“…Most previous methods either rely on employing handcrafted visual features [13,24,47,77], such as color and shape, or using mid-level holistic image representations [11,33,44,75,76] constructed by encoding hand-crafted visual features. Recently, deep Convolutional Neural Networks (CNNs) have revolutionized computer vision by significantly advancing the state-of-the-art in many areas such as, image classification [8,20,31,38,43,64], object detection/segmentation [19,28,30,40,53,57,68,69,81] and action recognition [26,48,51,63]. Similarly, deep learning techniques have also made an impact on satellite image analysis, including aerial scene classification [2,32,54,73] and hyperspectral image analysis [14,15,66].…”