-
Deep Automatic Portrait Matting
The dataset used for training and testing the proposed LSSC system, which consists of 1530 training images and 170 test images in RGB format. -
Vaihingen dataset
The Vaihingen dataset consists of 1440 scenes with a size of 250×250 pixels. Each scene is a colour-infrared (CIR) true orthophoto and a height grid (digital surface model; DSM)... -
MIT-Adobe FiveK
The MIT-Adobe FiveK dataset, a large-scale dataset for image segmentation and object detection.