Scholarlink

In this work, we propose Many-MobileNet − an efficient model fusion strategy for retinal disease classification using lightweight CNN architecture. Our method addresses key challenges such as over-fitting and limited dataset variability by training multiple models with distinct data augmentation strategies and different model complexities. Through this fusion technique, we achieved robust generalization in data-scarce environments while balancing computational efficiency with feature extraction capabilities. As a result, we secured 3rd place in the MICCAI UWF4DR 2024 Challenge for image quality assessment in ultra-widefield fundus images. Our software package is available at https://github.com/Retinal-Research/NN-MOBILENET .

错误：搜索内容不能为空，请输入英文关键词
错误：关键词超出字数限制，请精简
高级检索

Many-MobileNet: Multi-model Augmentation for Robust Retinal Disease Classification

  • 会议论文

  • 发表日期：

    2025年

查看全文
  • Hao Wang,
  • Wenhui Zhu,
  • Xuanzhao Dong,
  • Yanxi Chen,
  • Xin Li,
  • Peijie Qiu,
  • Xiwen Chen,
  • Vamsi Krishna Vasa,
  • Yujian Xiong,
  • Oana M. Dumitrascu,
  • Abolfazl Razi,
  • Yalin Wang

摘要

In this work, we propose Many-MobileNet − an efficient model fusion strategy for retinal disease classification using lightweight CNN architecture. Our method addresses key challenges such as over-fitting and limited dataset variability by training multiple models with distinct data augmentation strategies and different model complexities. Through this fusion technique, we achieved robust generalization in data-scarce environments while balancing computational efficiency with feature extraction capabilities. As a result, we secured 3rd place in the MICCAI UWF4DR 2024 Challenge for image quality assessment in ultra-widefield fundus images. Our software package is available at https://github.com/Retinal-Research/NN-MOBILENET .