Part-based Quantitative Analysis for Heatmaps
This work addresses the need for automated and granular evaluation metrics in XAI to improve accessibility and cost-effectiveness for end-users, though it appears incremental as it builds on existing heatmap methods.
The paper tackles the problem of subjective and expert-dependent analysis of heatmaps in Explainable AI by proposing a part-based quantitative analysis method, aiming to make heatmap evaluation more objective, scalable, and user-friendly.
Heatmaps have been instrumental in helping understand deep network decisions, and are a common approach for Explainable AI (XAI). While significant progress has been made in enhancing the informativeness and accessibility of heatmaps, heatmap analysis is typically very subjective and limited to domain experts. As such, developing automatic, scalable, and numerical analysis methods to make heatmap-based XAI more objective, end-user friendly, and cost-effective is vital. In addition, there is a need for comprehensive evaluation metrics to assess heatmap quality at a granular level.