Summary of Uncertainty Driven Active Learning For Image Segmentation in Underwater Inspection, by Luiza Ribeiro Marnet et al.
Uncertainty Driven Active Learning for Image Segmentation in Underwater Inspection
by Luiza Ribeiro Marnet, Yury Brodskiy, Stella Grasshof, Andrzej Wasowski
First submitted to arxiv on: 20 Mar 2024
Categories
- Main: Computer Vision and Pattern Recognition (cs.CV)
- Secondary: Machine Learning (cs.LG)
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 Active learning for image segmentation in underwater infrastructure inspection tasks is explored in this study. A pipeline inspection dataset containing over 50,000 images was used to train and evaluate a HyperSeg model with active learning. The model achieved a mean IoU of 67.5% using only 12.5% of the data, outperforming a random sampling approach. This demonstrates the potential for cost savings in this application. DenseNet and HyperSeg were trained with the CamVid dataset using active learning to assess the effectiveness of the framework. Mutual information was used as the acquisition function, calculated using Monte Carlo dropout. |
| Low | GrooveSquid.com (original content) | Low Difficulty Summary This study shows that active learning can be effective in image segmentation tasks related to underwater infrastructure inspection. A large dataset of pipeline inspection images was used to train and evaluate a HyperSeg model with active learning. The results showed that the model performed well using only a small portion of the data, which could help reduce costs. |
Keywords
* Artificial intelligence * Active learning * Dropout * Image segmentation
