A novel approach to generate datasets with XAI ground truth to evaluate image models
This addresses the lack of ground truth for verifying XAI techniques, which is crucial for understanding AI model decisions, but it is incremental as it builds on existing XAI evaluation needs.
The paper tackles the problem of verifying explainable AI (XAI) methods by proposing a new approach to generate datasets with ground truth for evaluating image models, achieving excellent results in experiments that compared the ground truth with real model explanations.
With the increased usage of artificial intelligence (AI), it is imperative to understand how these models work internally. These needs have led to the development of a new field called eXplainable artificial intelligence (XAI). This field consists of on a set of techniques that allows us to theoretically determine the cause of the AI decisions. One main issue of XAI is how to verify the works on this field, taking into consideration the lack of ground truth (GT). In this study, we propose a new method to generate datasets with GT. We conducted a set of experiments that compared our GT with real model explanations and obtained excellent results confirming that our proposed method is correct.