Figure: Training framework of GH-Feat.
Generative Hierarchical Features from Synthesizing Images
Yinghao Xu*, Yujun Shen*, Jiapeng Zhu, Ceyuan Yang, Bolei Zhou
arXiv preprint arXiv:2007.10379
[Paper] [Project Page]
In this repository, we show that well-trained GAN generators can be used as training supervision to learn hierarchical and disentangled visual features. We call this feature as Generative Hierarchical Feature (GH-Feat). Properly learned from a novel hierarchical encoder, GH-Feat is able to facilitate both discriminative and generative visual tasks, including face verification, landmark detection, layout prediction, transfer learning, style mixing, and image editing, etc. Some results are shown as follows.
Indoor scene layout prediction
Face verification (face reconstruction)
@article{xu2020generative,
title = {Generative Hierarchical Features from Synthesizing Images},
author = {Xu, Yinghao and Shen, Yujun and Zhu, Jiapeng and Yang, Ceyuan and Zhou, Bolei},
journal = {arXiv preprint arXiv:2007.10379},
year = {2020}
}