Segmentation and Smoothing Affect Explanation Quality More Than the Choice of Perturbation-based XAI Method for Image Explanations

TL;DR

This study demonstrates that segmentation and smoothing parameters significantly influence the quality of image explanations more than the choice of perturbation-based explanation method, using RISE as a baseline.

Contribution

It systematically evaluates how different parameters affect perturbation-based image explanations, highlighting the importance of segmentation and smoothing over attribution calculation.

Findings

Segmentation and smoothing greatly impact explanation quality.

Attribution calculation has minimal effect on results.

Parameter choices overshadow method selection in explanation performance.

Abstract

Perturbation-based post-hoc image explanation methods are commonly used to explain image prediction models. These methods perturb parts of the input to measure how those parts affect the output. Since the methods only require the input and output, they can be applied to any model, making them a popular choice to explain black-box models. While many different methods exist and have been compared with one another, it remains poorly understood which parameters of the different methods are responsible for their varying performance. This work uses the Randomized Input Sampling for Explanations (RISE) method as a baseline to evaluate many combinations of mask sampling, segmentation techniques, smoothing, attribution calculation, and per-segment or per-pixel attribution, using a proxy metric. The results show that attribution calculation, which is frequently the focus of other works, has little impact on the results. Conversely, segmentation and per-pixel attribution, rarely examined parameters, have a significant impact. The implementation of and data gathered in this work are available online: https://github.com/guspih/post-hoc-image-perturbation and https://bit.ly/smooth-mask-perturbation.