The reviewed record of science sign in
Pith

arxiv: 2508.09087 · v1 · pith:BD37IPQ5 · submitted 2025-08-12 · cs.CV

Addressing Bias in VLMs for Glaucoma Detection Without Protected Attribute Supervision

Reviewed by Pith T0 review T1 audit T2 compute T3 formal T4 kernel pith:BD37IPQ5record.jsonopen to challenge →

classification cs.CV
keywords glaucomacontrastivedemographicequalizedlossmethodmultimodalprotected
0
0 comments X
read the original 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 reducing subgroup disparities. We evaluate our method on the Harvard FairVLMed glaucoma subset, reporting Equalized Odds Distance (EOD), Equalized Subgroup AUC (ES AUC), and Groupwise AUC to demonstrate equitable performance across inferred demographic subgroups.

This paper has not been read by Pith yet.

discussion (0)

Sign in with ORCID, Apple, or X to comment. Anyone can read and Pith papers without signing in.