Research map / Detection and segmentation / CNN features
Phase-Shifting Coder: Predicting Accurate Orientation in 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 |
|---|---|---|---|
| Use dual-frequency PSC instead of single-frequency PSC (ablation) | YOLOv5s · DOTA | mAP75: 47.56 -> 51.50 | Helped |
| Use dual-frequency PSC instead of single-frequency PSC (ablation) | YOLOv5m · DOTA | mAP75: 50.50 -> 54.10 | Helped |
| Use dual-frequency PSC instead of single-frequency PSC (ablation) | FCOS and RetinaNet · HRSC | mAP75 | Hurt |
| Use dual-frequency PSC instead of single-frequency PSC (ablation) | FCOS and RetinaNet · OCDPCB | mAP75 | Hurt |
| Vary Nstep among 3, 4, and 5 (ablation) | RetinaNet + PSCD · DOTA and HRSC | mAP | No clear effect |
| Use PSC rather than CSL | Oriented detectors · DOTA | mAP75: +2.59 pp | Helped |
| Use PSCD rather than KLD | Oriented detectors · DOTA | mAP75: +2.36 pp | Helped |
| Use PSC rather than KLD | FCOS and RetinaNet · HRSC | mAP75: 1.1 pp and 2.54 pp | Helped |
| Use PSC rather than KLD | Oriented detectors · OCDPCB | mAP75: 9.83 pp | Helped |
| Use PSC angle coding | RetinaNet (R-50) · DOTA, 1024 × 1024 images | inference time: 43.0 -> 43.1 ms | Hurt |
| Use PSCD angle coding | RetinaNet (R-50) · DOTA, 1024 × 1024 images | inference time: 43.0 -> 43.4 ms | Hurt |
Closest papers by meaning
- Rethinking Boundary Discontinuity Problem for Oriented Object Detection (CVPR 2024 · similarity 0.87)
- ReDiffDet: Rotation-equivariant Diffusion Model for Oriented Object Detection (CVPR 2025 · similarity 0.82)
- PointOBB-v2: Towards Simpler, Faster, and Stronger Single Point Supervised Oriented Object Detection (ICLR 2025 · similarity 0.82)
- Selective Disk Bispectrum: A Complete and Rotation Invariant Image Descriptor (NeurIPS 2026 · similarity 0.81)
- Theoretically Achieving Continuous Representation of Oriented Bounding Boxes (CVPR 2024 · similarity 0.81)
- R2Det: Exploring Relaxed Rotation Equivariance in 2D Object Detection (ICLR 2025 · similarity 0.81)
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.