Deep metric learning (DML) based methods have been found very effective for content-based image retrieval (CBIR) in remote sensing (RS). For accurately learning the model parameters of deep neural networks, most of the DML methods require a high number of annotated training images, which can be costly to gather. To address this problem, in this paper we present an annotation cost efficient active learning (AL) method (denoted as ANNEAL). The proposed method aims to iteratively enrich the training set by annotating the most informative image pairs as similar or dissimilar, %answering a simple yes/no question, while accurately modelling a deep metric space. This is achieved by two consecutive steps. In the first step the pairwise image similarity is modelled based on the available training set. Then, in the second step the most uncertain and diverse (i.e., informative) image pairs are selected to be annotated. Unlike the existing AL methods for CBIR, at each AL iteration of ANNEAL a human expert is asked to annotate the most informative image pairs as similar/dissimilar. This significantly reduces the annotation cost compared to annotating images with land-use/land cover class labels. Experimental results show the effectiveness of our method. The code of ANNEAL is publicly available at https://git.tu-berlin.de/rsim/ANNEAL.

翻译：基于深度度量学习（DML）的方法已被证明对遥感（RS）中的内容图像检索（CBIR）非常有效。为准确学习深度神经网络模型参数，大多数DML方法需要大量标注训练图像，这通常成本高昂。为解决此问题，本文提出一种标注成本高效的主动学习（AL）方法（记为ANNEAL）。该方法旨在通过迭代地标注最具信息量的图像对为相似/不相似（即回答简单的"是/否"问题）来丰富训练集，同时准确建模深度度量空间。这通过两个连续步骤实现：第一步，基于可用训练集对图像对相似性进行建模；第二步，选择最不确定且最具多样性（即信息量最大）的图像对进行标注。与现有面向CBIR的主动学习方法不同，在ANNEAL的每次主动学习迭代中，人类专家被要求标注最具信息量的图像对为相似/不相似。与使用土地利用/土地覆盖类别标签标注图像相比，这显著降低了标注成本。实验结果表明了本方法的有效性。ANNEAL的代码已在https://git.tu-berlin.de/rsim/ANNEAL公开提供。