Human-Centered Evaluation of XAI Methods
This work addresses the problem of AI transparency for users by showing that multiple explanation methods are similarly effective in enhancing interpretability, though it is incremental as it compares existing methods without introducing new ones.
The study evaluated three XAI methods (Prototypical Part Network, Occlusion, and Layer-wise Relevance Propagation) for image classification, finding that despite variations in highlighted regions, all provided humans with nearly equivalent understanding for efficient image categorization.
In the ever-evolving field of Artificial Intelligence, a critical challenge has been to decipher the decision-making processes within the so-called "black boxes" in deep learning. Over recent years, a plethora of methods have emerged, dedicated to explaining decisions across diverse tasks. Particularly in tasks like image classification, these methods typically identify and emphasize the pivotal pixels that most influence a classifier's prediction. Interestingly, this approach mirrors human behavior: when asked to explain our rationale for classifying an image, we often point to the most salient features or aspects. Capitalizing on this parallel, our research embarked on a user-centric study. We sought to objectively measure the interpretability of three leading explanation methods: (1) Prototypical Part Network, (2) Occlusion, and (3) Layer-wise Relevance Propagation. Intriguingly, our results highlight that while the regions spotlighted by these methods can vary widely, they all offer humans a nearly equivalent depth of understanding. This enables users to discern and categorize images efficiently, reinforcing the value of these methods in enhancing AI transparency.