Learning Cross-Domain Disentangled Deep Representation with Supervision from A Single Domain
By Tzu-Chien Fu, Yen-Cheng Liu, Wei-Chen Chiu, Sheng-De Wang, Yu-Chiang Frank Wang. 2017
10 citations recorded by the source corpus.
The recent progress and development of deep generative models have led to remark- able improvements in research topics in computer vision and machine learning. In this paper, we address the task of cross-domain feature disentanglement. We advance the idea of unsupervised domain adaptation and propose to perform joint feature disentanglement and adaptation. Based on generative adversarial networks, we present a novel deep learning architecture with disentanglement ability, which observes cross-domain image data and derives latent features with the underly- ing factors (e.g., attributes). As a result, our generative model is able to address cross-domain feature disentanglement with only the (attribute) supervision from the source-domain data (not the target-domain ones). In the experiments, we apply our model for generating and classifying images with particular attributes, and show that satisfactory results can be produced.
Subfields: Artificial Intelligence, Computer Vision and Pattern Recognition
How researchers see this paper
The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.
In Artificial Intelligence
- Sebastian Nowozin
- Ryota Tomioka
- Diane Bouchacourt
- Ali Lalbakhsh
- Stefano Ermon
- Sergey Levine
- Yoshua Bengio
- Jiaming Song
In Computer Vision and Pattern Recognition
- Sebastian Nowozin
- Ryota Tomioka
- Diane Bouchacourt
- Stefano Ermon
- Luc Van Gool
- Dacheng Tao
- Andreas Geiger
- Ming-Hsuan Yang
Citations in the corpus
- Multi-Level Variational Autoencoder: Learning Disentangled Representations from Grouped Observations (2017, background): “Multiple works perform image-toimage translation between two unpaired images sets using adversarial training (Zhu et al. 2017; Kim et al. 2017; Yi et al. 2017; Fu et al. 2017; Taigman, Polyak, and Wolf 2017; Shrivastava et al. 2017; Bousmalis et al. 2017; Liu, Breuel, and Kautz 2017).”
- Artificial Intelligence and COVID-19: Deep Learning Approaches for Diagnosis and Treatment (2020, background): “It is also demonstrated that GANs are useful for semi-supervised learning [79], fully supervised learning [80] and reinforcement learning [81].”