mlsanityData to 7 Oct 2026

FairEnc: A Fair Vision-Language Model with Fair Vision and Text Encoders for Glaucoma Detection

arXiv 2605.04882 ↗First posted 6 May 2026cs.CV cs.AI cs.LGcited by 0

On the map: Multimodal LLMs / vision-language models → Medical vision-language models

Abstract (arXiv)

Automated glaucoma detection is critical for preventing irreversible vision loss and reducing the burden on healthcare systems. However, ensuring fairness across diverse patient populations remains a significant challenge. In this paper, we propose FairEnc, a fair pretraining method for vision-language models (VLMs) that enables simultaneous debiasing across multiple sensitive attributes. FairEnc jointly mitigates biases in both textual and visual modalities with respect to multiple sensitive attributes, including race, gender, ethnicity, and language. Specifically, for the textual encoder, we leverage a large language model to generate synthetic clinical descriptions with varied sensitive attributes while preserving disease semantics, and employ a contrastive alignment objective to encourage demographic-invariant representations. For the visual encoder, we propose a dual-level fairness strategy that combines mutual information regularization to reduce statistical dependence between learned features and demographic groups, with multi-discriminator adversarial debiasing. Comprehensive experiments on the publicly available Harvard-FairVLMed dataset demonstrate that FairEnc effectively reduces demographic disparity as measured by DPD and DEOdds while achieving strong diagnostic performance under both zero-shot and linear probing evaluations. Additional experiments on the private FairFundus dataset show that FairEnc consistently preserves fairness advantages under cross-domain and cross-modality settings and maintains diagnostic performance within a competitive range. These results highlight FairEnc's ability to generalize fairness under distribution shifts, supporting its potential for more equitable deployment in real-world clinical settings. Our codebase and synthetic clinical notes are available at https://github.com/Mohamed-Elhabebe/FairEnc

Key facts. No citing papers in the map yet (data through 7 Oct 2026). Placed in Medical vision-language models, one of 16 directions in Multimodal LLMs / vision-language models. Builds on 33 of its 49 references that are in the map. First posted on arXiv 6 May 2026.

Builds on

33 of 49 references.

Closest ancestors · 1

Same direction, newest first

  1. 2025Robust Fairness Vision-Language Learning for Medical Image Analysis6 May

Other references · 32

  1. 2021Learning Transferable Visual Models From Natural Language Supervisioncited by 33,456
  2. 2020An Image is Worth 16x16 Words: Transformers for Image Recognition at Scalecited by 29,915
  3. 2024The Llama 3 Herd of Modelscited by 14,192
  4. 2020A Simple Framework for Contrastive Learning of Visual Representationscited by 11,979
  5. 2025Qwen3 Technical Reportcited by 8,195
  6. 2018Representation Learning with Contrastive Predictive Codingcited by 7,662
  7. 2017Neural Discrete Representation Learningcited by 4,650
  8. 2022BLIP: Bootstrapping Language-Image Pre-training for Unified Vision-Language Understanding and Generationcited by 4,310
  9. 2013Sinkhorn Distances: Lightspeed Computation of Optimal Transportation Distancescited by 2,277
  10. 2023Vision-Language Models for Vision Tasks: A Surveycited by 834
  11. 2018MINE: Mutual Information Neural Estimationcited by 680
  12. 2018Mitigating Unwanted Biases with Adversarial Learningcited by 663
20 more
  1. 2018A Reductions Approach to Fair Classificationcited by 585
  2. 2021Just Train Twice: Improving Group Robustness without Training Group Informationcited by 522
  3. 2020Fairness without Demographics through Adversarially Reweighted Learningcited by 251
  4. 2020CLUB: A Contrastive Log-ratio Upper Bound of Mutual Informationcited by 233
  5. 2019Fair Regression: Quantitative Definitions and Reduction-based Algorithmscited by 168
  6. 2020FairBatch: Batch Selection for Model Fairnesscited by 99
  7. 2024Med42-v2: A Suite of Clinical LLMscited by 89
  8. 2023Simple and Fast Group Robustness by Automatic Feature Reweightingcited by 68
  9. 2022Learning Debiased Classifier with Biased Committeecited by 51
  10. 2021Learning Fair Classifiers with Partially Annotated Group Labelscited by 40
  11. 2023Harvard Glaucoma Fairness: A Retinal Nerve Disease Dataset for Fairness Learning and Fair Identity Normalizationcited by 31
  12. 2023Re-weighting Based Group Fairness Regularization via Classwise Robust Optimizationcited by 20
  13. 2023On Fairness of Medical Image Classification with Multiple Sensitive Attributes via Learning Orthogonal Representationscited by 17
  14. 2019Deep Learning Fundus Image Analysis for Diabetic Retinopathy and Macular Edema Gradingcited by 12
  15. 2024Achieve Fairness without Demographics for Dermatological Disease Diagnosiscited by 10
  16. 2024Efficient Bias Mitigation Without Privileged Informationcited by 8
  17. 2023Mitigating Calibration Bias Without Fixed Attribute Grouping for Improved Fairness in Medical Imaging Analysiscited by 7
  18. 2024FairREAD: Re-fusing Demographic Attributes after Disentanglement for Fair Medical Image Classificationcited by 3
  19. 2024DiffuPT: Class Imbalance Mitigation for Glaucoma Detection via Diffusion Based Generation and Model Pretrainingcited by 1
  20. 2025FairFedMed: Benchmarking Group Fairness in Federated Medical Imaging with FairLoRAcited by 1

Built on by

Not cited yet.

Similar, not cited

Close in wording, no citation either way

  1. 2025Fairness-Aware Fine-Tuning of Vision-Language Models for Medical Glaucoma Diagnosis
  2. 2025Addressing Bias in VLMs for Glaucoma Detection Without Protected Attribute Supervision
  3. 2026FairLLaVA: Fairness-Aware Parameter-Efficient Fine-Tuning for Large Vision-Language Assistants
  4. 2025Toward Robust Medical Fairness: Debiased Dual-Modal Alignment via Text-Guided Attribute-Disentangled Prompt Learning for Vision-Language Models
  5. 2026A Closed-Form Solution for Debiasing Vision-Language Models with Utility Guarantees Across Modalities and Tasks
  6. 2025Intersectional Fairness in Vision-Language Models for Medical Image Disease Classification
  7. 2025Fair-MoE: Fairness-Oriented Mixture of Experts in Vision-Language Models
  8. 2024FairDeDup: Detecting and Mitigating Vision-Language Fairness Disparities in Semantic Dataset Deduplication