TbExplain: A Text-based Explanation Method for Scene Classification Models with the Statistical Prediction Correction

TL;DR

TbExplain introduces a text-based explanation framework for scene classification models that enhances interpretability and prediction reliability using object detection and statistical correction, improving accuracy and trustworthiness.

Contribution

The paper presents a novel text-based explanation method for scene classification that combines XAI techniques with statistical prediction correction, addressing heatmap interpretability issues.

Findings

Text explanations are deemed sufficiently reliable by qualitative assessment.

The method improves classification accuracy over ResNet models.

The framework enhances interpretability for non-expert users.

Abstract

The field of Explainable Artificial Intelligence (XAI) aims to improve the interpretability of black-box machine learning models. Building a heatmap based on the importance value of input features is a popular method for explaining the underlying functions of such models in producing their predictions. Heatmaps are almost understandable to humans, yet they are not without flaws. Non-expert users, for example, may not fully understand the logic of heatmaps (the logic in which relevant pixels to the model's prediction are highlighted with different intensities or colors). Additionally, objects and regions of the input image that are relevant to the model prediction are frequently not entirely differentiated by heatmaps. In this paper, we propose a framework called TbExplain that employs XAI techniques and a pre-trained object detector to present text-based explanations of scene classification models. Moreover, TbExplain incorporates a novel method to correct predictions and textually explain them based on the statistics of objects in the input image when the initial prediction is unreliable. To assess the trustworthiness and validity of the text-based explanations, we conducted a qualitative experiment, and the findings indicated that these explanations are sufficiently reliable. Furthermore, our quantitative and qualitative experiments on TbExplain with scene classification datasets reveal an improvement in classification accuracy over ResNet variants.