DetoxAI: a Python Toolkit for Debiasing Deep Learning Models in Computer Vision
This provides a domain-specific solution for improving fairness in vision-based classification tasks, which is incremental as it adapts existing fairness methods to a new data type.
The authors tackled the lack of fairness tools for deep learning in computer vision by introducing DetoxAI, an open-source Python toolkit that implements post-hoc debiasing algorithms, fairness metrics, and visualization tools, resulting in a practical resource for engineers and researchers.
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.