R3Det: Refined Single-Stage Detector with Feature Refinement for Rotating Object
Xue Yang, Junchi Yan, Ziming Feng, Tao He
Abstract
Rotation detection is a challenging task due to the difficulties of locating the multi-angle objects and separating them effectively from the background. Though considerable progress has been made, for practical settings, there still exist challenges for rotating objects with large aspect ratio, dense distribution and category extremely imbalance. In this paper, we propose an end-to-end refined single-stage rotation detector for fast and accurate object detection by using a progressive regression approach from coarse to fine granularity. Considering the shortcoming of feature misalignment in existing refined single-stage detector, we design a feature refinement module to improve detection performance by getting more accurate features. The key idea of feature refinement module is to re-encode the position information of the current refined bounding box to the corresponding feature points through pixel-wise feature interpolation to realize feature reconstruction and alignment. For more accurate rotation estimation, an approximate SkewIoU loss is proposed to solve the problem that the calculation of SkewIoU is not derivable. Experiments on three popular remote sensing public datasets DOTA, HRSC2016, UCAS-AOD as well as one scene text dataset ICDAR2015 show the effectiveness of our approach. The source code is available at https://github.com/Thinklab-SJTU/R3Det_Tensorflow and is also integrated in our open source rotation detection benchmark: https://github.com/yangxue0827/RotationDetection.
Ask Lune
Know this paper in minutes, not an afternoon.
Lune can read every page of it and the top-tier papers that cite it, and gives you its claims, its evidence and its limits, each one cited to the paper it comes from. No skimming, no AI slop.
31 top-tier papers have cited it since. Know what they found before your reviewers do.
Lune can draw on
the full paper · the top-tier papers that cite it · related work
Free to start. No credit card required.
Lineage
- Large Selective Kernel Network for Remote Sensing Object Detection cites SCRDet: Towards More Robust Detection for Small, Cluttered and Rotated Objects
- Large Selective Kernel Network for Remote Sensing Object Detection cites Learning High-Precision Bounding Box for Rotated Object Detection via Kullback-Leibler Divergence
- Large Selective Kernel Network for Remote Sensing Object Detection cites Learning Modulated Loss for Rotated Object Detection
- Large Selective Kernel Network for Remote Sensing Object Detection cites Oriented R-CNN for Object Detection
- Large Selective Kernel Network for Remote Sensing Object Detection cites Dynamic Anchor Learning for Arbitrary-Oriented Object Detection
- Learning High-Precision Bounding Box for Rotated Object Detection via Kullback-Leibler Divergence cites SCRDet: Towards More Robust Detection for Small, Cluttered and Rotated Objects
- Learning High-Precision Bounding Box for Rotated Object Detection via Kullback-Leibler Divergence cites Distance-IoU Loss: Faster and Better Learning for Bounding Box Regression
- Learning High-Precision Bounding Box for Rotated Object Detection via Kullback-Leibler Divergence cites Learning Modulated Loss for Rotated Object Detection
- Learning High-Precision Bounding Box for Rotated Object Detection via Kullback-Leibler Divergence cites Dynamic Anchor Learning for Arbitrary-Oriented Object Detection
- Learning High-Precision Bounding Box for Rotated Object Detection via Kullback-Leibler Divergence cites Dynamic Refinement Network for Oriented and Densely Packed Object Detection
- Learning Modulated Loss for Rotated Object Detection cites SCRDet: Towards More Robust Detection for Small, Cluttered and Rotated Objects
- Oriented R-CNN for Object Detection cites SCRDet: Towards More Robust Detection for Small, Cluttered and Rotated Objects
- Oriented R-CNN for Object Detection cites Learning Modulated Loss for Rotated Object Detection
- Oriented R-CNN for Object Detection cites Dynamic Anchor Learning for Arbitrary-Oriented Object Detection
- Oriented R-CNN for Object Detection cites Dynamic Refinement Network for Oriented and Densely Packed Object Detection
- Dynamic Anchor Learning for Arbitrary-Oriented Object Detection cites SCRDet: Towards More Robust Detection for Small, Cluttered and Rotated Objects
- Dynamic Anchor Learning for Arbitrary-Oriented Object Detection cites Dynamic Refinement Network for Oriented and Densely Packed Object Detection
- Dynamic Refinement Network for Oriented and Densely Packed Object Detection cites SCRDet: Towards More Robust Detection for Small, Cluttered and Rotated Objects
Cited by top-tier papers31
- Oriented R-CNN for Object DetectionXingxing Xie, Gong Cheng, Jiabao Wang, Xiwen Yao et al.ICCV 2021 · 1,070 citations
- Learning High-Precision Bounding Box for Rotated Object Detection via Kullback-Leibler DivergenceXue Yang, Xiaojiang Yang, Jirui Yang, Qi Ming et al.NeurIPS 2021 · 603 citations
- Large Selective Kernel Network for Remote Sensing Object DetectionYuxuan Li, Qibin Hou, Zhaohui Zheng, Ming-Ming Cheng et al.ICCV 2023 · 535 citations
- Learning Modulated Loss for Rotated Object DetectionWen Qian, Xue Yang, Silong Peng, Junchi Yan et al.AAAI 2021 · 392 citations
- Dynamic Anchor Learning for Arbitrary-Oriented Object DetectionQi Ming, Zhiqiang Zhou, Lingjuan Miao, Hongwei Zhang et al.AAAI 2021 · 332 citations
Builds on3
- Distance-IoU Loss: Faster and Better Learning for Bounding Box RegressionZhaohui Zheng, Ping Wang, Wei Liu, Jinze Li et al.AAAI 2020 · 4,823 citations
- SCRDet: Towards More Robust Detection for Small, Cluttered and Rotated ObjectsXue Yang, Jirui Yang, Junchi Yan, Yue Zhang et al.ICCV 2019 · 865 citations
- Dynamic Refinement Network for Oriented and Densely Packed Object DetectionXingjia Pan, Yuqiang Ren, Kekai Sheng, Weiming Dong et al.CVPR 2020
Related papers
- OSKDet: Orientation-sensitive Keypoint Localization for Rotated Object DetectionDongchen Lu, Dongmei Li, Yali Li, Shengjin WangCVPR 2022 · 25 citations
- Dense Label Encoding for Boundary Discontinuity Free Rotation DetectionXue Yang, Liping Hou, Yue Zhou, Wentao Wang et al.CVPR 2021
- The KFIoU Loss for Rotated Object DetectionXue Yang, Yue Zhou, Gefan Zhang, Jirui Yang et al.ICLR 2023 · 89 citations
- Fourier Angle Alignment for Oriented Object Detection in Remote SensingChangyu Gu, Linwei Chen, Lin Gu, Ying FuCVPR 2026 · 9 citations
- Measuring the Impact of Rotation Equivariance on Aerial Object DetectionXiuyu Wu, Xinhao Wang, Xiubin Zhu, Lan Yang et al.ICCV 2025 · 4 citations
