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

Abstract

TbExplain is a framework that employs explainable AI (XAI) techniques and a pre-trained object detector to present text-based explanations of scene classification models. It 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, improving both interpretability and robustness.

Publication
In Proceedings of the Conference on Governance, Understanding and Integration of Data for Effective and Responsible AI (GUIDE-AI)
comments powered by Disqus

Related