Summary of Copronn: Concept-based Prototypical Nearest Neighbors For Explaining Vision Models, by Teodor Chiaburu et al.
CoProNN: Concept-based Prototypical Nearest Neighbors for Explaining Vision Models
by Teodor Chiaburu, Frank Haußer, Felix Bießmann
First submitted to arxiv on: 23 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 This paper proposes a novel approach to designing task-specific explanations for computer vision tasks, leveraging deep generative methods and natural language. The authors introduce CoProNN, a modular framework that enables domain experts to create concept-based explanations intuitively via text-to-image methods. This approach is designed to be simple to implement, adaptable to new tasks, and replaceable with more powerful models as they become available. The paper shows that CoProNN competes well with other concept-based XAI approaches on coarse-grained image classification tasks and may even outperform them on fine-grained tasks. |
| Low | GrooveSquid.com (original content) | Low Difficulty Summary CoProNN is a way for experts to make computer vision tasks easier to understand. It lets experts create explanations using natural language, which can then be used to explain what a computer vision model is doing. This approach is simple and easy to use, and it works well with other approaches that are already out there. |
Keywords
» Artificial intelligence » Image classification
