1. [Publications](/publications)
2. Semi-Supervised StyleGAN for Disentanglement Learning
 
 # Semi-Supervised StyleGAN for Disentanglement Learning

  ![](/sites/default/files/publications/teaser2.gif) 

 Disentanglement learning is crucial for obtaining disentangled representations and controllable generation. Current disentanglement methods face several inherent limitations: difficulty with high-resolution images, primarily on learning disentangled representations, and non-identifiability due to the unsupervised setting. To alleviate these limitations, we design new architectures and loss functions based on StyleGAN (Karras et al., 2019), for semi-supervised high-resolution disentanglement learning. We create two complex high-resolution synthetic datasets for systematic testing. We investigate the impact of limited supervision and find that using only 0.25%~2.5% of labeled data is sufficient for good disentanglement on both synthetic and real datasets. We propose new metrics to quantify generator controllability, and observe there may exist a crucial trade-off between disentangled representation learning and controllable generation. We also consider semantic fine-grained image editing to achieve better generalization to unseen images.



 ## Authors



Weili Nie (Rice University)

[Tero Karras](/person/tero-karras)

Animesh Garg (NVIDIA)

Shoubhik Debnath (NVIDIA)

Anjul Patney (NVIDIA)

Ankit B. Patel (Rice University)

Anima Anandkumar (NVIDIA)

 

 

 ## Publication Date



Tuesday, July 14, 2020

 

 ## Published in



[International Conference on Machine Learning (ICML) 2020](https://icml.cc/virtual/2020)

 

 ## Research Area



[Artificial Intelligence and Machine Learning ](/research-area/machine-learning-artificial-intelligence)

[Computer Graphics](/research-area/computer-graphics)

[Computer Vision](/research-area/computer-vision)

[Generative AI](/research-area/generative-ai)

 

 

 ## External Links



[Project Page](https://sites.google.com/nvidia.com/semi-stylegan)

[Paper (arXiv)](https://arxiv.org/abs/2003.03461)

[Dataset](https://github.com/NVlabs/High-res-disentanglement-datasets)

[Slides](https://docs.google.com/presentation/d/127ChXpeWUNXIOkf6Z6qB201BhnJUxZepK4mvtsq9ELM/edit?usp=sharing)