Summary of Class-balanced Open-set Semi-supervised Object Detection For Medical Images, by Zhanyun Lu et al.
Class-balanced Open-set Semi-supervised Object Detection for Medical Images
by Zhanyun Lu, Renshu Gu, Huimin Cheng, Siyu Pang, Mingyu Xu, Peifang Xu, Yaqi Wang, Yuichiro Kinoshita, Juan Ye, Gangyong Jia, Qing Wu
First submitted to arxiv on: 22 Aug 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 paper presents an innovative approach to Semi-Supervised Object Detection (SSOD) for medical images, addressing two key limitations in existing methods: class imbalance and open-set challenges. The proposed method incorporates Category Control Embed (CCE) and out-of-distribution Detection Fusion Classifier (OODFC). CCE tackles dataset imbalance by constructing a Foreground information Library, while OODFC integrates the “unknown” information into basic pseudo-labels. This approach achieves a 4.25 mAP improvement on the public Parasite dataset, surpassing state-of-the-art SSOD performance. |
| Low | GrooveSquid.com (original content) | Low Difficulty Summary This paper is about using medical images to train an object detector that can recognize objects in real-world situations. Normally, these images don’t have labels or are imbalanced, which makes it hard for the detector to learn. The existing approaches try to solve this problem by ignoring the parts of the image that they’re not sure about, but this is not a very good solution. This paper proposes two new techniques: Category Control Embed (CCE) and out-of-distribution Detection Fusion Classifier (OODFC). CCE helps with class imbalance, while OODFC makes the detector smarter at recognizing what it doesn’t know. The result is an object detector that performs much better than existing ones. |
Keywords
» Artificial intelligence » Object detection » Semi supervised
