populations densities and commuting patterns. We use a non-supervised learning algorithm to identify meaningful locations for …

populations densities and commuting patterns. We use a non-supervised learning algorithm to identify meaningful locations for …

the ability of self-supervised learning methods and attention mechanism to extract features on a single class of images … extract the global semantic information of the image, a novel model with the combination of attention mechanism and self-supervised … learning method is proposed. First, an auxiliary task, reconstruct rotated image, is set to enable the network to learn global …