# H2RBox: Horizontal Box Annotation is All You Need for Oriented Object Detection

arXiv: https://arxiv.org/abs/2210.06742 · HTML: https://mlsanity.com/paper/2210.06742/

## Key facts

- Cited by 36 papers in the map (data through 14 Oct 2026).
- Builds on 42 of its 50 references that are in the map.
- First posted on arXiv 13 Oct 2022.

## Builds on (most cited first, 30 of 42)

- [Deep Residual Learning for Image Recognition](https://mlsanity.com/paper/1512.03385/) (2015)
- [PyTorch: An Imperative Style, High-Performance Deep Learning Library](https://mlsanity.com/paper/1912.01703/) (2019)
- [Mask R-CNN](https://mlsanity.com/paper/1703.06870/) (2017)
- [Feature Pyramid Networks for Object Detection](https://mlsanity.com/paper/1612.03144/) (2016)
- [FCOS: Fully Convolutional One-Stage Object Detection](https://mlsanity.com/paper/1904.01355/) (2019)
- [Focal Loss for Dense Object Detection](https://mlsanity.com/paper/1708.02002/) (2017)
- [DOTA: A Large-scale Dataset for Object Detection in Aerial Images](https://mlsanity.com/paper/1711.10398/) (2017)
- [Bridging the Gap Between Anchor-based and Anchor-free Detection via Adaptive Training Sample Selection](https://mlsanity.com/paper/1912.02424/) (2019)
- [Deep Learning for Generic Object Detection: A Survey](https://mlsanity.com/paper/1809.02165/) (2018)
- [Object Detection in Optical Remote Sensing Images: A Survey and A New Benchmark](https://mlsanity.com/paper/1909.00133/) (2019)
- [Conditional Convolutions for Instance Segmentation](https://mlsanity.com/paper/2003.05664/) (2020)
- [RepPoints: Point Set Representation for Object Detection](https://mlsanity.com/paper/1904.11490/) (2019)
- [EAST: An Efficient and Accurate Scene Text Detector](https://mlsanity.com/paper/1704.03155/) (2017)
- [Simple Does It: Weakly Supervised Instance and Semantic Segmentation](https://mlsanity.com/paper/1603.07485/) (2016)
- [UnitBox: An Advanced Object Detection Network](https://mlsanity.com/paper/1608.01471/) (2016)
- [ReDet: A Rotation-equivariant Detector for Aerial Object Detection](https://mlsanity.com/paper/2103.07733/) (2021)
- [R3Det: Refined Single-Stage Detector with Feature Refinement for Rotating Object](https://mlsanity.com/paper/1908.05612/) (2019)
- [Align Deep Features for Oriented Object Detection](https://mlsanity.com/paper/2008.09397/) (2020)
- [Arbitrary-Oriented Scene Text Detection via Rotation Proposals](https://mlsanity.com/paper/1703.01086/) (2017)
- [Rethinking Rotated Object Detection with Gaussian Wasserstein Distance Loss](https://mlsanity.com/paper/2101.11952/) (2021)
- [BoxInst: High-Performance Instance Segmentation with Box Annotations](https://mlsanity.com/paper/2012.02310/) (2020)
- [Gliding vertex on the horizontal bounding box for multi-oriented object detection](https://mlsanity.com/paper/1911.09358/) (2019)
- [Learning High-Precision Bounding Box for Rotated Object Detection via Kullback-Leibler Divergence](https://mlsanity.com/paper/2106.01883/) (2021)
- [TextBoxes++: A Single-Shot Oriented Scene Text Detector](https://mlsanity.com/paper/1801.02765/) (2018)
- [MMRotate: A Rotated Object Detection Benchmark using PyTorch](https://mlsanity.com/paper/2204.13317/) (2022)
- [Anchor-free Oriented Proposal Generator for Object Detection](https://mlsanity.com/paper/2110.01931/) (2021)
- [Oriented RepPoints for Aerial Object Detection](https://mlsanity.com/paper/2105.11111/) (2021)
- [Multiscale Combinatorial Grouping for Image Segmentation and Object Proposal Generation](https://mlsanity.com/paper/1503.00848/) (2015)
- [Dense Label Encoding for Boundary Discontinuity Free Rotation Detection](https://mlsanity.com/paper/2011.09670/) (2020)
- [The KFIoU Loss for Rotated Object Detection](https://mlsanity.com/paper/2201.12558/) (2022)

## Built on by (most cited first, 30 of 36)

- [ARS-DETR: Aspect Ratio-Sensitive Detection Transformer for Aerial Oriented Object Detection](https://mlsanity.com/paper/2303.04989/) (2023)
- [STAR: A First-Ever Dataset and A Large-Scale Benchmark for Scene Graph Generation in Large-Size Satellite Imagery](https://mlsanity.com/paper/2406.09410/) (2024)
- [H2RBox-v2: Incorporating Symmetry for Boosting Horizontal Box Supervised Oriented Object Detection](https://mlsanity.com/paper/2304.04403/) (2023)
- [LR-FPN: Enhancing Remote Sensing Object Detection with Location Refined Feature Pyramid Network](https://mlsanity.com/paper/2404.01614/) (2024)
- [PointOBB: Learning Oriented Object Detection via Single Point Supervision](https://mlsanity.com/paper/2311.14757/) (2023)
- [Point2Mask: Point-supervised Panoptic Segmentation via Optimal Transport](https://mlsanity.com/paper/2308.01779/) (2023)
- [PointSAM: Pointly-Supervised Segment Anything Model for Remote Sensing Images](https://mlsanity.com/paper/2409.13401/) (2024)
- [Box2Mask: Box-supervised Instance Segmentation via Level-set Evolution](https://mlsanity.com/paper/2212.01579/) (2022)
- [Point2RBox: Combine Knowledge from Synthetic Visual Patterns for End-to-end Oriented Object Detection with Single Point Supervision](https://mlsanity.com/paper/2311.14758/) (2023)
- [Remote Sensing Object Detection Meets Deep Learning: A Meta-review of Challenges and Advances](https://mlsanity.com/paper/2309.06751/) (2023)
- [PointOBB-v2: Towards Simpler, Faster, and Stronger Single Point Supervised Oriented Object Detection](https://mlsanity.com/paper/2410.08210/) (2024)
- [SOOD++: Leveraging Unlabeled Data to Boost Oriented Object Detection](https://mlsanity.com/paper/2407.01016/) (2024)
- [RSAR: Restricted State Angle Resolver and Rotated SAR Benchmark](https://mlsanity.com/paper/2501.04440/) (2025)
- [Point2RBox-v2: Rethinking Point-supervised Oriented Object Detection with Spatial Layout Among Instances](https://mlsanity.com/paper/2502.04268/) (2025)
- [OrientedFormer: An End-to-End Transformer-Based Oriented Object Detector in Remote Sensing Images](https://mlsanity.com/paper/2409.19648/) (2024)
- [P2RBox: Point Prompt Oriented Object Detection with SAM](https://mlsanity.com/paper/2311.13128/) (2023)
- [Theoretically Achieving Continuous Representation of Oriented Bounding Boxes](https://mlsanity.com/paper/2402.18975/) (2024)
- [PointOBB-v3: Expanding Performance Boundaries of Single Point-Supervised Oriented Object Detection](https://mlsanity.com/paper/2501.13898/) (2025)
- [Wholly-WOOD: Wholly Leveraging Diversified-quality Labels for Weakly-supervised Oriented Object Detection](https://mlsanity.com/paper/2502.09471/) (2025)
- [More Clear, More Flexible, More Precise: A Comprehensive Oriented Object Detection benchmark for UAV](https://mlsanity.com/paper/2504.20032/) (2025)
- [Semi-Supervised Object Detection with Uncurated Unlabeled Data for Remote Sensing Images](https://mlsanity.com/paper/2310.05498/) (2023)
- [Oriented Tiny Object Detection: A Dataset, Benchmark, and Dynamic Unbiased Learning](https://mlsanity.com/paper/2412.11582/) (2024)
- [Partial Weakly-Supervised Oriented Object Detection](https://mlsanity.com/paper/2507.02751/) (2025)
- [Point2RBox-v3: Self-Bootstrapping from Point Annotations via Integrated Pseudo-Label Refinement and Utilization](https://mlsanity.com/paper/2509.26281/) (2025)
- [Active-SAOOD: Active Sparsely Annotated Oriented Object Detection in Remote Sensing Images](https://mlsanity.com/paper/2605.10162/) (2026)
- [SARVLM: A Vision Language Foundation Model for Semantic Understanding in SAR Imagery](https://mlsanity.com/paper/2510.22665/) (2025)
- [SLIP-RS: Structured-Attribute Language-Image Pre-Training for Remote Sensing Object Detection](https://mlsanity.com/paper/2605.23144/) (2026)
- [FPDIoU Loss: A Loss Function for Efficient Bounding Box Regression of Rotated Object Detection](https://mlsanity.com/paper/2405.09942/) (2024)
- [Structure Tensor Representation for Robust Oriented Object Detection](https://mlsanity.com/paper/2411.10497/) (2024)
- [BAFPN: Bi directional alignment of features to improve localization accuracy](https://mlsanity.com/paper/2412.01859/) (2024)

## Abstract (arXiv)

Oriented object detection emerges in many applications from aerial images to autonomous driving, while many existing detection benchmarks are annotated with horizontal bounding box only which is also less costive than fine-grained rotated box, leading to a gap between the readily available training corpus and the rising demand for oriented object detection. This paper proposes a simple yet effective oriented object detection approach called H2RBox merely using horizontal box annotation for weakly-supervised training, which closes the above gap and shows competitive performance even against those trained with rotated boxes. The cores of our method are weakly- and self-supervised learning, which predicts the angle of the object by learning the consistency of two different views. To our best knowledge, H2RBox is the first horizontal box annotation-based oriented object detector. Compared to an alternative i.e. horizontal box-supervised instance segmentation with our post adaption to oriented object detection, our approach is not susceptible to the prediction quality of mask and can perform more robustly in complex scenes containing a large number of dense objects and outliers. Experimental results show that H2RBox has significant performance and speed advantages over horizontal box-supervised instance segmentation methods, as well as lower memory requirements. While compared to rotated box-supervised oriented object detectors, our method shows very close performance and speed. The source code is available at PyTorch-based hrefhttps://github.com/yangxue0827/h2rbox-mmrotateMMRotate and Jittor-based hrefhttps://github.com/yangxue0827/h2rbox-jittorJDet.