Interaction as Explanation: A User Interaction-based Method for Explaining Image Classification Models
This work addresses the need for more intuitive and accessible explainability in AI systems for end-users, though it is incremental in focusing on user interaction rather than a fundamental breakthrough.
The paper tackles the 'black-box' problem in image classification models by introducing an interaction-based explainable AI method that allows users to modify images via painting and erasing to observe classification changes, with experiments on five images demonstrating its potential to reveal feature importance.
In computer vision, explainable AI (xAI) methods seek to mitigate the 'black-box' problem by making the decision-making process of deep learning models more interpretable and transparent. Traditional xAI methods concentrate on visualizing input features that influence model predictions, providing insights primarily suited for experts. In this work, we present an interaction-based xAI method that enhances user comprehension of image classification models through their interaction. Thus, we developed a web-based prototype allowing users to modify images via painting and erasing, thereby observing changes in classification results. Our approach enables users to discern critical features influencing the model's decision-making process, aligning their mental models with the model's logic. Experiments conducted with five images demonstrate the potential of the method to reveal feature importance through user interaction. Our work contributes a novel perspective to xAI by centering on end-user engagement and understanding, paving the way for more intuitive and accessible explainability in AI systems.