Learning to Transfer: Unsupervised Meta Domain Translation
arXiv:1906.00181
Abstract
Unsupervised domain translation has recently achieved impressive performance with Generative Adversarial Network (GAN) and sufficient (unpaired) training data. However, existing domain translation frameworks form in a disposable way where the learning experiences are ignored and the obtained model cannot be adapted to a new coming domain. In this work, we take on unsupervised domain translation problems from a meta-learning perspective. We propose a model called Meta-Translation GAN (MT-GAN) to find good initialization of translation models. In the meta-training procedure, MT-GAN is explicitly trained with a primary translation task and a synthesized dual translation task. A cycle-consistency meta-optimization objective is designed to ensure the generalization ability. We demonstrate effectiveness of our model on ten diverse two-domain translation tasks and multiple face identity translation tasks. We show that our proposed approach significantly outperforms the existing domain translation methods when each domain contains no more than ten training samples.
arXiv comment10 pages, 2 figures
References in corpus (16)
- Adam: A Method for Stochastic Optimization
- Very Deep Convolutional Networks for Large-Scale Image Recognition
- Conditional Generative Adversarial Nets
- Unsupervised Representation Learning with Deep Convolutional Generative Adversarial Networks
- Model-Agnostic Meta-Learning for Fast Adaptation of Deep Networks
- Prototypical Networks for Few-shot Learning
- GANs Trained by a Two Time-Scale Update Rule Converge to a Local Nash Equilibrium
- Learning a Probabilistic Latent Space of Object Shapes via 3D Generative-Adversarial Modeling
- A Simple Neural Attentive Meta-Learner
- Learning to Discover Cross-Domain Relations with Generative Adversarial Networks
- Dual Learning for Machine Translation
- Unsupervised Learning via Meta-Learning
- One-Shot Unsupervised Cross Domain Translation
- A Unified Feature Disentangler for Multi-Domain Image Translation and Manipulation
- Meta-Learning Update Rules for Unsupervised Representation Learning
- Optimal Unsupervised Domain Translation