A copy of this work was available on the public web and has been preserved in the Wayback Machine. The capture dates from 2017; you can also visit the original URL.
The file type is
We investigate and improve self-supervision as a dropin replacement for ImageNet pretraining, focusing on automatic colorization as the proxy task. Self-supervised training has been shown to be more promising for utilizing unlabeled data than other, traditional unsupervised learning methods. We build on this success and evaluate the ability of our self-supervised network in several contexts. On VOC segmentation and classification tasks, we present results that are state-of-the-art among methodsdoi:10.1109/cvpr.2017.96 dblp:conf/cvpr/LarssonMS17 fatcat:qwfv3pqovrhlbarjtovpfxroxq