Generative Adversarial Networks (GANs) have recently advanced image synthesis by learning the underlying distribution of observed data in an unsupervised manner . However, how the features trained from solving the task of image synthesis are applicable to visual tasks remains seldom explored… In this work, we show that learning to synthesize images is able to bring remarkable hierarchical visual features that are generalizable across a wide range of visual tasks . Extensive experiments on face verification, landmark detection, layout prediction, transfer learning, style mixing, and image editing show the appealing performance of the GH-Feat learned from synthesizing images, outperforming existing unsupervisory feature learning methods . The visual feature produced by our encoder has compelling discriminative and disentangled properties, facilitating a range of

Links: PDF - Abstract

Code :

Keywords : learning - visual - features - image - images -

Leave a Reply

Your email address will not be published. Required fields are marked *


Enjoy this blog? Please spread the word :)