Evaluation of Saliency-based Explainability Method

Authors:
  • SSSam Zabdiel Sunder Samuel
    Sam Zabdiel Sunder Samuel
  • VKVidhya Kamakshi
    Vidhya Kamakshi
  • NLNamrata Lodhi
    Namrata Lodhi
  • NKNarayanan C Krishnan
    Narayanan C Krishnan
Preprint
Publisher website
Google Scholar
Abstract
A particular class of Explainable AI (XAI) methods provide saliency maps to highlight part of the image a Convolutional Neural Network (CNN) model looks at to classify the image as a way to explain its working. These methods provide an intuitive way for users to understand predictions made by CNNs. Other than quantitative computational tests, the vast majority of evidence to highlight that the methods are valuable is anecdotal. Given that humans would be the end-users of such methods, we devise three human subject experiments through which we gauge the effectiveness of these saliency-based explainability methods.
All Related Versions