Paper ID: 2405.13264

Part-based Quantitative Analysis for Heatmaps

Osman Tursun, Sinan Kalkan, Simon Denman, Sridha Sridharan, Clinton Fookes

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.

Submitted: May 22, 2024