Summary of Epl: Evidential Prototype Learning For Semi-supervised Medical Image Segmentation, by Yuanpeng He
EPL: Evidential Prototype Learning for Semi-supervised Medical Image Segmentation
by Yuanpeng He
First submitted to arxiv on: 9 Apr 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 Evidential Prototype Learning (EPL) approach effectively fuses voxel probability predictions from various sources, leveraging voxel-level dual uncertainty masking. This method utilizes an extended probabilistic framework to integrate labeled and unlabeled data under a generalized evidential framework. The uncertainty enables the model to self-correct predictions and improves the guided learning process with pseudo-labels, feeding back into hidden feature construction. EPL outperforms current semi-supervised medical segmentation methods on LA, Pancreas-CT, and TBAD datasets in various labeled ratios. |
| Low | GrooveSquid.com (original content) | Low Difficulty Summary Evidential Prototype Learning (EPL) is a new way to improve medical image segmentation. It combines information from different sources to get more accurate results. This approach also helps the model correct its own mistakes and learn better. EPL works well on several important datasets, showing that it’s a powerful tool for medical imaging. |
Keywords
» Artificial intelligence » Image segmentation » Probability » Semi supervised
