Research map / Detection and segmentation / CNN features
A Coarse-Fine Network for Keypoint Localization
Shaoli Huang, Mingming Gong, Dacheng Tao
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 |
|---|---|---|---|
| add multi-level supervision instead of strict supervision only (ablation) | CFN unified detection · CUB200-2011 (alpha=0.1) | PCK (%): 83.7 -> 88.0 | Improved |
| add multi-level supervision instead of strict supervision only (ablation) | CFN unified detection · CUB200-2011 (alpha=0.05) | PCK (%): 69.3 -> 71.0 | Improved |
| add multi-level supervision instead of strict supervision only (ablation) | CFN unified detection · CUB200-2011 (alpha=0.02) | PCK (%): 27.3 -> 27.3 | No clear effect |
| add multi-level supervision instead of strict supervision only (ablation) | coarse detector 4a · CUB200-2011 (alpha=0.1) | PCK (%): 66.1 -> 79.2 | Improved |
| add multi-level supervision instead of strict supervision only (ablation) | coarse detector 4b · CUB200-2011 (alpha=0.1) | PCK (%): 59.6 -> 84.9 | Improved |
| add multi-level supervision instead of strict supervision only (ablation) | coarse detector 4c · CUB200-2011 (alpha=0.1) | PCK (%): 79.9 -> 82.0 | Improved |
| add multi-level supervision instead of strict supervision only (ablation) | coarse detector 4c · CUB200-2011 (alpha=0.05) | PCK (%): 66.6 -> 52.4 | Hurt |
| add multi-level supervision instead of strict supervision only (ablation) | fine detector · CUB200-2011 (alpha=0.1) | PCK (%): 80.8 -> 80.8 | No clear effect |
| add deep multi-scale CFN instead of prior best method | CFN · CUB200-2011 | total PCP (%): 69.1 -> 72.1 | Improved |
| use CFN instead of second best method under strict PCK | CFN · CUB200-2011 (alpha=0.05) | mean PCK (%): 52.4 -> 70.9 | Improved |
| use CFN instead of Yu et al. without extra MPII data | CFN · LSP (PCK@0.2) | PCK (%): 84.3 -> 84.5 | No clear effect |
| use CFN instead of G-RMI (COCO-int) | CFN · COCO keypoints test-dev | AP: 68.5 -> 72.6 | Improved |
Closest papers by meaning
- Few-Shot Geometry-Aware Keypoint Localization (CVPR 2023 · similarity 0.88)
- Deep Corner (IJCV 2023 · similarity 0.87)
- From Coarse to Fine: Robust Hierarchical Localization at Large Scale (CVPR 2019 · similarity 0.87)
- EdgePoint2: Compact Descriptors for Superior Efficiency and Accuracy (IJCV 2026 · similarity 0.86)
- Occlusion-Net: 2D/3D Occluded Keypoint Localization Using Graph Networks (CVPR 2019 · similarity 0.86)
- Neural Outlier Rejection for Self-Supervised Keypoint Learning (ICLR 2020 · similarity 0.86)
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.
