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 2108.07779cs.CV
收藏

基于外观的航空影像深领域自适应分类

Appearance Based Deep Domain Adaptation for the Classification of Aerial Images

Leibniz University Hannover(莱布尼茨汉诺威大学)

Dennis Wittich, Franz Rottensteiner

摘要:

本文讨论了领域自适应的遥感数据的像素分类,使用深度神经网络(DNN)作为一种策略,以减少DNN的要求方面的训练数据的可用性。我们专注于设置标记的数据仅在源域DS中可用,但在目标域DT中不可用。我们的方法基于对外观自适应网络(AAN)的对抗性训练,该网络将DS中的图像进行变换,使其看起来像DT中的图像。与来自DS的原始标签映射一起,转换后的图像用于使DNN适应DT。我们提出了一个联合训练策略的AAN和分类器,约束AAN变换图像,使它们被正确分类。通过这种方式,某个类的对象被改变,使得它们类似于DT中相同类的对象。为了进一步提高自适应性能,我们提出了一种新的正则化损失用于域对抗训练的神经网络。我们还解决了找到训练的网络参数的最佳值的问题,提出了一个无监督的基于熵的参数选择标准,该标准补偿了DT中没有可以监视的验证集的事实。作为一个小小的贡献,我们提出了一个新的加权策略的交叉熵损失,解决不平衡的类分布的问题。我们的方法进行了评估,在42个适应方案,使用数据集从7个城市,所有组成的高分辨率数字正射影像和高度数据。它在所有情况下都实现了正迁移,并且平均而言,它在目标域中的性能提高了4.3%。在ISPRS语义标签基准数据集之间的适应场景中,我们的方法在平均交集上比最近出版物的方法高出10-20%。

英文摘要:

This paper addresses domain adaptation for the pixel-wise classification of remotely sensed data using deep neural networks (DNN) as a strategy to reduce the requirements of DNN with respect to the availability of training data. We focus on the setting in which labelled data are only available in a source domain DS, but not in a target domain DT. Our method is based on adversarial training of an appearance adaptation network (AAN) that transforms images from DS such that they look like images from DT. Together with the original label maps from DS, the transformed images are used to adapt a DNN to DT. We propose a joint training strategy of the AAN and the classifier, which constrains the AAN to transform the images such that they are correctly classified. In this way, objects of a certain class are changed such that they resemble objects of the same class in DT. To further improve the adaptation performance, we propose a new regularization loss for the discriminator network used in domain adversarial training. We also address the problem of finding the optimal values of the trained network parameters, proposing an unsupervised entropy based parameter selection criterion which compensates for the fact that there is no validation set in DT that could be monitored. As a minor contribution, we present a new weighting strategy for the cross-entropy loss, addressing the problem of imbalanced class distributions. Our method is evaluated in 42 adaptation scenarios using datasets from 7 cities, all consisting of high-resolution digital orthophotos and height data. It achieves a positive transfer in all cases, and on average it improves the performance in the target domain by 4.3% in overall accuracy. In adaptation scenarios between datasets from the ISPRS semantic labelling benchmark our method outperforms those from recent publications by 10-20% with respect to the mean intersection over union.

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。

↑