DetoxAI: a Python Toolkit for Debiasing Deep Learning Models in Computer Vision
Fuente:
arXiv
Saved in:
| Main Authors: | , , , |
|---|---|
| Format: | Preprint |
| Published: |
2025
|
| Subjects: | |
| Online Access: | |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866918014322999296 |
|---|---|
| author | Stępka, Ignacy Sztukiewicz, Lukasz Wiliński, Michał Stefanowski, Jerzy |
| author_facet | Stępka, Ignacy Sztukiewicz, Lukasz Wiliński, Michał Stefanowski, Jerzy |
| contents | 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. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2505_05492 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | DetoxAI: a Python Toolkit for Debiasing Deep Learning Models in Computer Vision Stępka, Ignacy Sztukiewicz, Lukasz Wiliński, Michał Stefanowski, Jerzy Computer Vision and Pattern Recognition Artificial Intelligence Machine Learning 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. |
| title | DetoxAI: a Python Toolkit for Debiasing Deep Learning Models in Computer Vision |
| topic | Computer Vision and Pattern Recognition Artificial Intelligence Machine Learning |
| url | https://arxiv.org/abs/2505.05492 |