Repository logo

Infoscience

  • English
  • French
Log In
Logo EPFL, École polytechnique fédérale de Lausanne

Infoscience

  • English
  • French
Log In
  1. Home
  2. Academic and Research Output
  3. Journal articles
  4. RG-Flow: a hierarchical and explainable flow model based on renormalization group and sparse prior
 
Loading...
Thumbnail Image
research article

RG-Flow: a hierarchical and explainable flow model based on renormalization group and sparse prior

Hu, Hong-Ye
•
Wu, Dian  
•
You, Yi-Zhuang
Show more
September 1, 2022
Machine Learning-Science And Technology

Flow-based generative models have become an important class of unsupervised learning approaches. In this work, we incorporate the key ideas of renormalization group (RG) and sparse prior distribution to design a hierarchical flow-based generative model, RG-Flow, which can separate information at different scales of images and extract disentangled representations at each scale. We demonstrate our method on synthetic multi-scale image datasets and the CelebA dataset, showing that the disentangled representations enable semantic manipulation and style mixing of the images at different scales. To visualize the latent representations, we introduce receptive fields for flow-based models and show that the receptive fields of RG-Flow are similar to those of convolutional neural networks. In addition, we replace the widely adopted isotropic Gaussian prior distribution by the sparse Laplacian distribution to further enhance the disentanglement of representations. From a theoretical perspective, our proposed method has O(log L) complexity for inpainting of an image with edge length L, compared to previous generative models with O(L-2) complexity.

  • Files
  • Details
  • Metrics
Loading...
Thumbnail Image
Name

ac8393.htm

Type

Publisher's Version

Access type

openaccess

License Condition

CC BY

Size

2.89 KB

Format

HTML

Checksum (MD5)

76b775362081cdce471a5004ba5bc108

Logo EPFL, École polytechnique fédérale de Lausanne
  • Contact
  • infoscience@epfl.ch

  • Follow us on Facebook
  • Follow us on Instagram
  • Follow us on LinkedIn
  • Follow us on X
  • Follow us on Youtube
AccessibilityLegal noticePrivacy policyCookie settingsEnd User AgreementGet helpFeedback

Infoscience is a service managed and provided by the Library and IT Services of EPFL. © EPFL, tous droits réservés