Unsupervised Multi-Domain Image Translation with Domain-Specific Encoders/Decoders

Abstract

Unsupervised Image-to-Image Translation achieves spectacularly advanced developments nowadays. However, recent approaches mainly focus on one model with two domains, which may face heavy burdens with large cost of $O(n^2)$ training time and model parameters, under such a requirement that $n$ domains are freely transferred to each other in a general setting. To address this problem, we propose a novel and unified framework named Domain-Bank, which consists of a global shared auto-encoder and $n$ domain-specific encoders/decoders, assuming that a universal shared-latent sapce can be projected. Thus, we yield $O(n)$ complexity in model parameters along with a huge reduction of the time budgets. Besides the high efficiency, we show the comparable (or even better) image translation results over state-of-the-arts on various challenging unsupervised image translation tasks, including face image translation, fashion-clothes translation and painting style translation. We also apply the proposed framework to domain adaptation and achieve state-of-the-art performance on digit benchmark datasets. Further, thanks to the explicit representation of the domain-specific decoders as well as the universal shared-latent space, it also enables us to conduct incremental learning to add a new domain encoder/decoder. Linear combination of different domains' representations is also obtained by fusing the corresponding decoders.

References in corpus (12)

• Conditional Generative Adversarial Nets
• Unsupervised Representation Learning with Deep Convolutional Generative Adversarial Networks
• Fashion-MNIST: a Novel Image Dataset for Benchmarking Machine Learning Algorithms
• Unpaired Image-to-Image Translation using Cycle-Consistent Adversarial Networks
• Deep Unsupervised Learning using Nonequilibrium Thermodynamics
• Improved Techniques for Training GANs
• Autoencoding beyond pixels using a learned similarity metric
• Invertible Conditional GANs for image editing
• Unsupervised Cross-Domain Image Generation
• Auxiliary Deep Generative Models
• Improving Variational Inference with Inverse Autoregressive Flow
• StyleBank: An Explicit Representation for Neural Image Style Transfer

Cited by in corpus (4)

• Multimodal Unsupervised Image-to-Image Translation
• Few-Shot Unsupervised Image-to-Image Translation
• STGAN: A Unified Selective Transfer Network for Arbitrary Image Attribute Editing
• COCO-FUNIT: Few-Shot Unsupervised Image Translation with a Content Conditioned Style Encoder