FairEnc通过双模态联合去偏，提升眼科疾病检测的公平性。
FairEnc: A Fair Vision-Language Model with Fair Vision and Text Encoders for Glaucoma Detection
- 用大模型生成带不同属性的合成病历，保持疾病语义同时减少文本偏见。
- 视觉编码器结合互信息正则与多判别器对抗训练，降低特征与人口属性关联。
- 在多个数据集上验证，跨域跨模态仍保持公平性且诊断性能优异。
自动化青光眼检测对预防不可逆视力丧失和减轻医疗系统负担至关重要。然而，在多样化患者群体中保障公平性仍是重大挑战。本文提出 FairEnc，一种面向视觉-语言模型（VLMs）的公平预训练方法，可同时缓解多种敏感属性（包括种族、性别、族裔和语言）带来的偏见。对于文本编码器，利用大语言模型生成带有不同敏感属性的合成临床描述，同时保留疾病语义，并采用对比对齐目标促使表征与人口属性无关。对于视觉编码器，提出双层公平策略：结合互信息正则化以减少学习特征与人群组之间的统计依赖，并使用多判别器对抗去偏。在公开的 Harvard-FairVLMed 数据集上的全面实验表明，FairEnc 显著降低了基于 DPD 与 DEOdds 的人口差异，同时在零样本和线性探测评估中均表现良好。在私有数据集 FairFundus 上的额外实验显示，FairEnc 在跨域与跨模态设置下仍能持续保持公平优势，且诊断性能处于竞争范围。结果表明 FairEnc 具备在分布偏移下的公平性泛化能力，支持其在真实临床场景中的更公平部署。代码与合成病历数据已开源。
原文摘要 · Abstract (English)
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
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。