Semi-supervised contrastive learning for remote sensing: identifying ancient urbanization in the south-central Andes
Semi-supervised contrastive learning for remote sensing: identifying ancient urbanization in the south-central Andes
复制标题
DOI：
10.1080/01431161.2023.2192879
复制
发表时间：
2021-12
影响因子：
3.4
通讯作者：
Jiachen Xu;James Zimmer-Dauphinee;Quan Liu;Yuxuan Shi;Steven A. Wernke;Yuankai Huo
中科院分区：
文献类型：
--
作者：
Jiachen Xu;James Zimmer-Dauphinee;Quan Liu;Yuxuan Shi;Steven A. Wernke;Yuankai Huo
考古学长期以来一直面临着采样和标量表示的基本问题。传统上，通过系统的行人调查产生了从地方到区域规模的住区模式视图。最近，系统的人工调查的卫星和航空图像，使连续分布的意见，考古现象在区域间的规模。然而，这样的“蛮力”手动图像调查方法是时间和劳动密集型的，以及易于在灵敏度和特异性上的观察者之间的差异。自我监督学习方法（如对比学习）的发展提供了一个可扩展的学习计划，使用未标记的卫星和历史航空图像定位考古特征。然而，考古特征通常只在相对于景观的很小比例中可见，而现代对比监督学习方法通常在高度不平衡的数据集上产生较差的性能。在这项工作中，我们提出了一个框架来解决这个长尾问题。与现有的通常单独处理标记和未标记数据的对比学习方法相反，我们提出的方法改革了半监督设置下的学习范式，以充分利用宝贵的注释数据（在我们的设置中<7%）。具体而言，数据的高度不平衡性质被用作先验知识，以便通过对未注释的图像块和注释的锚图像之间的相似性进行排名来形成伪负对。在这项研究中，我们使用了95，358张未标记的图像和5，830张标记的图像，以解决从长尾卫星图像数据集中检测古建筑的相关问题。从结果来看，我们的半监督对比学习模型实现了79.0%的有希望的测试平衡准确率，与其他最先进的方法相比，提高了3.8%。
ABSTRACT Archaeology has long faced fundamental issues of sampling and scalar representation. Traditionally, the local-to-regional-scale views of settlement patterns are produced through systematic pedestrian surveys. Recently, systematic manual survey of satellite and aerial imagery has enabled continuous distributional views of archaeological phenomena at interregional scales. However, such ‘brute force’ manual imagery survey methods are both time- and labour-intensive, as well as prone to inter-observer differences in sensitivity and specificity. The development of self-supervised learning methods (e.g. contrastive learning) offers a scalable learning scheme for locating archaeological features using unlabelled satellite and historical aerial images. However, archaeological features are generally only visible in a very small proportion relative to the landscape, while the modern contrastive-supervised learning approach typically yields an inferior performance on highly imbalanced datasets. In this work, we propose a framework to address this long-tail problem. As opposed to the existing contrastive learning approaches that typically treat the labelled and unlabelled data separately, our proposed method reforms the learning paradigm under a semi-supervised setting in order to fully utilize the precious annotated data (<7% in our setting). Specifically, the highly unbalanced nature of the data is employed as the prior knowledge in order to form pseudo negative pairs by ranking the similarities between unannotated image patches and annotated anchor images. In this study, we used 95,358 unlabelled images and 5,830 labelled images in order to solve the issues associated with detecting ancient buildings from a long-tailed satellite image dataset. From the results, our semi-supervised contrastive learning model achieved a promising testing balanced accuracy of 79.0%, which is a 3.8% improvement as compared to other state-of-the-art approaches.