Unaligned Image-to-Image Translation by Learning to Reweight

Abstract

Unsupervised image-to-image translation aims at learning the mapping from the source to target domain without using paired images for training. An essential yet restrictive assumption for unsupervised image translation is that the two domains are aligned, e.g., for the selfie2anime task, the anime (selfie) domain must contain only anime (selfie) face images that can be translated to some images in the other domain. Collecting aligned domains can be laborious and needs lots of attention. In this paper, we consider the task of image translation between two unaligned domains, which may arise for various possible reasons. To solve this problem, we propose to select images based on importance reweighting and develop a method to learn the weights and perform translation simultaneously and automatically. We compare the proposed method with state-of-the-art image translation approaches and present qualitative and quantitative results on different tasks with unaligned domains. Extensive empirical evidence demonstrates the usefulness of the proposed problem formulation and the superiority of our method.

arXiv commentICCV2021

References in corpus (12)

• Conditional Generative Adversarial Nets
• GANs Trained by a Two Time-Scale Update Rule Converge to a Local Nash Equilibrium
• Classification with Noisy Labels by Importance Reweighting
• Learning to Discover Cross-Domain Relations with Generative Adversarial Networks
• Augmented CycleGAN: Learning Many-to-Many Mappings from Unpaired Data
• Unsupervised Attention-guided Image to Image Translation
• A Meta-Transfer Objective for Learning to Disentangle Causal Mechanisms
• Boundary-Seeking Generative Adversarial Networks
• A Unified Feature Disentangler for Multi-Domain Image Translation and Manipulation
• On Unifying Deep Generative Models
• Multi-mapping Image-to-Image Translation via Learning Disentanglement
• Multi-marginal Wasserstein GAN