This paper quantifies the quality of heatmap-based eXplainable AI (XAI) methods w.r.t image classification problem. Here, a heatmap is considered desirable if it improves the probability of predicting the correct classes. Different XAI heatmap-based methods are empirically shown to improve classification confidence to different extents depending on the datasets, e.g. Saliency works best on ImageNet and Deconvolution on Chest X-Ray Pneumonia dataset. The novelty includes a new gap distribution that shows a stark difference between correct and wrong predictions. Finally, the generative augmentative explanation is introduced, a method to generate heatmaps capable of improving predictive confidence to a high level.
@article{arxiv.2201.00009,
title = {Improving Deep Neural Network Classification Confidence using Heatmap-based eXplainable AI},
author = {Erico Tjoa and Hong Jing Khok and Tushar Chouhan and Guan Cuntai},
journal= {arXiv preprint arXiv:2201.00009},
year = {2023}
}