NeurIPS 2018poster47 citations
Dual Swap Disentangling
Zunlei Feng, Xinchao Wang, Chenglong Ke, An-Xiang Zeng, Dacheng Tao, Mingli Song
Abstract
Learning interpretable disentangled representations is a crucial yet challenging task. In this paper, we propose a weakly semi-supervised method, termed as Dual Swap Disentangling (DSD), for disentangling using both labeled and unlabeled data. Unlike conventional weakly supervised methods that rely on full annotations on the group of samples, we require only limited annotations on paired samples that indicate their shared attribute like the color. Our model takes the form of a dual autoencoder structure. To achieve disentangling using the labeled pairs, we follow a
BibTeX
@inproceedings{NEURIPS2018_fdf1bc56,
author = {Feng, Zunlei and Wang, Xinchao and Ke, Chenglong and Zeng, An-Xiang and Tao, Dacheng and Song, Mingli},
booktitle = {Advances in Neural Information Processing Systems},
editor = {S. Bengio and H. Wallach and H. Larochelle and K. Grauman and N. Cesa-Bianchi and R. Garnett},
pages = {},
publisher = {Curran Associates, Inc.},
title = {Dual Swap Disentangling},
url = {https://proceedings.neurips.cc/paper_files/paper/2018/file/fdf1bc5669e8ff5ba45d02fded729feb-Paper.pdf},
volume = {31},
year = {2018}
}