AdFair-CLIP: Adversarial Fair Contrastive Language-Image Pre-training for Chest X-rays
Not on the map. Why?
Abstract (arXiv)
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.
Key facts. Cited by 2 papers in the map (data through 14 Oct 2026). Builds on 24 of its 33 references that are in the map. First posted on arXiv 30 Jun 2025.
Builds on
24 of 33 references.
References · 24
- 2015Deep Residual Learning for Image Recognitioncited by 52,096
- 2014Adam: A Method for Stochastic Optimizationcited by 37,240
- 2021Learning Transferable Visual Models From Natural Language Supervisioncited by 33,744
- 2018Representation Learning with Contrastive Predictive Codingcited by 7,777
- 2015Domain-Adversarial Training of Neural Networkscited by 3,044
- 2019CheXpert: A Large Chest Radiograph Dataset with Uncertainty Labels and Expert Comparisoncited by 1,423
- 2019Publicly Available Clinical BERT Embeddingscited by 1,002
- 2020Contrastive Learning of Medical Visual Representations from Paired Images and Textcited by 641
- 2018A Reductions Approach to Fair Classificationcited by 587
- 2022MedCLIP: Contrastive Learning from Unpaired Medical Images and Textcited by 570
- 2023BiomedCLIP: a multimodal biomedical foundation model pretrained from fifteen million scientific image-text pairscited by 520
- 2020CheXclusion: Fairness gaps in deep chest X-ray classifierscited by 153
12 more
- 2019Fairness in Recommendation Ranking through Pairwise Comparisonscited by 127
- 2024CheXpert Plus: Augmenting a Large Chest X-ray Dataset with Text Radiology Reports, Patient Demographics and Additional Image Formatscited by 106
- 2022A Prompt Array Keeps the Bias Away: Debiasing Vision-Language Models with Adversarial Learningcited by 104
- 2021Are Gender-Neutral Queries Really Gender-Neutral? Mitigating Gender Bias in Image Searchcited by 90
- 2023CXR-CLIP: Toward Large Scale Chest X-ray Language-Image Pre-trainingcited by 82
- 2024FairCLIP: Harnessing Fairness in Vision-Language Learningcited by 69
- 2022Improving the Fairness of Chest X-ray Classifierscited by 52
- 2024FairMedFM: Fairness Benchmarking for Medical Imaging Foundation Modelscited by 47
- 2023CLIPSyntel: CLIP and LLM Synergy for Multimodal Question Summarization in Healthcarecited by 43
- 2019A Simple and Effective Framework for Pairwise Deep Metric Learningcited by 13
- 2022Stochastic Methods for AUC Optimization subject to AUC-based Fairness Constraintscited by 9
- 2024Provable Optimization for Adversarial Fair Self-supervised Contrastive Learningcited by 2
Built on by
Citing papers per year: 2026: 2.
2 papers.