Scholarlink

<p>Generalising UNet-based models for road extraction from high-resolution remote sensing datasets remains challenging in practical applications. This work evaluates seven UNet variants using the Massachusetts Roads, DeepGlobe, and CHN6-CUG datasets. To test generalization ability we evaluated their transferability to our Unmanned Aerial Vehicle (UAV) imagery. We apply conventional evaluation criteria such as IoU, precision, recall, F1-score, and computing cost. The results demonstrate a consistent trend: higher architectural complexity produces relatively minimal improvements. Also, each model exhibits a notable drop in performance when evaluated with images from other road dataset, highlighting that cross-dataset adaptation continues to be an important challenge. The original UNet demonstrates comparable performance to more advanced models while having significantly more computational efficiency, thereby proving its position as a solid baseline. The results highlight the need for segmentation models that can adapt to the significant variability found in real-world data.</p>

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

Exploring the Generalization Limits of UNet Variants in Road Extraction

  • 期刊论文

  • 发表日期：

    2026年3月16日

查看全文
  • T. V. Jayakumar,
  • Deepak Mishra,
  • M. Ramiya Anandakumar,
  • Jai G. Singla

摘要

Generalising UNet-based models for road extraction from high-resolution remote sensing datasets remains challenging in practical applications. This work evaluates seven UNet variants using the Massachusetts Roads, DeepGlobe, and CHN6-CUG datasets. To test generalization ability we evaluated their transferability to our Unmanned Aerial Vehicle (UAV) imagery. We apply conventional evaluation criteria such as IoU, precision, recall, F1-score, and computing cost. The results demonstrate a consistent trend: higher architectural complexity produces relatively minimal improvements. Also, each model exhibits a notable drop in performance when evaluated with images from other road dataset, highlighting that cross-dataset adaptation continues to be an important challenge. The original UNet demonstrates comparable performance to more advanced models while having significantly more computational efficiency, thereby proving its position as a solid baseline. The results highlight the need for segmentation models that can adapt to the significant variability found in real-world data.