How to choose a deep learning architecture to detect aircrafts in satellite imagery?

In recent years, artificial intelligence has made great strides in the field of computer vision. One area that has seen particularly impressive progress is object detection, with a variety of deep learning models achieving high levels of accuracy. However, this abundance of choice can be overwhelming for practitioners who are looking to implement an object detection system. On top of this, most public models and academic research are benchmarked on COCO which are dataset made of photographs. Satellite images are quite different from photographs: the objects to detect are usually much smaller and much more numerous, they are oriented in all kind of direction and acquired in slightly different colors. In photographs, trees are always seen as green objects with the trunk below the foliage. So, if a model architecture performs well on a photographic dataset, it does not mean that it will perform as well on an aerial dataset.