Nie, Weili and Karras, Tero and Garg, Animesh and Debhath, Shoubhik and Patney, Anjul and Patel, Ankit B. and Anandkumar, Anima (2020) Semi-Supervised StyleGAN for Disentanglement Learning. . (Unpublished) https://resolver.caltech.edu/CaltechAUTHORS:20200402-135651804
![]() |
PDF (28 Apr 2020)
- Submitted Version
See Usage Policy. 35MB |
Use this Persistent URL to link to this item: https://resolver.caltech.edu/CaltechAUTHORS:20200402-135651804
Abstract
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.
Item Type: | Report or Paper (Discussion Paper) | ||||||
---|---|---|---|---|---|---|---|
Related URLs: |
| ||||||
ORCID: |
| ||||||
Record Number: | CaltechAUTHORS:20200402-135651804 | ||||||
Persistent URL: | https://resolver.caltech.edu/CaltechAUTHORS:20200402-135651804 | ||||||
Usage Policy: | No commercial reproduction, distribution, display or performance rights in this work are provided. | ||||||
ID Code: | 102273 | ||||||
Collection: | CaltechAUTHORS | ||||||
Deposited By: | Tony Diaz | ||||||
Deposited On: | 02 Apr 2020 21:02 | ||||||
Last Modified: | 06 Nov 2020 22:35 |
Repository Staff Only: item control page