Research map / Detection and segmentation / CNN features
Harmonious Semantic Line Detection via Maximal Weight Clique Selection
Dongkwon Jin, Wonhui Park, Seong-Gyun Jeong, Chang-Su Kim
Check 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 the proposed method instead of DRM | Semantic line detection · SEL | AUC_F: 86.29 -> 86.83 | Improved |
| Use the proposed method instead of DRM | Semantic line detection · SEL | HIoU: 80.23 -> 81.03 | Improved |
| Use the proposed method instead of DRM | Semantic line detection · SEL_Hard | AUC_F: 82.17 -> 79.38 | Hurt |
| Use the proposed method instead of DRM | Semantic line detection · SEL_Hard | HIoU: 68.83 -> 65.99 | Hurt |
| Use the proposed method instead of Zhao et al. | Semantic line detection · SL5K | F-measure: 72.3 -> 80.3; 8.0 | Improved |
| Use the proposed method instead of SAD | Road lane detection · CULane no lane | AUC_F: 88.67 -> 92.04 | Improved |
| Use the proposed method instead of SAD | Road lane detection · CULane no lane | HIoU: 74.77 -> 76.46 | Improved |
| Add H-Net harmony scoring and MWCS to S-Net (ablation) | Semantic line detection · SEL | AUC_F: 77.75 -> 86.83 | Improved |
| Add H-Net harmony scoring and MWCS to S-Net (ablation) | Semantic line detection · SEL | HIoU: 69.03 -> 81.03 | Improved |
| Add the IRC module to H-Net (ablation) | S-Net+H-Net+MWCS · SEL | AUC_F: 84.66 -> 86.83 | Improved |
| Add the IRC module to H-Net (ablation) | S-Net+H-Net+MWCS · SEL | HIoU: 79.14 -> 81.03 | Improved |
| Use regression offsets to refine detected lines (ablation) | S-Net+H-Net+MWCS · SEL | AUC_F: 86.60 -> 86.83 | Improved |
Closest papers by meaning
- Semantic Line Detection Using Mirror Attention and Comparative Ranking and Matching (ECCV 2020 · similarity 0.91)
- Semantic Line Combination Detector (CVPR 2024 · similarity 0.86)
- Semantic Line Detection and Its Applications (ICCV 2017 · similarity 0.85)
- Deep Hough Transform for Semantic Line Detection (ECCV 2020 · similarity 0.82)
- CPN: Complementary Proposal Network for Unconstrained Text Detection (AAAI 2024 · similarity 0.82)
- Semantic Consistency Networks for 3D Object Detection (AAAI 2021 · similarity 0.82)
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.
