Langevin Cooling for Domain Translation

by   Vignesh Srinivasan, et al.

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.


page 1

page 3

page 7

page 9

page 10


Crossing-Domain Generative Adversarial Networks for Unsupervised Multi-Domain Image-to-Image Translation

State-of-the-art techniques in Generative Adversarial Networks (GANs) ha...

Image-to-image translation for cross-domain disentanglement

Deep image translation methods have recently shown excellent results, ou...

AdaFlow: Domain-Adaptive Density Estimator with Application to Anomaly Detection and Unpaired Cross-Domain Translation

We tackle unsupervised anomaly detection (UAD), a problem of detecting d...

Cross-lingual Visual Pre-training for Multimodal Machine Translation

Pre-trained language models have been shown to improve performance in ma...

Mix and match networks: encoder-decoder alignment for zero-pair image translation

We address the problem of image translation between domains or modalitie...

Invertible Autoencoder for domain adaptation

The unsupervised image-to-image translation aims at finding a mapping be...

Augmented CycleGAN: Learning Many-to-Many Mappings from Unpaired Data

Learning inter-domain mappings from unpaired data can improve performanc...

Code Repositories