arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2004.11819cs.CVcs.LGeess.IVstat.ML
收藏

基于域自适应转移攻击(DATA)分割网络的航空影像建筑物提取

Domain Adaptive Transfer Attack (DATA)-based Segmentation Networks for Building Extraction from Aerial Images

National Institute of Standards and Technology(国家标准与技术研究院);Rice University(莱斯大学);Colorado State University(科罗拉多州立大学);National Research Institute for Metals(金属材料研究所)

Younghwan Na, Jun Hee Kim, Kyungsu Lee, Juhum Park, Jae Youn Hwang, Jihwan P. Choi

摘要:

基于卷积神经网络(CNN)的语义分割模型在遥感领域得到了广泛的关注,并在高分辨率航空影像建筑物提取方面取得了显著的效果。然而,对于不可见图像的有限概括的问题仍然存在。当训练数据集和测试数据集之间存在域间隙时,由训练数据集训练的基于CNN的分割模型无法为测试数据集分割建筑物。在本文中,我们提出了分割网络的基础上域自适应转移攻击(DATA)计划从航空图像中提取建筑物。所提出的系统结合了域转移和对抗攻击的概念。基于DATA方案,可以将输入图像的分布转移到目标图像的分布,同时将图像转化为针对目标网络的对抗性示例。防御对抗性的例子适应于目标域可以克服由于域间隙的性能下降,并增加分割模型的鲁棒性。针对三个不同的数据集进行了跨数据集实验和消融研究:Inria航空图像标记数据集,马萨诸塞州建筑数据集和WHU东亚数据集。与没有DATA方案的分段网络的性能相比,所提出的方法在整体IoU方面有所改进。此外,它被验证,所提出的方法优于即使相比,特征自适应(FA)和输出空间自适应(OSA)。

英文摘要:

Semantic segmentation models based on convolutional neural networks (CNNs) have gained much attention in relation to remote sensing and have achieved remarkable performance for the extraction of buildings from high-resolution aerial images. However, the issue of limited generalization for unseen images remains. When there is a domain gap between the training and test datasets, CNN-based segmentation models trained by a training dataset fail to segment buildings for the test dataset. In this paper, we propose segmentation networks based on a domain adaptive transfer attack (DATA) scheme for building extraction from aerial images. The proposed system combines the domain transfer and adversarial attack concepts. Based on the DATA scheme, the distribution of the input images can be shifted to that of the target images while turning images into adversarial examples against a target network. Defending adversarial examples adapted to the target domain can overcome the performance degradation due to the domain gap and increase the robustness of the segmentation model. Cross-dataset experiments and the ablation study are conducted for the three different datasets: the Inria aerial image labeling dataset, the Massachusetts building dataset, and the WHU East Asia dataset. Compared to the performance of the segmentation network without the DATA scheme, the proposed method shows improvements in the overall IoU. Moreover, it is verified that the proposed method outperforms even when compared to feature adaptation (FA) and output space adaptation (OSA).

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。

↑