Land Cover Classification from Satellite Imagery with U-Net and Lovász-Softmax Loss
Land Cover Classification from Satellite Imagery with U-Net and Lovász-Softmax Loss
复制标题
DOI：
10.1109/cvprw.2018.00048
复制
发表时间：
2018-06
期刊：
影响因子：
--
通讯作者：
A. Rakhlin;A. Davydow;S. Nikolenko
中科院分区：
文献类型：
--
作者：
A. Rakhlin;A. Davydow;S. Nikolenko
DeepGlobe挑战赛的土地覆盖分类任务由于数据量小、不完整甚至有时是不正确的标记以及高度不平衡的类别，甚至对最先进的分割模型也构成了重大障碍。在这项工作中，我们展示了一种基于U-Net架构的方法，该方法具有成功解决这些问题的Lov 'asz-Softmax损失;我们比较了U-Net编码器的几种不同卷积架构。
The land cover classification task of the DeepGlobe Challenge presents significant obstacles even to state of the art segmentation models due to a small amount of data, incomplete and sometimes incorrect labeling, and highly imbalanced classes. In this work, we show an approach based on the U-Net architecture with the Lov´asz-Softmax loss that successfully alleviates these problems; we compare several different convolutional architectures for U-Net encoders.