Summary of Pceve: Part Contribution Evaluation Based Model Explanation For Human Figure Drawing Assessment and Beyond, by Jongseo Lee et al.
PCEvE: Part Contribution Evaluation Based Model Explanation for Human Figure Drawing Assessment and Beyond
by Jongseo Lee, Geo Ahn, Seong Tae Kim, Jinwoo Choi
First submitted to arxiv on: 26 Sep 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 PCEvE framework proposes a novel model explanation approach for automatic human figure drawing (HFD) assessment tasks, such as diagnosing autism spectrum disorder (ASD). The existing pixel-level attribution-based explainable AI (XAI) methods require significant user effort to interpret semantic information, which can be time-consuming and impractical. The PCEvE framework overcomes this challenge by measuring the Shapley Value of each individual part to evaluate its contribution to a model decision, providing a straightforward explanation in the form of a part contribution histogram. This approach expands explanations beyond sample-level to include class-level and task-level insights, offering a richer understanding of model behavior. |
| Low | GrooveSquid.com (original content) | Low Difficulty Summary The PCEvE framework is a new way to explain how AI models make decisions about drawing human figures. Right now, it’s hard for people to understand why an AI model chose one answer over another. The PCEvE framework makes it easier by showing what parts of the drawing contributed most to the model’s decision. This can help diagnose autism spectrum disorder and other conditions more accurately. |
