Langevin Cooling for Domain Translation

08/31/2020 ∙ by Vignesh Srinivasan, et al. ∙ 5

Domain translation is the task of finding correspondence between two domains. Several Deep Neural Network (DNN) models, e.g., CycleGAN and cross-lingual language models, have shown remarkable successes on this task under the unsupervised setting—the mappings between the domains are learned from two independent sets of training data in both domains (without paired samples). However, those methods typically do not perform well on a significant proportion of test samples. In this paper, we hypothesize that many of such unsuccessful samples lie at the fringe—relatively low-density areas—of data distribution, where the DNN was not trained very well, and propose to perform Langevin dynamics to bring such fringe samples towards high density areas. We demonstrate qualitatively and quantitatively that our strategy, called Langevin Cooling (L-Cool), enhances state-of-the-art methods in image translation and language translation tasks.

READ FULL TEXT
POST COMMENT

Comments

There are no comments yet.

Authors

page 1

page 3

page 7

page 9

page 10

Code Repositories

This week in AI

Get the week's most popular data science and artificial intelligence research sent straight to your inbox every Saturday.