Research map / Detection and segmentation / CNN features
Shape-Adaptive Selection and Measurement for Oriented Object Detection
Read the paperCheck 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 |
|---|---|---|---|
| Add SA-S and SA-M to RepPoints | RepPoints · HRSC2016 | mAP: 85.16 -> 90.00 | Helped |
| Add SA-S and SA-M to S2A-Net | S2A-Net · HRSC2016 | mAP: 90.17 -> 90.27 | Helped |
| Add SA-S and SA-M to S2A-Net | S2A-Net · DOTA-v1.0 | mAP: 76.95 -> 79.17 | Helped |
| Add SA-S and SA-M to RepPoints | RepPoints · UCAS-AOD | AP50: 86.18 -> 90.38 | Helped |
| Add SA-S and SA-M to RepPoints | RepPoints · UCAS-AOD | AP75: 49.30 -> 58.66 | Helped |
| Add SA-S and SA-M to RepPoints | RepPoints · ICDAR2015 | F-measure: 73.2 -> 83.9 | Helped |
| Add boundary-center loss (ablation) | RepPoints · DOTA | mAP: 70.25 -> 70.96 | Helped |
| Add SA-S (ablation) | RepPoints + BCL · DOTA | mAP: 70.96 -> 74.60 | Helped |
| Add SA-M (ablation) | RepPoints + BCL + SA-S · DOTA | mAP: 74.60 -> 74.92 | Helped |
| Add boundary-center loss (ablation) | RepPoints · HRSC2016 | mAP: 75.11 -> 77.38 | Helped |
| Add SA-S (ablation) | RepPoints + BCL · HRSC2016 | mAP: 77.38 -> 87.01 | Helped |
| Add SA-M (ablation) | RepPoints + BCL + SA-S · HRSC2016 | mAP: 87.01 -> 88.60 | Helped |
Closest papers by meaning
- Bridging the Gap Between Anchor-Based and Anchor-Free Detection via Adaptive Training Sample Selection (CVPR 2020 · similarity 0.89)
- PointOBB-v2: Towards Simpler, Faster, and Stronger Single Point Supervised Oriented Object Detection (ICLR 2025 · similarity 0.85)
- Rethinking Boundary Discontinuity Problem for Oriented Object Detection (CVPR 2024 · similarity 0.83)
- ReDiffDet: Rotation-equivariant Diffusion Model for Oriented Object Detection (CVPR 2025 · similarity 0.83)
- AS-Det: Active Sampling for Adaptive 3D Object Detection in Point Clouds (AAAI 2025 · similarity 0.83)
- Improving Single Domain-Generalized Object Detection: A Focus on Diversification and Alignment (CVPR 2024 · similarity 0.83)
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.