遥感图像军用飞机目标识别是对遥感图像中的军用飞机进行定位和细粒度分类，其在侦察预警、情报分析等领域起着至关重要的作用。但是，由于数据集匮乏，遥感图像军用飞机目标识别发展相对缓慢。为推动该领域的研究进展，本文构建了公开的遥感图像军用飞机目标识别数据集MAR20（Military Aircraft Recognition）。该数据集具有以下特点：（1）MAR20是目前规模最大的遥感图像军用飞机目标识别数据集，包含3842张图像、20种军用飞机型号以及22341个实例，并且每个目标实例具有水平边界框和有向边界框两种标注方式；（2）由于所有的细粒度类别均隶属于飞机大类，因此不同型号的飞机往往具有相似的特征，导致不同型号目标具有较高的相似性；（3）由于遥感图像采集过程中受到气候、季节、光照、遮挡、乃至大气散射等因素的影响，相同型号的目标存在较大的类内差异性。最后，为建立遥感图像军用飞机目标识别基准，本文在MAR20数据集上评估了7种常用的水平框目标识别方法和8种有向框目标识别方法。MAR20数据集下载链接：https://gcheng-nwpu.github.io/。

Military aircraft recognition in remote sensing images is to locate military aircraft in remote sensing images and classify them at a fine-grained level, which plays a vital role in reconnaissance and early warning, intelligence analysis and other fields. However, due to the lack of datasets, the development of military aircraft recognition in remote sensing images is relatively slow. In order to promote the research progress in this field, this paper constructs a public remote sensing image military aircraft recognition dataset, named MAR20. The dataset has the following characteristics: (1) MAR20 is currently the largest remote sensing image military aircraft recognition dataset, including 3842 images, 20 types and 22341 instances, and each instance has a horizontal bounding box and also an oriented bounding box; (2) Since all fine-grained types belong to the aircraft category, different types of aircraft often have similar characteristics, resulting in high similarity of different types of targets; (3) Due to the influence of climate, season, illumination, occlusion, and even the atmospheric scattering in the process of remote sensing imaging, there are large intra-class differences between the targets of the same type. Finally, in order to establish a benchmark for military aircraft recognition in remote sensing images, this paper evaluates 7 commonly used horizontal object recognition methods and 8 oriented object recognition methods on the MAR20 dataset. MAR20 can be downloaded at https://gcheng-nwpu.github.io/.