SIDU: Similarity Difference and Uniqueness Method for Explainable AI

TL;DR

This paper introduces SIDU, a novel visual explanation method for deep learning that produces saliency maps to localize objects, enhancing interpretability and trust in AI models through comprehensive evaluations.

Contribution

The paper presents SIDU, a new explainability technique that improves object localization in saliency maps, outperforming existing methods in clarity and trustworthiness.

Findings

Effective localization of object regions in saliency maps.

Enhanced trust in AI explanations demonstrated through evaluations.

Promising results on both general and clinical datasets.

Abstract

A new brand of technical artificial intelligence ( Explainable AI ) research has focused on trying to open up the 'black box' and provide some explainability. This paper presents a novel visual explanation method for deep learning networks in the form of a saliency map that can effectively localize entire object regions. In contrast to the current state-of-the art methods, the proposed method shows quite promising visual explanations that can gain greater trust of human expert. Both quantitative and qualitative evaluations are carried out on both general and clinical data sets to confirm the effectiveness of the proposed method.