Improving Deep Neural Network Classification Confidence using Heatmap-based eXplainable AI

2021/12/30 by Erico Tjoa, Hong Jing Khok, Tjoa, Erico +4
Computer Science · Medicine · #Artificial Intelligence (cs.AI) #COVID-19 diagnosis using AI #Explainable Artificial Intelligence (XAI) #FOS: Computer and information sciences #Machine Learning (cs.LG) #Machine Learning in Healthcare

paper · pdf · doi:10.48550/arxiv.2201.00009

openalex publication_date 2021/12/30 · openalex created_date 2022/05/05 · openalex updated_date 2026/07/28

Abstract

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.

Related

• Quantifying Explainability of Saliency Methods in Deep Neural Networks with a Synthetic Dataset
• Improving Disease Classification Performance and Explainability of Deep Learning Models in Radiology with Heatmap Generators
• Embedded Encoder-Decoder in Convolutional Networks Towards Explainable AI
• Deep Learning Reproducibility and Explainable AI (XAI)
• A Comparative Study of Explainable AI Methods: Model-Agnostic vs. Model-Specific Approaches