BOREx: Bayesian-Optimization--Based Refinement of Saliency Map for Image- and Video-Classification Models

TL;DR

BOREx is a black-box method that refines existing heat maps for image and video classification explanations using Bayesian optimization, significantly improving their quality.

Contribution

It introduces BOREx, a novel Bayesian optimization-based approach that refines heat maps from any explanation method, enhancing their accuracy in visual model explanations.

Findings

BOREx improves the quality of heat maps for image classification.

BOREx enhances explanation accuracy for video classification.

Statistical evidence shows significant refinement benefits.

Abstract

Explaining a classification result produced by an image- and video-classification model is one of the important but challenging issues in computer vision. Many methods have been proposed for producing heat-map--based explanations for this purpose, including ones based on the white-box approach that uses the internal information of a model (e.g., LRP, Grad-CAM, and Grad-CAM++) and ones based on the black-box approach that does not use any internal information (e.g., LIME, SHAP, and RISE). We propose a new black-box method BOREx (Bayesian Optimization for Refinement of visual model Explanation) to refine a heat map produced by any method. Our observation is that a heat-map--based explanation can be seen as a prior for an explanation method based on Bayesian optimization. Based on this observation, BOREx conducts Gaussian process regression (GPR) to estimate the saliency of each pixel in a given image starting from the one produced by another explanation method. Our experiments statistically demonstrate that the refinement by BOREx improves low-quality heat maps for image- and video-classification results.