Convolutional Neural Networks for Large-Scale Remote-Sensing Image Classification
Convolutional Neural Networks for Large-Scale Remote-Sensing Image Classification
复制标题
DOI：
10.1109/tgrs.2016.2612821
复制
发表时间：
2017-02-01
影响因子：
8.2
通讯作者：
Alliez, Pierre
中科院分区：
文献类型：
--
作者：
Maggiori, Emmanuel;Tarabalka, Yuliya;Alliez, Pierre
我们提出了一个端到端框架，用于使用卷积神经网络（CNN）对卫星图像进行密集的像素级分类。在我们的框架中，CNN 被直接训练以根据输入图像生成分类图。我们首先设计了一个全卷积架构，并证明了它与密集分类问题的相关性。然后，我们通过两步训练方法解决训练数据不完善的问题：首先使用大量可能不准确的参考数据来初始化 CNN，然后在少量准确标记的数据上进行细化。为了完成我们的框架，我们设计了一个多尺度神经元模块，以减轻识别和精确定位之间的常见权衡。一系列实验表明，我们的网络考虑大量上下文来提供细粒度的分类图。
We propose an end-to-end framework for the dense, pixelwise classification of satellite imagery with convolutional neural networks (CNNs). In our framework, CNNs are directly trained to produce classification maps out of the input images. We first devise a fully convolutional architecture and demonstrate its relevance to the dense classification problem. We then address the issue of imperfect training data through a two-step training approach: CNNs are first initialized by using a large amount of possibly inaccurate reference data, and then refined on a small amount of accurately labeled data. To complete our framework, we design a multiscale neuron module that alleviates the common tradeoff between recognition and precise localization. A series of experiments show that our networks consider a large amount of context to provide fine-grained classification maps.