Generative Adversarial Networks for Cross-Scene Classification in Remote Sensing Images
Generative Adversarial Networks for Cross-Scene Classification in Remote Sensing Images
复制标题
DOI：
10.1109/igarss.2018.8517487
复制
发表时间：
2018-07
期刊：
影响因子：
--
通讯作者：
Laila Bashmal;Y. Bazi;H. Alhichri;N. Alajlan
中科院分区：
文献类型：
--
作者：
Laila Bashmal;Y. Bazi;H. Alhichri;N. Alajlan
在本文中，我们提出了一种基于生成对抗网络（GAN）的遥感图像跨场景分类新方法。为此，我们以对抗方式训练编码器-解码器网络与鉴别器网络，对来自两个不同域的标记和未标记数据进行训练。编码器-解码器网络旨在减少两个域的分布之间的差异，而鉴别器则试图区分它们。在优化过程结束时，我们在获得的编码标记数据上训练一个额外的网络，然后对编码的未标记数据进行分类。在波茨坦和法伊欣根市获取的两个数据集（空间分辨率分别为 5 厘米和 9 厘米）的实验结果证实了该方法的良好性能。
In this paper, we present a novel method for cross-scene classification in remote sensing images based on generative adversarial networks (GANs). To this end, we train in an adversarial manner an encoder-decoder network coupled with a discriminator network on labeled and unlabeled data coming from two different domains. The encoder-decoder network aims to reduce the discrepancy between the distributions of the two domains, while the discriminator tries to discriminate between them. At the end of the optimization process, we train an extra network on the obtained encoded labeled data and then classify the encoded unlabeled data. Experimental results on two datasets acquired over the cities of Potsdam and Vaihingen with spatial resolutions of 5cm and 9cm, respectively, confirm the promising capability of the proposed method.