Research map / Detection and segmentation / CNN features
Joint Semantic Segmentation and Boundary Detection Using Iterative Pyramid Contexts
Check 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 |
|---|---|---|---|
| Use RPCNet instead of DANet | ResNet101 semantic segmentation · Cityscapes test | mIoU: 81.5 -> 81.8 | Helped |
| Use RPCNet instead of STEAL with Test NMS | semantic boundary detection · Cityscapes val | MF (ODS): 71.42 -> 78.22 | Helped |
| Use RPCNet instead of CASENet* with Test NMS | semantic boundary detection · Cityscapes val | AP: 68.13 -> 78.79 | Helped |
| Add duality loss (ablation) | semantic segmentation and boundary detection · Cityscapes ablation | mIoU: 78.14 -> 79.58 | Helped |
| Add duality loss (ablation) | semantic boundary detection · Cityscapes ablation | MF (ODS): 73.61 -> 74.24 | Helped |
| Add spatial gradient fusion (ablation) | RPCNet semantic segmentation · Cityscapes ablation | mIoU: 79.58 -> 79.81 | Helped |
| Add spatial gradient fusion (ablation) | RPCNet semantic boundary detection · Cityscapes ablation | AP: 73.57 -> 74.20 | Helped |
| Add PCM with patch setup {1, 3, 5, 7} (ablation) | RPCNet semantic segmentation · Cityscapes ablation | mIoU: 79.81 -> 80.43 | Helped |
| Add PCM with patch setup {1, 3, 5, 7} (ablation) | RPCNet semantic boundary detection · Cityscapes ablation | MF (ODS): 74.45 -> 75.54 | Helped |
| Increase PCM steps from S=1 to S=2 and train both tasks (ablation) | RPCNet · Cityscapes ablation | mIoU: 77.65 -> 78.77 | Helped |
| Increase PCM steps from S=2 to S=8 (ablation) | RPCNet · Cityscapes ablation | mIoU: 78.77 -> 80.43 | Helped |
| Increase PCM steps from S=2 to S=8 (ablation) | RPCNet boundary detection · Cityscapes ablation | MF (ODS): 73.44 -> 75.54 | Helped |
Closest papers by meaning
- Efficient Piecewise Training of Deep Structured Models for Semantic Segmentation (CVPR 2016 · similarity 0.89)
- Beyond Pixel-wise Supervision: Local Structure Regularization for Semantic Segmentation (NeurIPS 2026 · similarity 0.89)
- Semantic Segmentation via Structured Patch Prediction, Context CRF and Guidance CRF (CVPR 2017 · similarity 0.88)
- BFANet: Revisiting 3D Semantic Segmentation with Boundary Feature Analysis (CVPR 2025 · similarity 0.86)
- W2P: Switching from Weak Supervision to Partial Supervision for Semantic Segmentation (AAAI 2024 · similarity 0.86)
- Contextrast: Contextual Contrastive Learning for Semantic Segmentation (CVPR 2024 · similarity 0.85)
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.