Improving Deep Neural Network Classification Confidence using Heatmap-based eXplainable AI
This work addresses the need for reliable XAI methods to boost trust in deep neural network predictions, particularly in critical domains like medical imaging, though it is incremental in refining existing heatmap techniques.
The paper tackles the problem of quantifying heatmap-based explainable AI (XAI) methods for image classification by assessing their ability to improve classification confidence, showing that methods like Saliency and Deconvolution enhance confidence to varying extents across datasets such as ImageNet and Chest X-Ray Pneumonia.
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.