudo-labels as training targets | WSSS segmentation · MS COCO 2014 val | mIoU: 43.8 -> 45.1 | Helped |
| use BECO rather than the strongest listed prior method | WSSS segmentation with ResNet101 · PASCAL VOC 2012 val | mIoU: 72.0 -> 72.1 | Helped |
Closest papers by meaning
- W2P: Switching from Weak Supervision to Partial Supervision for Semantic Segmentation (AAAI 2024 · similarity 0.93)
- Separate and Conquer: Decoupling Co-occurrence via Decomposition and Representation for Weakly Supervised Semantic Segmentation (CVPR 2024 · similarity 0.91)
- Progressive Feature Self-Reinforcement for Weakly Supervised Semantic Segmentation (AAAI 2024 · similarity 0.90)
- From SAM to CAMs: Exploring Segment Anything Model for Weakly Supervised Semantic Segmentation (CVPR 2024 · similarity 0.89)
- Weakly Supervised Semantic Segmentation via Progressive Confidence Region Expansion (CVPR 2025 · similarity 0.89)
- DuPL: Dual Student with Trustworthy Progressive Learning for Robust Weakly Supervised Semantic Segmentation (CVPR 2024 · 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.