Research map / Detection and segmentation / CNN features
Towards Rotation Invariance in Object Detection
Agastya Kalra, Guy Stoppi, Bradley Brown, Rishav Agarwal, Achuta Kadambi
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 |
|---|---|---|---|
| replace Largest Box labels with Ellipse + RU Loss for rotation augmentation | object detector (Detectron2) · Transparent Object Bin Picking | AP75: largest box almost 50% worse, ours 4.5% better | Improved |
| use Ellipse label instead of Largest Box (and every other prior tried) (ablation) | rotation augmentation for COCO detection · COCO val2017 rotated 0-40 degrees | AP | Improved |
| add RU Loss with delta=10 degrees on top of Ellipse labels (ablation) | Ellipse label rotation · COCO val2017 rotated 0-40 degrees | AP | Improved |
| use larger delta in RU Loss on simpler datasets than COCO (ablation) | RU Loss · simpler detection datasets | AP | Improved |
| higher Expected IoU of the rotation label method (ablation) | label rotation methods · COCO val2017 at 10 degrees | AP | Improved |
| use Ellipse versus other label methods at 0 degrees (ablation) | rotation label methods · COCO val2017 at 0 degrees | AP | No clear effect |
| use COCO shape priors instead of random shapes for the optimization (ablation) | Ellipse method · COCO | AP | No clear effect |
Closest papers by meaning
- Arbitrary-Oriented Object Detection with Circular Smooth Label (ECCV 2020 · similarity 0.89)
- FRED: Towards a Full Rotation-Equivariance in Aerial Image Object Detection (AAAI 2024 · similarity 0.88)
- Rethinking Boundary Discontinuity Problem for Oriented Object Detection (CVPR 2024 · similarity 0.86)
- R2Det: Exploring Relaxed Rotation Equivariance in 2D Object Detection (ICLR 2025 · similarity 0.86)
- ReDiffDet: Rotation-equivariant Diffusion Model for Oriented Object Detection (CVPR 2025 · similarity 0.85)
- Selective Disk Bispectrum: A Complete and Rotation Invariant Image Descriptor (NeurIPS 2026 · similarity 0.85)
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.
