Summary of Underwater Sonar Image Classification and Analysis Using Lime-based Explainable Artificial Intelligence, by Purushothaman Natarajan and Athira Nambiar
Underwater SONAR Image Classification and Analysis using LIME-based Explainable Artificial Intelligence
by Purushothaman Natarajan, Athira Nambiar
First submitted to arxiv on: 23 Aug 2024
Categories
- Main: Computer Vision and Pattern Recognition (cs.CV)
- Secondary: Artificial Intelligence (cs.AI); Human-Computer Interaction (cs.HC); 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 This paper explores the application of Explainable Artificial Intelligence (XAI) to interpret underwater image classification results, using deep learning techniques to mimic human cognition. The study focuses on SONAR image classification, utilizing a custom dataset derived from various sources. An extensive analysis is conducted on transfer learning techniques for image classification using benchmark CNN architectures such as VGG16, ResNet50, InceptionV3, and DenseNet121. To provide transparent justifications for the model’s decisions, post-hoc XAI techniques like Local Interpretable Model-Agnostic Explanations (LIME) are incorporated, perturbing input data locally to see how predictions change. Additionally, Submodular Picks LIME (SP-LIME), a version of LIME specific to images, is studied, leveraging Quickshift and Simple Linear Iterative Clustering (SLIC) for submodular picks. The analysis highlights the interpretability of results in a more human-compliant way, increasing confidence and reliability. |
| Low | GrooveSquid.com (original content) | Low Difficulty Summary This paper uses special computer programs called deep learning techniques to help humans understand how computers make decisions about underwater images. It creates a custom dataset from different sources and tests different computer models like VGG16 and ResNet50 to see which one works best. To explain why the model chose a certain image, it uses another technique called LIME that changes small parts of the image to see how the prediction changes. This helps humans understand what the computer is looking at in the image. The study shows that this approach can help make computers more reliable and trustworthy. |
Keywords
» Artificial intelligence » Clustering » Cnn » Deep learning » Image classification » Transfer learning
