Context Encoders: Feature Learning by Inpainting

• Published in: 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR) pp. 2536 - 2544
• Main Authors: Pathak, Deepak, Krahenbuhl, Philipp, Donahue, Jeff, Darrell, Trevor, Efros, Alexei A.
• Format: Conference Proceeding
• Language: English
• Published: IEEE 01.06.2016
• Subjects: Computer architecture; Context; Convolutional codes; Decoding; Image reconstruction; Semantics; Visualization

We present an unsupervised visual feature learning algorithm driven by context-based pixel prediction. By analogy with auto-encoders, we propose Context Encoders - a convolutional neural network trained to generate the contents of an arbitrary image region conditioned on its surroundings. In order t...