DetoxAI: a Python Toolkit for Debiasing Deep Learning Models in Computer Vision

TL;DR

DetoxAI is an open-source Python toolkit designed to improve fairness in deep learning vision classifiers through post-hoc debiasing, visualization, and fairness metrics, addressing a gap in existing fairness solutions for vision tasks.

Contribution

We introduce DetoxAI, a comprehensive library implementing state-of-the-art debiasing algorithms and visualization tools specifically for deep learning in computer vision.

Findings

DetoxAI effectively reduces bias in vision classifiers.

The toolkit provides quantitative metrics to evaluate fairness improvements.

Visualization tools help interpret bias mitigation results.

Abstract

While machine learning fairness has made significant progress in recent years, most existing solutions focus on tabular data and are poorly suited for vision-based classification tasks, which rely heavily on deep learning. To bridge this gap, we introduce DetoxAI, an open-source Python library for improving fairness in deep learning vision classifiers through post-hoc debiasing. DetoxAI implements state-of-the-art debiasing algorithms, fairness metrics, and visualization tools. It supports debiasing via interventions in internal representations and includes attribution-based visualization tools and quantitative algorithmic fairness metrics to show how bias is mitigated. This paper presents the motivation, design, and use cases of DetoxAI, demonstrating its tangible value to engineers and researchers.