PCEvE: Part Contribution Evaluation Based Model Explanation for Human Figure Drawing Assessment and Beyond
This work addresses the need for clearer explanations in diagnostic tasks like autism spectrum disorder assessment from drawings, offering a more practical approach than existing methods, though it is incremental in improving XAI for specific applications.
The paper tackles the challenge of interpretability in automatic human figure drawing assessment by proposing the PCEvE framework, which uses part detection and Shapley Values to provide part contribution histograms for model decisions, validated on multiple datasets with extensions to other domains like Stanford Cars.
For automatic human figure drawing (HFD) assessment tasks, such as diagnosing autism spectrum disorder (ASD) using HFD images, the clarity and explainability of a model decision are crucial. Existing pixel-level attribution-based explainable AI (XAI) approaches demand considerable effort from users to interpret the semantic information of a region in an image, which can be often time-consuming and impractical. To overcome this challenge, we propose a part contribution evaluation based model explanation (PCEvE) framework. On top of the part detection, we measure the Shapley Value of each individual part to evaluate the contribution to a model decision. Unlike existing attribution-based XAI approaches, the PCEvE provides a straightforward explanation of a model decision, i.e., a part contribution histogram. Furthermore, the PCEvE expands the scope of explanations beyond the conventional sample-level to include class-level and task-level insights, offering a richer, more comprehensive understanding of model behavior. We rigorously validate the PCEvE via extensive experiments on multiple HFD assessment datasets. Also, we sanity-check the proposed method with a set of controlled experiments. Additionally, we demonstrate the versatility and applicability of our method to other domains by applying it to a photo-realistic dataset, the Stanford Cars.