用知识蒸馏把大模型压缩到嵌入式设备，实现眼底病快速筛查。
Cross-Architecture Knowledge Distillation (KD) for Retinal Fundus Image Anomaly Detection on NVIDIA Jetson Nano
- 跨架构蒸馏：用ViT教师模型指导轻量CNN学生模型。
- 在Jetson Nano上保持93%的诊断准确率，参数量减少97.4%。
- 适合资源匮乏地区部署，可作为基层眼科筛查工具。
早期精准识别视网膜疾病对防止视力衰退至关重要，但低资源地区常缺乏可靠诊断设备。本研究提出一种面向边缘设备的轻量化疾病分类器，采用跨架构知识蒸馏技术。首先使用自监督学习预训练的视觉变换器（ViT）教师模型，在I-JEPA数据集上对眼底图像进行四类分类：正常、糖尿病视网膜病变、青光眼和白内障。为适应资源受限环境（如NVIDIA Jetson Nano），将教师模型压缩为基于CNN的学生模型，采用新型框架，包含分块交叉注意力（PCA）投影器、组内线性（GL）投影器及多视角鲁棒训练方法。教师模型参数量比学生模型多97.4%，分类准确率达89%，学生模型保留了约93%的教师性能。临床分类行为的保留验证了方法有效性。本工作展示了可在低资源地区规模化部署的AI分诊解决方案。
原文摘要 · Abstract (English)
Early and accurate identification of retinal ailments is crucial for averting ocular decline; however, access to dependable diagnostic devices is not often available in low-resourced settings. This project proposes to solve that by developing a lightweight, edge-device deployable disease classifier using cross-architecture knowledge distilling. We first train a high-capacity vision transformer (ViT) teacher model, pre-trained using I-JEPA self-supervised learning, to classify fundus images into four classes: Normal, Diabetic Retinopathy, Glaucoma, and Cataract. We kept an Internet of Things (IoT) focus when compressing to a CNN-based student model for deployment in resource-limited conditions, such as the NVIDIA Jetson Nano. This was accomplished using a novel framework which included a Partitioned Cross-Attention (PCA) projector, a Group-Wise Linear (GL) projector, and a multi-view robust training method. The teacher model has 97.4 percent more parameters than the student model, with it achieving 89 percent classification with a roughly 93 percent retention of the teacher model's diagnostic performance. The retention of clinical classification behavior supports our method's initial aim: compression of the ViT while retaining accuracy. Our work serves as an example of a scalable, AI-driven triage solution for retinal disorders in under-resourced areas.
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。