Zero-Shot Scene Classification for High Spatial Resolution Remote Sensing Images
Zero-Shot Scene Classification for High Spatial Resolution Remote Sensing Images
复制标题
高空间分辨率遥感图像的零样本场景分类
DOI：
10.1109/tgrs.2017.2689071
复制
发表时间：
2017-07-01
影响因子：
8.2
通讯作者：
Wen, Ji-Rong
中科院分区：
文献类型：
--
作者：
Li, Aoxue;Lu, Zhiwu;Wen, Ji-Rong
由于各种传感器技术的快速发展，现在可以获取海量的高空间分辨率(HSR)图像数据。如何从这样的高铁图像数据中高效地识别场景已经成为一项关键的任务。传统的遥感场景分类方法仅利用高铁图像中的信息。因此，它们总是需要大量的标记数据，并且在标记数据中没有任何视觉样本的情况下无法识别来自不可见场景类的图像。为了克服这一缺陷，我们提出了一种新的从未见场景类中识别图像的方法，即零镜头场景分类(ZSSC)。在该方法中，我们首先使用著名的自然语言过程模型word2vec将已见/未见场景类的名称映射到语义向量。然后在语义向量上构建语义有向图，用于描述不可见类和可见类之间的关系。为了将知识从可见类中的图像传递到不可见类中，我们通过一个无监督的域自适应模型对测试图像进行初始标签预测。利用语义有向图和初始预测，给出了ZSSC的标签传播算法。利用同一场景类图像之间的视觉相似性，采用基于稀疏学习的标签细化方法抑制零镜头分类结果中的噪声。实验结果表明，该方法的性能明显优于ZSSC中的最新方法。
Due to the rapid technological development of various sensors, a huge volume of high spatial resolution (HSR) image data can now be acquired. How to efficiently recognize the scenes from such HSR image data has become a critical task. Conventional approaches to remote sensing scene classification only utilize information from HSR images. Therefore, they always need a large amount of labeled data and cannot recognize the images from an unseen scene class without any visual sample in the labeled data. To overcome this drawback, we propose a novel approach for recognizing images from unseen scene classes, i.e., zero-shot scene classification (ZSSC). In this approach, we first use the well-known natural language process model, word2vec, to map names of seen/unseen scene classes to semantic vectors. A semantic-directed graph is then constructed over the semantic vectors for describing the relationships between unseen classes and seen classes. To transfer knowledge from the images in seen classes to those in unseen classes, we make an initial label prediction on test images by an unsupervised domain adaptation model. With the semantic-directed graph and initial prediction, a label-propagation algorithm is then developed for ZSSC. By leveraging the visual similarity among images from the same scene class, a label refinement approach based on sparse learning is used to suppress the noise in the zero-shot classification results. Experimental results show that the proposed approach significantly outperforms the state-of-the-art approaches in ZSSC.