Summary of Semi-supervised Semantic Segmentation Using Redesigned Self-training For White Blood Cells, by Vinh Quoc Luu et al.
Semi-Supervised Semantic Segmentation using Redesigned Self-Training for White Blood Cells
by Vinh Quoc Luu, Duy Khanh Le, Huy Thanh Nguyen, Minh Thanh Nguyen, Thinh Tien Nguyen, Vinh Quang Dinh
First submitted to arxiv on: 14 Jan 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 This paper tackles the challenges of using Artificial Intelligence (AI) in healthcare, specifically for diagnosing white blood cell cancer. The main issues are the lack of large-scale labeled datasets and outdated segmentation methods, hindering the development of accurate and modern techniques. To address this, the authors propose a novel self-training pipeline incorporating FixMatch, a consistency-regularization algorithm that improves performance. By using FixMatch in the self-training pipeline, the authors achieve high accuracy rates on various benchmark datasets. |
| Low | GrooveSquid.com (original content) | Low Difficulty Summary Artificial Intelligence is helping doctors diagnose cancer better. But there’s a problem: we don’t have enough labeled data to train AI models for white blood cell cancer diagnosis. This makes it hard to develop new and more accurate ways of diagnosing this type of cancer. To solve this issue, the authors created a new way of training AI models using limited data. They combined two techniques: self-training and FixMatch. Self-training uses the trained model to predict labels for unlabeled data and then trains again on both labeled and unlabeled data. FixMatch makes the model more robust by ensuring it’s consistent when looking at slightly different images. By combining these techniques, the authors achieved high accuracy rates on various datasets. |
Keywords
» Artificial intelligence » Regularization » Self training
