Revisiting The Evaluation of Class Activation Mapping for Explainability: A Novel Metric and Experimental Analysis
This work addresses the need for improved evaluation and reproducibility of visualization techniques for explainability in deep learning, though it is incremental as it builds on existing CAM methods.
The paper tackles the problem of evaluating Class Activation Mapping (CAM) approaches for explainability in deep learning by proposing a novel set of metrics to quantify explanation maps, resulting in better effectiveness and simplified comparisons as demonstrated on the ImageNet validation set.
As the request for deep learning solutions increases, the need for explainability is even more fundamental. In this setting, particular attention has been given to visualization techniques, that try to attribute the right relevance to each input pixel with respect to the output of the network. In this paper, we focus on Class Activation Mapping (CAM) approaches, which provide an effective visualization by taking weighted averages of the activation maps. To enhance the evaluation and the reproducibility of such approaches, we propose a novel set of metrics to quantify explanation maps, which show better effectiveness and simplify comparisons between approaches. To evaluate the appropriateness of the proposal, we compare different CAM-based visualization methods on the entire ImageNet validation set, fostering proper comparisons and reproducibility.