Disentangled Unsupervised Image Translation via Restricted Information Flow

Abstract

Unsupervised image-to-image translation methods aim to map images from one domain into plausible examples from another domain while preserving structures shared across two domains. In the many-to-many setting, an additional guidance example from the target domain is used to determine domain-specific attributes of the generated image. In the absence of attribute annotations, methods have to infer which factors are specific to each domain from data during training. Many state-of-art methods hard-code the desired shared-vs-specific split into their architecture, severely restricting the scope of the problem. In this paper, we propose a new method that does not rely on such inductive architectural biases, and infers which attributes are domain-specific from data by constraining information flow through the network using translation honesty losses and a penalty on the capacity of domain-specific embedding. We show that the proposed method achieves consistently high manipulation accuracy across two synthetic and one natural dataset spanning a wide variety of domain-specific and shared attributes.

References in corpus (7)

• Disentangling by Factorising
• Texture Networks: Feed-forward Synthesis of Textures and Stylized Images
• Augmented CycleGAN: Learning Many-to-Many Mappings from Unpaired Data
• CycleGAN, a Master of Steganography
• Bias Correction of Learned Generative Models using Likelihood-Free Importance Weighting
• Generative Models for Effective ML on Private, Decentralized Datasets
• Adversarial Self-Defense for Cycle-Consistent GANs