AdFair-CLIP: Adversarial Fair Contrastive Language-Image Pre-training for Chest X-rays

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Yi, Chenlang, Xiong, Zizhan, Qi, Qi, Wei, Xiyuan, Bathla, Girish, Lin, Ching-Long, Mortazavi, Bobak Jack, Yang, Tianbao
Format: Preprint
Published: 2025
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866908623717793792
author Yi, Chenlang
Xiong, Zizhan
Qi, Qi
Wei, Xiyuan
Bathla, Girish
Lin, Ching-Long
Mortazavi, Bobak Jack
Yang, Tianbao
author_facet Yi, Chenlang
Xiong, Zizhan
Qi, Qi
Wei, Xiyuan
Bathla, Girish
Lin, Ching-Long
Mortazavi, Bobak Jack
Yang, Tianbao
contents Contrastive Language-Image Pre-training (CLIP) models have demonstrated superior performance across various visual tasks including medical image classification. However, fairness concerns, including demographic biases, have received limited attention for CLIP models. This oversight leads to critical issues, particularly those related to race and gender, resulting in disparities in diagnostic outcomes and reduced reliability for underrepresented groups. To address these challenges, we introduce AdFair-CLIP, a novel framework employing adversarial feature intervention to suppress sensitive attributes, thereby mitigating spurious correlations and improving prediction fairness. We conduct comprehensive experiments on chest X-ray (CXR) datasets, and show that AdFair-CLIP significantly enhances both fairness and diagnostic accuracy, while maintaining robust generalization in zero-shot and few-shot scenarios. These results establish new benchmarks for fairness-aware learning in CLIP-based medical diagnostic models, particularly for CXR analysis.
format Preprint
id arxiv_https___arxiv_org_abs_2506_23467
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle AdFair-CLIP: Adversarial Fair Contrastive Language-Image Pre-training for Chest X-rays
Yi, Chenlang
Xiong, Zizhan
Qi, Qi
Wei, Xiyuan
Bathla, Girish
Lin, Ching-Long
Mortazavi, Bobak Jack
Yang, Tianbao
Computer Vision and Pattern Recognition
Machine Learning
Contrastive Language-Image Pre-training (CLIP) models have demonstrated superior performance across various visual tasks including medical image classification. However, fairness concerns, including demographic biases, have received limited attention for CLIP models. This oversight leads to critical issues, particularly those related to race and gender, resulting in disparities in diagnostic outcomes and reduced reliability for underrepresented groups. To address these challenges, we introduce AdFair-CLIP, a novel framework employing adversarial feature intervention to suppress sensitive attributes, thereby mitigating spurious correlations and improving prediction fairness. We conduct comprehensive experiments on chest X-ray (CXR) datasets, and show that AdFair-CLIP significantly enhances both fairness and diagnostic accuracy, while maintaining robust generalization in zero-shot and few-shot scenarios. These results establish new benchmarks for fairness-aware learning in CLIP-based medical diagnostic models, particularly for CXR analysis.
title AdFair-CLIP: Adversarial Fair Contrastive Language-Image Pre-training for Chest X-rays
topic Computer Vision and Pattern Recognition
Machine Learning
url https://arxiv.org/abs/2506.23467