Skip to content
This repository has been archived by the owner on Oct 30, 2020. It is now read-only.
/ average-joe Public archive

Image convergence through regularization by data

License

Notifications You must be signed in to change notification settings

hungyiwu/average-joe

Folders and files

NameName
Last commit message
Last commit date

Latest commit

 

History

6 Commits
 
 
 
 
 
 
 
 
 
 
 
 

Repository files navigation

Image convergence: regularize by data

Leveraging similar concept as in N2N [1], variational autoencoder (VAE) [2], and Siamese network [3]. The regularization effect is similar to VAE: in VAE, the model aims to reconstruct the input image from an off-by-a-bit latent vector (sampled from the latent space), while here the model aims to reconstruct an off-by-a-bit target image (shuffled with label preserved) from the latent vector. The net effect is the model converged to the typical image(s) within the label group. The latent space from models like this allows new image generation, clustering, and other applications.

Example training data

digit_2
digit_3
digit_4

Example test result

digit_2
digit_3
digit_4

Reference

[1] Noise2Noise: Learning Image Restoration without Clean Data (arxiv)
[2] Variational autoencoder (Wikipedia)
[3] Siamese neural network (Wikipedia)

About

Image convergence through regularization by data

Resources

License

Stars

Watchers

Forks

Languages