InfoGAN-CR and ModelCentrality: Self-supervised Model Training and Selection for Disentangling GANs
@inproceedings{Lin2020InfoGANCRAM, title={InfoGAN-CR and ModelCentrality: Self-supervised Model Training and Selection for Disentangling GANs}, author={Z. Lin and Kiran Koshy Thekumparampil and Giulia Fanti and Sewoong Oh}, booktitle={ICML}, year={2020} }
Disentangled generative models map a latent code vector to a target space, while enforcing that a subset of the learned latent codes are interpretable and associated with distinct properties of the target distribution. Recent advances have been dominated by Variational AutoEncoder (VAE)-based methods, while training disentangled generative adversarial networks (GANs) remains challenging. In this work, we show that the dominant challenges facing disentangled GANs can be mitigated through the use… CONTINUE READING
Figures, Tables, and Topics from this paper
10 Citations
Learning Disentangled Representations with Latent Variation Predictability
- Computer Science
- ECCV
- 2020
- 1
- PDF
An Improved Semi-Supervised VAE for Learning Disentangled Representations
- Computer Science, Mathematics
- ArXiv
- 2020
- PDF
Evaluating the Disentanglement of Deep Generative Models through Manifold Topology
- Mathematics, Computer Science
- ArXiv
- 2020
- PDF
DynamicVAE: Decoupling Reconstruction Error and Disentangled Representation Learning
- Computer Science, Mathematics
- 2020
- PDF
Challenging $\beta$-VAE with $\beta < 1$ for Disentanglement Via Dynamic Learning
- Computer Science
- 2020
Deep Generative Model for Efficient 3D Airfoil Parameterization and Generation
- Computer Science
- ArXiv
- 2021
- PDF
References
SHOWING 1-10 OF 74 REFERENCES
Learning Disentangled Representations with Semi-Supervised Deep Generative Models
- Computer Science, Mathematics
- NIPS
- 2017
- 198
- PDF
Hyperprior Induced Unsupervised Disentanglement of Latent Representations
- Computer Science, Mathematics
- AAAI
- 2019
- 16
- PDF
beta-VAE: Learning Basic Visual Concepts with a Constrained Variational Framework
- Computer Science
- ICLR
- 2017
- 1,585
- Highly Influential
A Heuristic for Unsupervised Model Selection for Variational Disentangled Representation Learning
- Computer Science, Mathematics
- ICLR
- 2020
- 13
- Highly Influential
- PDF
OOGAN: Disentangling GAN with One-Hot Sampling and Orthogonal Regularization
- Computer Science
- AAAI
- 2020
- 11
- PDF
VEEGAN: Reducing Mode Collapse in GANs using Implicit Variational Learning
- Computer Science, Mathematics
- NIPS
- 2017
- 268
- PDF
Weakly Supervised Disentanglement by Pairwise Similarities
- Computer Science, Mathematics
- AAAI
- 2020
- 18
- PDF
Challenging Common Assumptions in the Unsupervised Learning of Disentangled Representations
- Computer Science, Mathematics
- ICML
- 2019
- 348
- PDF
Learning Deep Disentangled Embeddings with the F-Statistic Loss
- Computer Science, Mathematics
- NeurIPS
- 2018
- 71
- PDF