Research map / Detection and segmentation / CNN features
Gliding Vertex on the Horizontal Bounding Box for Multi-Oriented Object Detection
Yongchao Xu, Mingtao Fu, Qimeng Wang, Yukang Wang, Kai Chen, Gui-Song Xia, Xiang Bai
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 divide-and-conquer selection by obliquity factor r (ablation) | Gliding Vertex · DOTA (IoU 0.5) with FPN | mAP (%): 74.43 -> 75.02 | Improved |
| Add divide-and-conquer selection by obliquity factor r (ablation) | Gliding Vertex · DOTA (IoU 0.5) w/o FPN | mAP (%): 72.33 -> 73.39 | Improved |
| Add divide-and-conquer selection by obliquity factor r (ablation) | Gliding Vertex · DOTA (IoU 0.7) with FPN | mAP (%): 50.94 -> 53.49 | Improved |
| Gliding vertex representation instead of RBox regression | Faster R-CNN with FPN · DOTA (IoU 0.5) | mAP (%): 68.72 -> 75.02 | Improved |
| Gliding vertex representation instead of direct Vertex regression | Faster R-CNN with FPN · DOTA (IoU 0.5) | mAP (%): 63.65 -> 75.02 | Improved |
| Gliding vertex instead of RBox regression at stricter IoU 0.7 | Faster R-CNN with FPN · DOTA (IoU 0.7) | mAP (%): 27.56 -> 53.49 | Improved |
| Add FPN to Gliding Vertex (ablation) | Gliding Vertex · DOTA (IoU 0.5) | mAP (%): 73.39 -> 75.02 | Improved |
| Raise obliquity threshold t_r from 0.65 to 0.85 (ablation) | Gliding Vertex with FPN · DOTA | mAP (%): 73.29 -> 75.06 | Improved |
| Raise obliquity threshold t_r from 0.85 to 0.95 (ablation) | Gliding Vertex with FPN · DOTA | mAP (%): 75.06 -> 74.44 | Hurt |
| Use multi-scale test | Gliding Vertex · RCTW-17 | F-measure (%): 68.1 -> 69.3 | Improved |
| Swap Faster R-CNN head for light-head R-CNN (ablation) | Gliding Vertex · DOTA (FPN) | mAP (%): 75.02 -> 74.05 | Hurt |
Closest papers by meaning
- ABBSPO: Adaptive Bounding Box Scaling and Symmetric Prior based Orientation Prediction for Detecting Aerial Image Objects (CVPR 2025 · similarity 0.89)
- H2RBox: Horizontal Box Annotation is All You Need for Oriented Object Detection (ICLR 2023 · similarity 0.89)
- Learning High-Precision Bounding Box for Rotated Object Detection via Kullback-Leibler Divergence (NeurIPS 2021 · similarity 0.88)
- Theoretically Achieving Continuous Representation of Oriented Bounding Boxes (CVPR 2024 · similarity 0.88)
- FRED: Towards a Full Rotation-Equivariance in Aerial Image Object Detection (AAAI 2024 · similarity 0.87)
- ReDiffDet: Rotation-equivariant Diffusion Model for Oriented Object Detection (CVPR 2025 · 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.
