论文标题
在土地使用分类中适应异质域适应的循环GAN方法
A Cycle GAN Approach for Heterogeneous Domain Adaptation in Land Use Classification
论文作者
论文摘要
在遥感领域，更具体地说，在地球观察中，每天都有来自不同传感器的新数据。在分类任务中利用这些数据的价格是在操作设置中不现实的强烈标签任务的价格。尽管域的适应性可能有助于平衡此问题，但大多数通常的方法都假定适应的数据是可比的（它们属于同一度量空间），当多个传感器处于危险之中时，情况并非如此。异质域适应方法是解决此问题的特殊解决方案。我们提出了一种基于修改后的Cyclegan版本来处理此类案例的新方法，该版本结合了分类损失和度量空间对准项。我们通过Google Earth和Sentinel-2的图像展示了其在土地使用分类任务上的力量。
In the field of remote sensing and more specifically in Earth Observation, new data are available every day, coming from different sensors. Leveraging on those data in classification tasks comes at the price of intense labelling tasks that are not realistic in operational settings. While domain adaptation could be useful to counterbalance this problem, most of the usual methods assume that the data to adapt are comparable (they belong to the same metric space), which is not the case when multiple sensors are at stake. Heterogeneous domain adaptation methods are a particular solution to this problem. We present a novel method to deal with such cases, based on a modified cycleGAN version that incorporates classification losses and a metric space alignment term. We demonstrate its power on a land use classification tasks, with images from both Google Earth and Sentinel-2.
