Fairness Analysis of CLIP-Based Foundation Models for X-Ray Image Classification

Fuente: arXiv
Salvato in:
Dettagli Bibliografici
Autori principali: Sun, Xiangyu, Zou, Xiaoguang, Wu, Yuanquan, Wang, Guotai, Zhang, Shaoting
Natura: Preprint
Pubblicazione: 2025
Soggetti:
Accesso online:
Tags: Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
_version_ 1866916592224305152
author Sun, Xiangyu
Zou, Xiaoguang
Wu, Yuanquan
Wang, Guotai
Zhang, Shaoting
author_facet Sun, Xiangyu
Zou, Xiaoguang
Wu, Yuanquan
Wang, Guotai
Zhang, Shaoting
contents X-ray imaging is pivotal in medical diagnostics, offering non-invasive insights into a range of health conditions. Recently, vision-language models, such as the Contrastive Language-Image Pretraining (CLIP) model, have demonstrated potential in improving diagnostic accuracy by leveraging large-scale image-text datasets. However, since CLIP was not initially designed for medical images, several CLIP-like models trained specifically on medical images have been developed. Despite their enhanced performance, issues of fairness - particularly regarding demographic attributes - remain largely unaddressed. In this study, we perform a comprehensive fairness analysis of CLIP-like models applied to X-ray image classification. We assess their performance and fairness across diverse patient demographics and disease categories using zero-shot inference and various fine-tuning techniques, including Linear Probing, Multilayer Perceptron (MLP), Low-Rank Adaptation (LoRA), and full fine-tuning. Our results indicate that while fine-tuning improves model accuracy, fairness concerns persist, highlighting the need for further fairness interventions in these foundational models.
format Preprint
id arxiv_https___arxiv_org_abs_2501_19086
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle Fairness Analysis of CLIP-Based Foundation Models for X-Ray Image Classification
Sun, Xiangyu
Zou, Xiaoguang
Wu, Yuanquan
Wang, Guotai
Zhang, Shaoting
Computer Vision and Pattern Recognition
Artificial Intelligence
X-ray imaging is pivotal in medical diagnostics, offering non-invasive insights into a range of health conditions. Recently, vision-language models, such as the Contrastive Language-Image Pretraining (CLIP) model, have demonstrated potential in improving diagnostic accuracy by leveraging large-scale image-text datasets. However, since CLIP was not initially designed for medical images, several CLIP-like models trained specifically on medical images have been developed. Despite their enhanced performance, issues of fairness - particularly regarding demographic attributes - remain largely unaddressed. In this study, we perform a comprehensive fairness analysis of CLIP-like models applied to X-ray image classification. We assess their performance and fairness across diverse patient demographics and disease categories using zero-shot inference and various fine-tuning techniques, including Linear Probing, Multilayer Perceptron (MLP), Low-Rank Adaptation (LoRA), and full fine-tuning. Our results indicate that while fine-tuning improves model accuracy, fairness concerns persist, highlighting the need for further fairness interventions in these foundational models.
title Fairness Analysis of CLIP-Based Foundation Models for X-Ray Image Classification
topic Computer Vision and Pattern Recognition
Artificial Intelligence
url https://arxiv.org/abs/2501.19086