Summary of Theoretically Achieving Continuous Representation Of Oriented Bounding Boxes, by Zi-kai Xiao et al.
Theoretically Achieving Continuous Representation of Oriented Bounding Boxes
by Zi-Kai Xiao, Guo-Ye Yang, Xue Yang, Tai-Jiang Mu, Junchi Yan, Shi-min Hu
First submitted to arxiv on: 29 Feb 2024
Categories
- Main: Computer Vision and Pattern Recognition (cs.CV)
- Secondary: Artificial Intelligence (cs.AI)
GrooveSquid.com Paper Summaries
GrooveSquid.com’s goal is to make artificial intelligence research accessible by summarizing AI papers in simpler terms. Each summary below covers the same AI paper, written at different levels of difficulty. The medium difficulty and low difficulty versions are original summaries written by GrooveSquid.com, while the high difficulty version is the paper’s original abstract. Feel free to learn from the version that suits you best!
| Summary difficulty | Written by | Summary |
|---|---|---|
| High | Paper authors | High Difficulty Summary Read the original abstract here |
| Medium | GrooveSquid.com (original content) | Medium Difficulty Summary The proposed paper tackles a long-standing issue in Oriented Object Detection (OOD) regarding the discontinuity in Oriented Bounding Box (OBB) representation, which hinders the performance of existing OOD methods. The authors present a novel approach called Continuous OBB (COBB), which ensures continuity in bounding box regression, a feature that has not been achieved before for rectangle-based object representation. COBB can be integrated into popular detectors like Faster-RCNN as a plugin, and outperforms peer methods on the DOTA dataset by 1.13% mAP50 and 2.46% mAP75 without any tricks. |
| Low | GrooveSquid.com (original content) | Low Difficulty Summary This paper solves a problem in Oriented Object Detection (OOD) that has been around for a long time. The issue is about how to represent objects in a way that makes sense, and the authors come up with a new method called Continuous OBB (COBB). This helps improve the performance of object detectors like Faster-RCNN. COBB works better than other methods on a popular dataset, which shows its effectiveness. |
Keywords
» Artificial intelligence » Bounding box » Faster rcnn » Object detection » Regression
