A Model-agnostic Approach for Generating Saliency Maps to Explain Inferred Decisions of Deep Learning Models

Savvas Karatsiolis, Andreas Kamilaris, Andreas Kamilaris

2023

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. 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.

Paper Citation

in Harvard Style

Karatsiolis S. and Kamilaris A. (2023). A Model-agnostic Approach for Generating Saliency Maps to Explain Inferred Decisions of Deep Learning Models. In Proceedings of the 18th International Joint Conference on Computer Vision, Imaging and Computer Graphics Theory and Applications (VISIGRAPP 2023) - Volume 4: VISAPP; ISBN 978-989-758-634-7, SciTePress, pages 39-46. DOI: 10.5220/0011612400003417

in Bibtex Style

@conference{visapp23,
author={Savvas Karatsiolis and Andreas Kamilaris},
title={A Model-agnostic Approach for Generating Saliency Maps to Explain Inferred Decisions of Deep Learning Models},
booktitle={Proceedings of the 18th International Joint Conference on Computer Vision, Imaging and Computer Graphics Theory and Applications (VISIGRAPP 2023) - Volume 4: VISAPP},
year={2023},
pages={39-46},
publisher={SciTePress},
organization={INSTICC},
doi={10.5220/0011612400003417},
isbn={978-989-758-634-7},
}

in EndNote Style

TY - CONF

JO - Proceedings of the 18th International Joint Conference on Computer Vision, Imaging and Computer Graphics Theory and Applications (VISIGRAPP 2023) - Volume 4: VISAPP
TI - A Model-agnostic Approach for Generating Saliency Maps to Explain Inferred Decisions of Deep Learning Models
SN - 978-989-758-634-7
AU - Karatsiolis S.
AU - Kamilaris A.
PY - 2023
SP - 39
EP - 46
DO - 10.5220/0011612400003417
PB - SciTePress