Langevin Cooling for Domain Translation

Abstract

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.

References in corpus (18)

• Very Deep Convolutional Networks for Large-Scale Image Recognition
• Batch Normalization: Accelerating Deep Network Training by Reducing Internal Covariate Shift
• PyTorch: An Imperative Style, High-Performance Deep Learning Library
• A Simple Framework for Contrastive Learning of Visual Representations
• Google's Neural Machine Translation System: Bridging the Gap between Human and Machine Translation
• Bootstrap your own latent: A new approach to self-supervised Learning
• Methods for Interpreting and Understanding Deep Neural Networks
• Improved Baselines with Momentum Contrastive Learning
• Wide Residual Networks
• Unsupervised Data Augmentation for Consistency Training
• Learning to Discover Cross-Domain Relations with Generative Adversarial Networks
• Dual Learning for Machine Translation
• GAN Augmentation: Augmenting Training Data using Generative Adversarial Networks
• Normalizing Flows for Probabilistic Modeling and Inference
• Unsupervised Attention-guided Image to Image Translation
• Generalized Denoising Auto-Encoders as Generative Models
• Bayesian Inference for Large Scale Image Classification
• Robustifying Models Against Adversarial Attacks by Langevin Dynamics