Object detection in remote sensing images aims at localizing the targets of interest in the images and predicting their attributes. With the rapid development of remote sensing technology, the imaging quality and spatial resolution of remote sensing images have been gradually improved, which makes it possible to extract the targets of interest from the remote sensing images quickly and automatically. Currently, deep learning-based object detection methods have achieved the promising performance on the publicly available datasets, which has demonstrated significant application potential in the field of object detection and recognition in remote sensing images. However, for the real-world applications, existing object detection methods still encounter a series of challenges such as complex and diverse remote sensing scenes, imbalanced target distributions, densely arranged targets, as well as weak, small, or poorly illuminated targets [1]. The details are as follows: