Addressing Bias In Vlms For Glaucoma Detection Without Protected Attribute Supervision

Abstract

Vision-Language Models (VLMs) have achieved remarkable success on multimodal tasks such as image-text retrieval and zero-shot classification, yet they can exhibit demographic biases even when explicit protected attributes are absent during training. In this work, we focus on automated glaucoma screening from retinal fundus images, a critical application given that glaucoma is a leading cause of irreversible blindness and disproportionately affects underserved populations. Building on a reweighting-based contrastive learning framework, we introduce an attribute-agnostic debiasing method that (i) infers proxy subgroups via unsupervised clustering of image-image embeddings, (ii) computes gradient-similarity weights between the CLIP-style multimodal loss and a SimCLR-style image-pair contrastive loss, and (iii) applies these weights in a joint, top-\(k\) weighted objective to upweight underperforming clusters. This label-free approach adaptively targets the hardest examples, thereby reduci

Stats

• citations0
• S2 citations—
• github stars0
• HF likes0
• heat score0.00
• arxiv keyakash2025addressing

Related papers

• Bendvlm: Test-time Debiasing Of Vision-language Embeddings (2024)4.52
• Vision-language Modelling For Radiological Imaging And Reports In The Low Data Regime (2023)0.00
• Fairclip: Social Bias Elimination Based On Attribute Prototype Learning And Representation Neutralization (2022)0.00
• Efficient Medical Vision-language Alignment Through Adapting Masked Vision Models (2025)5.74
• A Multimodal Recaptioning Framework To Account For Perceptual Diversity Across Languages In Vision-language Modeling (2025)0.00
• Advancing Myopia To Holism: Fully Contrastive Language-image Pre-training (2024)0.00
• Blind To Position, Biased In Language: Probing Mid-layer Representational Bias In Vision-language Encoders For Zero-shot Language-grounded Spatial Understanding (2025)0.00
• Mitigating Test-time Bias For Fair Image Retrieval (2023)0.00