Research map / Detection and segmentation / Weakly supervised detection and segmentation
Wholly-WOOD: Wholly Leveraging Diversified-Quality Labels for Weakly-Supervised Oriented Object Detection
Yi Yu, Xue Yang, Yansheng Li, Zhenjun Han, Feipeng Da, Junchi Yan
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 PSC angle coder and snap loss together (ablation) | H2RBox-v2 · DOTA-v1.0 | AP50: 52.24 -> 72.31 | Improved |
| add PSC angle coder and snap loss together (ablation) | H2RBox-v2 · HRSC | AP50: 7.83 -> 89.66 | Improved |
| add fusion and scaling to P2R subnet (ablation) | Wholly-WOOD Point-to-RBox · DOTA-v1.0 | AP50: 53.02 -> 62.63 | Improved |
| add fusion and scaling to Point2RBox (ablation) | Point2RBox · DOTA-v1.0 | AP50: 40.27 -> 51.99 | Improved |
| add recolor step in pattern generator (ablation) | Point2RBox · DOTA-v1.0 | AP50: 28.72 -> 40.27 | Improved |
| add CircumIoU loss (ablation) | Wholly-WOOD HBox branch · DOTA-v1.0 | AP50: 71.49 -> 72.31 | Improved |
| use reflection padding instead of zeros (ablation) | H2RBox-v2 · HRSC | AP50: 89.32 -> 89.66 | Improved |
| restrict rotation range to pi/4~3pi/4 instead of -pi~pi (ablation) | H2RBox-v2 · HRSC | AP50: 89.47 -> 89.45 | Mixed |
| lambda 0.05 versus 0 (add flip loss weight) (ablation) | H2RBox-v2 · HRSC | AP50: 0.32 -> 89.66 | Improved |
| increase lambda to 1.0 (ablation) | H2RBox-v2 · HRSC | AP50: 89.66 -> 6.97 | Hurt |
| add 30% annotation noise (ablation) | Point2RBox · DOTA-v1.0 | AP50: 40.27 -> 38.42 | No clear effect |
| add 30% annotation noise (ablation) | H2RBox-v2 · DOTA-v1.0 | AP50: 72.31 -> 71.11 | No clear effect |
Closest papers by meaning
- Point2RBox: Combine Knowledge from Synthetic Visual Patterns for End-to-end Oriented Object Detection with Single Point Supervision (CVPR 2024 · similarity 0.91)
- ABBSPO: Adaptive Bounding Box Scaling and Symmetric Prior based Orientation Prediction for Detecting Aerial Image Objects (CVPR 2025 · similarity 0.90)
- Relational Matching for Weakly Semi-Supervised Oriented Object Detection (CVPR 2024 · similarity 0.89)
- Multi-clue Consistency Learning to Bridge Gaps Between General and Oriented Object in Semi-supervised Detection (AAAI 2025 · similarity 0.88)
- Point2RBox-v2: Rethinking Point-supervised Oriented Object Detection with Spatial Layout Among Instances (CVPR 2025 · similarity 0.88)
- PointOBB-v2: Towards Simpler, Faster, and Stronger Single Point Supervised Oriented Object Detection (ICLR 2025 · similarity 0.87)
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.
