A model-agnostic approach for generating Saliency Maps to explain inferred decisions of Deep Learning Models

TL;DR

This paper introduces a model-agnostic method using Differential Evolution to generate saliency maps for deep learning models, providing explanations without needing internal model details, suitable for complex applications like computer vision.

Contribution

The paper presents a novel, model-agnostic approach for generating saliency maps using Differential Evolution, eliminating the need for internal model information.

Findings

DE-CAM produces high-quality class activation maps

Method is effective without access to model internals

Achieves comparable results to model-specific algorithms

Abstract

The widespread use of black-box AI models has raised the need for algorithms and methods that explain the decisions made by these models. In recent years, the AI research community is increasingly interested in models' explainability since black-box models take over more and more complicated and challenging tasks. Explainability becomes critical considering the dominance of deep learning techniques for a wide range of applications, including but not limited to computer vision. In the direction of understanding the inference process of deep learning models, many methods that provide human comprehensible evidence for the decisions of AI models have been developed, with the vast majority relying their operation on having access to the internal architecture and parameters of these models (e.g., the weights of neural networks). We propose a model-agnostic method for generating saliency maps that has access only to the output of the model and does not require additional information such as gradients. We use Differential Evolution (DE) to identify which image pixels are the most influential in a model's decision-making process and produce class activation maps (CAMs) whose quality is comparable to the quality of CAMs created with model-specific algorithms. DE-CAM achieves good performance without requiring access to the internal details of the model's architecture at the cost of more computational complexity.