Mean Opinion Score as a New Metric for User-Evaluation of XAI Methods

TL;DR

This paper explores using Mean Opinion Score (MOS), a user-centric metric, to evaluate XAI explanation methods, comparing it with automatic metrics and analyzing their correlation through user experiments.

Contribution

It introduces MOS as a novel user-centric evaluation metric for XAI methods and compares its effectiveness with existing automatic metrics.

Findings

MOS correlates highly with IAUC and DAUC for MLFEM

Limited overall correlation between user-centric and automatic metrics

Highlights need for better alignment between automatic and user evaluations

Abstract

This paper investigates the use of Mean Opinion Score (MOS), a common image quality metric, as a user-centric evaluation metric for XAI post-hoc explainers. To measure the MOS, a user experiment is proposed, which has been conducted with explanation maps of intentionally distorted images. Three methods from the family of feature attribution methods - Gradient-weighted Class Activation Mapping (Grad-CAM), Multi-Layered Feature Explanation Method (MLFEM), and Feature Explanation Method (FEM) - are compared with this metric. Additionally, the correlation of this new user-centric metric with automatic metrics is studied via Spearman's rank correlation coefficient. MOS of MLFEM shows the highest correlation with automatic metrics of Insertion Area Under Curve (IAUC) and Deletion Area Under Curve (DAUC). However, the overall correlations are limited, which highlights the lack of consensus between automatic and user-centric metrics.