arXiv cs.CY· Lisa Y. W. Tang·· 13 小时前AI 评分22
双眼中一：面向资源受限筛查的特权学习框架
Two for One: Privileged Learning for Resource-Constrained Screening
AI 导读
研究提出一种特权学习框架，训练时教师模型可使用双眼彩色眼底照片（CFP），学生模型仅以单眼图像为输入学习迁移双眼知识，推理阶段无需对侧图像。在年龄相关性黄斑变性检测上，左眼图像 AUC 从 0.931 提升至 0.966；糖尿病视网膜病变从 0.789 提升至 0.836。该方法有望支持资源受限临床与筛查环境中的更可靠部署。
正文 · 原文
Abstract:Machine learning systems are often developed under data-rich conditions but deployed when only incomplete information is available. A natural example arises in colour fundus photography (CFP), where both eyes are commonly imaged because they can provide complementary information for ocular disease assessment. Prior approaches that exploit bilateral information either fuse both eyes in a single model or use knowledge distillation to compress a dual-eye teacher into a lightweight student that still requires both images at test time. However, bilateral acquisition may not always be feasible. We thus propose a privileged learning framework in which a teacher model has access to bilateral CFP images during training and learns representations informed by information from both eyes, while the student is trained to transfer this knowledge from the bilateral teacher using only a single-eye image as input. At inference, the student operates exclusively on this single-eye input and does not require the contralateral image. Experimental results show consistent improvements in area under the receiver operating characteristic curve over conventional monocular training, with the largest gains observed for left-eye images for the detection of age-related macular degeneration (0.931 vs. 0.966) and diabetic retinopathy (0.789 vs. 0.836).%, while requiring only a single-eye image at inference. By enabling models to benefit from bilateral information during training while requiring only a single-eye image at inference, our approach may support more reliable deployment in resource-constrained clinical and screening environments.
| Subjects: | Computer Vision and Pattern Recognition (cs.CV); Computers and Society (cs.CY) |
| Cite as: | arXiv:2610.29126 [cs.CV] |
| (or arXiv:2610.29126v1 [cs.CV] for this version) | |
| https://doi.org/10.48550/arXiv.2610.29126 arXiv-issued DOI via DataCite (pending registration) |
Submission history
From: Lisa Y.W. Tang [view email]
[v1]
Wed, 21 Oct 2026 03:09:41 UTC (59 KB)
来源：arXiv cs.CY · arxiv.org