arXivDaily arXiv每日学术速递 周一至周五更新
arXiv周末暂无论文更新,休息一下吧,周末愉快~~
arXiv 2006.05923eess.IVcs.LG
收藏

跨传感器对抗域适应:用于云检测的Landsat-8和Proba-V图像

Cross-Sensor Adversarial Domain Adaptation of Landsat-8 and Proba-V images for Cloud Detection

Gonzalo Mateo-García, Valero Laparra, Dan López-Puigdollers, Luis Gómez-Chova

AI总结:

本文提出了一种跨传感器对抗域适应方法,通过减少Landsat-8和Proba-V图像间的统计差异,提升云检测模型的性能。

摘要:

地球观测卫星携带具有相似特性的光学传感器的数量正在不断增长。尽管它们有相似之处,并且它们之间有潜在的协同效应,但衍生的卫星产品通常是为每个传感器独立开发的。检索辐射的差异导致了显著的准确性下降,这阻碍了传感器之间的知识和信息共享。这尤其对机器学习算法有害,因为为每个传感器收集新的地面真实数据来训练模型是昂贵的,且需要经验丰富的人员。在本工作中,我们提出了一种域适应转换,以减少两种卫星传感器图像之间的统计差异,以提升迁移学习模型的性能。所提出的方法基于循环一致生成对抗域适应(CyCADA)框架,该框架以无配对的方式训练转换模型。特别是,Landsat-8和Proba-V卫星,它们具有不同的但兼容的时空特性,被用来说明该方法。获得的转换显著减少了图像数据集之间的差异,同时保持了适应图像的空间和光谱信息,因此对任何通用的跨传感器应用都很有用。此外,所提出的对抗域适应模型的训练可以修改以在特定的遥感应用中提高性能,例如云检测,通过在成本函数中加入专用项。结果表明,当应用所提出的转换时,在Landsat-8数据上训练的云检测模型在Proba-V上提高了云检测准确性。

英文摘要:

The number of Earth observation satellites carrying optical sensors with similar characteristics is constantly growing. Despite their similarities and the potential synergies among them, derived satellite products are often developed for each sensor independently. Differences in retrieved radiances lead to significant drops in accuracy, which hampers knowledge and information sharing across sensors. This is particularly harmful for machine learning algorithms, since gathering new ground truth data to train models for each sensor is costly and requires experienced manpower. In this work, we propose a domain adaptation transformation to reduce the statistical differences between images of two satellite sensors in order to boost the performance of transfer learning models. The proposed methodology is based on the Cycle Consistent Generative Adversarial Domain Adaptation (CyCADA) framework that trains the transformation model in an unpaired manner. In particular, Landsat-8 and Proba-V satellites, which present different but compatible spatio-spectral characteristics, are used to illustrate the method. The obtained transformation significantly reduces differences between the image datasets while preserving the spatial and spectral information of adapted images, which is hence useful for any general purpose cross-sensor application. In addition, the training of the proposed adversarial domain adaptation model can be modified to improve the performance in a specific remote sensing application, such as cloud detection, by including a dedicated term in the cost function. Results show that, when the proposed transformation is applied, cloud detection models trained in Landsat-8 data increase cloud detection accuracy in Proba-V.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑