Investigating the Relationship Between Debiasing and Artifact Removal using Saliency Maps

Fuente: arXiv
Salvato in:
Dettagli Bibliografici
Autori principali: Sztukiewicz, Lukasz, Stępka, Ignacy, Wiliński, Michał, Stefanowski, Jerzy
Natura: Preprint
Pubblicazione: 2025
Soggetti:
Accesso online:
Tags: Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
_version_ 1866912343780229120
author Sztukiewicz, Lukasz
Stępka, Ignacy
Wiliński, Michał
Stefanowski, Jerzy
author_facet Sztukiewicz, Lukasz
Stępka, Ignacy
Wiliński, Michał
Stefanowski, Jerzy
contents The widespread adoption of machine learning systems has raised critical concerns about fairness and bias, making mitigating harmful biases essential for AI development. In this paper, we investigate the relationship between debiasing and removing artifacts in neural networks for computer vision tasks. First, we introduce a set of novel XAI-based metrics that analyze saliency maps to assess shifts in a model's decision-making process. Then, we demonstrate that successful debiasing methods systematically redirect model focus away from protected attributes. Finally, we show that techniques originally developed for artifact removal can be effectively repurposed for improving fairness. These findings provide evidence for the existence of a bidirectional connection between ensuring fairness and removing artifacts corresponding to protected attributes.
format Preprint
id arxiv_https___arxiv_org_abs_2503_00234
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle Investigating the Relationship Between Debiasing and Artifact Removal using Saliency Maps
Sztukiewicz, Lukasz
Stępka, Ignacy
Wiliński, Michał
Stefanowski, Jerzy
Machine Learning
Artificial Intelligence
Computers and Society
The widespread adoption of machine learning systems has raised critical concerns about fairness and bias, making mitigating harmful biases essential for AI development. In this paper, we investigate the relationship between debiasing and removing artifacts in neural networks for computer vision tasks. First, we introduce a set of novel XAI-based metrics that analyze saliency maps to assess shifts in a model's decision-making process. Then, we demonstrate that successful debiasing methods systematically redirect model focus away from protected attributes. Finally, we show that techniques originally developed for artifact removal can be effectively repurposed for improving fairness. These findings provide evidence for the existence of a bidirectional connection between ensuring fairness and removing artifacts corresponding to protected attributes.
title Investigating the Relationship Between Debiasing and Artifact Removal using Saliency Maps
topic Machine Learning
Artificial Intelligence
Computers and Society
url https://arxiv.org/abs/2503.00234