Evaluation of Saliency-based Explainability Method

Autor:	Samuel, Sam Zabdiel Sunder, Kamakshi, Vidhya, Lodhi, Namrata, Krishnan, Narayanan C
Rok vydání:	2021
Předmět:	Computer Science - Machine Learning
Druh dokumentu:	Working Paper
Popis:	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. Comment: Accepted at the ICML Workshop on Theoretic Foundation, Criticism, and Application Trend of Explainable AI, 2021
Databáze:	arXiv
Externí odkaz:	http://arxiv.org/abs/2106.12773 Zobrazit plný text záznamu View this record from Arxiv