FM-G-CAM: A Holistic Approach for Explainable AI in Computer Vision

TL;DR

This paper introduces FM-G-CAM, a comprehensive method for explaining CNN predictions in computer vision by considering multiple top classes, and provides an open-source implementation for practical use.

Contribution

The paper proposes FM-G-CAM, a novel holistic explanation technique for CNNs that accounts for multiple classes, enhancing interpretability over existing single-class methods.

Findings

FM-G-CAM considers multiple top-predicted classes for explanations.

Quantitative and qualitative comparisons show FM-G-CAM's benefits over Grad-CAM.

An open-source Python library for FM-G-CAM is provided.

Abstract

Explainability is a vital aspect of modern AI for real-world impact and usability. The main objective of this paper is to emphasise the need to understand the predictions of Computer Vision models, specifically Convolutional Neural Network (CNN) models. Existing methods for explaining CNN predictions are largely based on Gradient-weighted Class Activation Maps (Grad-CAM) and focus solely on a single target class; this assumption about the target class selection neglects a large portion of the predictor CNN's prediction process. In this paper, we present an exhaustive methodology, called Fused Multi-class Gradient-weighted Class Activation Map (FM-G-CAM), that considers multiple top-predicted classes and provides a holistic explanation of the predictor CNN's rationale. We also provide a detailed mathematical and algorithmic description of our method. Furthermore, alongside a concise comparison of existing methods, we compare FM-G-CAM with Grad-CAM, quantitatively and qualitatively highlighting its benefits through real-world practical use cases. Finally, we present an open-source Python library with an FM-G-CAM implementation to conveniently generate saliency maps for CNN-based model predictions.