Research map / Detection and segmentation / CNN features
Oriented R-CNN for Object Detection
Xingxing Xie, Gong Cheng, Jiabao Wang, Xiwen Yao, Junwei Han
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 RoI Transformer+ proposal generation with oriented RPN (Oriented R-CNN) | two-stage oriented detector, R-50-FPN · DOTA test | mAP: 74.61 -> 75.87 | Improved |
| replace RoI Transformer+ proposal generation with oriented RPN (Oriented R-CNN) | two-stage oriented detector, R-50-FPN · DOTA speed (RTX 2080Ti) | FPS: 11.3 -> 15.1 | Improved |
| use oriented R-CNN instead of one-stage RetinaNet-O | R-50-FPN detector · DOTA test | mAP / FPS: 68.43 -> 75.87 mAP; 16.1 -> 15.1 FPS | Mixed |
| add multi-scale training and testing | Oriented R-CNN R-50-FPN · DOTA test | mAP: 75.87 -> 80.87 | Improved |
| add multi-scale training and testing | Oriented R-CNN R-101-FPN · DOTA test | mAP: 76.28 -> 80.52 | Improved |
| use ResNet-101-FPN instead of ResNet-50-FPN backbone | Oriented R-CNN · DOTA test | mAP: 75.87 -> 76.28 | Improved |
| use ResNet-101-FPN instead of ResNet-50-FPN backbone | Oriented R-CNN · HRSC2016 (VOC12 metric) | mAP: 96.50 -> 97.60 | Improved |
| use ResNet-101-FPN instead of ResNet-50-FPN backbone | Oriented R-CNN · HRSC2016 (VOC07 metric) | mAP: 90.40 -> 90.50 | No clear effect |
| reduce proposals from 2000 to 1000 per image patch (ablation) | oriented RPN · DOTA val | recall: 92.80 -> 92.20 | Hurt |
| reduce proposals from 1000 to 300 per image patch (ablation) | oriented RPN · DOTA val | recall: 92.20 -> 81.60 | Hurt |
| outperform all R-101-FPN comparison methods using only R-50-FPN | Oriented R-CNN · DOTA test | mAP: 75.87 vs 75.02 (Gliding Vertex, R-101-FPN) | Improved |
Earlier methods this paper compares with
Named baselines from earlier accepted papers in this paper's results tables: better than 1 of 1 on most shared results.
- SCRDet — SCRDet: Towards More Robust Detection for Small, Cluttered and Rotated Objects (ICCV 2019) · better on 1 of 1 shared result
Matched by method name in results tables read by AI. Authors' own tables tend to favour the newer method, and a comparison can be missed when a method is renamed.
Closest papers by meaning
- Learning RoI Transformer for Oriented Object Detection in Aerial Images (CVPR 2019 · similarity 0.89)
- Faster R-CNN: Towards Real-Time Object Detection with Region Proposal Networks (TPAMI 2016 · similarity 0.89)
- Adaptive Rotated Convolution for Rotated Object Detection (ICCV 2023 · similarity 0.89)
- GRA: Detecting Oriented Objects through Group-wise Rotating and Attention (ECCV 2024 · similarity 0.88)
- R-FCN: Object Detection via Region-based Fully Convolutional Networks (NeurIPS 2016 · similarity 0.87)
- Sparse R-CNN: An End-to-End Framework for Object Detection (TPAMI 2023 · 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.
