H2RBox: Horizonal Box Annotation is All You Need for Oriented Object
Detection
- URL: http://arxiv.org/abs/2210.06742v1
- Date: Thu, 13 Oct 2022 05:12:45 GMT
- Title: H2RBox: Horizonal Box Annotation is All You Need for Oriented Object
Detection
- Authors: Xue Yang, Gefan Zhang, Wentong Li, Xuehui Wang, Yue Zhou, Junchi Yan
- Abstract summary: Oriented object detection emerges in many applications from aerial images to autonomous driving.
Many existing detection benchmarks are annotated with horizontal bounding box only which is also less costive than fine-grained rotated box.
This paper proposes a simple yet effective oriented object detection approach called H2RBox.
- Score: 63.66553556240689
- License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
- Abstract: 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, and even
surpasses them in some cases. The source code is available at
https://github.com/yangxue0827/h2rbox-mmrotate.
Related papers
- Wholly-WOOD: Wholly Leveraging Diversified-quality Labels for Weakly-supervised Oriented Object Detection [57.26265276035267]
Wholly-WOOD is a weakly-supervised OOD framework capable of wholly leveraging various labeling forms.
By only using HBox for training, our Wholly-WOOD achieves performance very close to that of the RBox-trained counterpart on remote sensing.
arXiv Detail & Related papers (2025-02-13T16:34:59Z) - Point2RBox-v2: Rethinking Point-supervised Oriented Object Detection with Spatial Layout Among Instances [50.80161958767447]
We present Point2RBox-v2, an approach to explore the spatial layout among instances for learning point-supervised OOD.
Our solution is elegant and lightweight, yet it is expected to give a competitive performance especially in densely packed scenes.
arXiv Detail & Related papers (2025-02-06T18:07:25Z) - Point2RBox: Combine Knowledge from Synthetic Visual Patterns for End-to-end Oriented Object Detection with Single Point Supervision [81.60564776995682]
We present Point2RBox, an end-to-end solution for point-supervised object detection.
Our method uses a lightweight paradigm, yet it achieves a competitive performance among point-supervised alternatives.
In particular, our method uses a lightweight paradigm, yet it achieves a competitive performance among point-supervised alternatives.
arXiv Detail & Related papers (2023-11-23T15:57:41Z) - SOOD: Towards Semi-Supervised Oriented Object Detection [57.05141794402972]
This paper proposes a novel Semi-supervised Oriented Object Detection model, termed SOOD, built upon the mainstream pseudo-labeling framework.
Our experiments show that when trained with the two proposed losses, SOOD surpasses the state-of-the-art SSOD methods under various settings on the DOTA-v1.5 benchmark.
arXiv Detail & Related papers (2023-04-10T11:10:42Z) - H2RBox-v2: Incorporating Symmetry for Boosting Horizontal Box Supervised
Oriented Object Detection [55.3948651109885]
We present H2RBox-v2, to bridge the gap between HBox-supervised and RBox-supervised oriented object detection.
To our best knowledge, H2RBox-v2 is the first symmetry-aware self-supervised paradigm for oriented object detection.
arXiv Detail & Related papers (2023-04-10T06:11:40Z) - Oriented Bounding Boxes for Small and Freely Rotated Objects [7.6997148655751895]
A novel object detection method is presented that handles freely rotated objects of arbitrary sizes.
The method encodes the precise location and orientation of features of the target objects at grid cell locations.
Evaluations on the xView and DOTA datasets show that the proposed method uniformly improves performance over existing state-of-the-art methods.
arXiv Detail & Related papers (2021-04-24T02:04:49Z) - Oriented Object Detection in Aerial Images with Box Boundary-Aware
Vectors [21.484827209503823]
Oriented object detection in aerial images is a challenging task as the objects in aerial images are displayed in arbitrary directions.
Current oriented object detection methods mainly rely on two-stage anchor-based detectors.
We extend the horizontal keypoint-based object to the oriented object detection task.
arXiv Detail & Related papers (2020-08-17T00:56:50Z)
This list is automatically generated from the titles and abstracts of the papers in this site.
This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.