Summary of Causal Explanations For Image Classifiers, by Hana Chockler et al.
Causal Explanations for Image Classifiers
by Hana Chockler, David A. Kelly, Daniel Kroening, Youcheng Sun
First submitted to arxiv on: 13 Nov 2024
Categories
- Main: Artificial Intelligence (cs.AI)
- Secondary: None
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 A novel approach to computing explanations for image classifiers is presented, grounded in the theory of actual causality. The method, which uses a principled framework based on formal definitions of causes and explanations, outperforms state-of-the-art tools in terms of efficiency, explanation size, and quality measures. The algorithm is proven to be terminating and has a guaranteed level of approximation compared to the precise definition. |
| Low | GrooveSquid.com (original content) | Low Difficulty Summary Imagine you’re trying to understand why an image was classified in a certain way by a computer. Existing methods for doing this have different ideas about what an “explanation” even means, and use different techniques to figure out why the computer made that decision. But none of these methods are based on clear definitions of causes and explanations. A new approach is presented here that uses formal definitions to understand why computers classify images in certain ways. This method is shown to be more efficient and effective than existing tools. |
