Attribute Guided Unpaired Image-to-Image Translation with Semi-supervised Learning

Abstract

Unpaired Image-to-Image Translation (UIT) focuses on translating images among different domains by using unpaired data, which has received increasing research focus due to its practical usage. However, existing UIT schemes defect in the need of supervised training, as well as the lack of encoding domain information. In this paper, we propose an Attribute Guided UIT model termed AGUIT to tackle these two challenges. AGUIT considers multi-modal and multi-domain tasks of UIT jointly with a novel semi-supervised setting, which also merits in representation disentanglement and fine control of outputs. Especially, AGUIT benefits from two-fold: (1) It adopts a novel semi-supervised learning process by translating attributes of labeled data to unlabeled data, and then reconstructing the unlabeled data by a cycle consistency operation. (2) It decomposes image representation into domain-invariant content code and domain-specific style code. The redesigned style code embeds image style into two variables drawn from standard Gaussian distribution and the distribution of domain label, which facilitates the fine control of translation due to the continuity of both variables. Finally, we introduce a new challenge, i.e., disentangled transfer, for UIT models, which adopts the disentangled representation to translate data less related with the training set. Extensive experiments demonstrate the capacity of AGUIT over existing state-of-the-art models.

References in corpus (8)

• Conditional Image Synthesis With Auxiliary Classifier GANs
• Semi-Supervised Learning with Deep Generative Models
• Learning to Discover Cross-Domain Relations with Generative Adversarial Networks
• Unsupervised and Semi-supervised Learning with Categorical Generative Adversarial Networks
• Disentangling factors of variation in deep representations using adversarial training
• Discovering Hidden Factors of Variation in Deep Networks
• A Unified Feature Disentangler for Multi-Domain Image Translation and Manipulation
• SRPGAN: Perceptual Generative Adversarial Network for Single Image Super Resolution

Cited by in corpus (5)

• Image-to-Image Translation: Methods and Applications
• Image-to-image Translation via Hierarchical Style Disentanglement
• Attribute-guided image generation from layout
• Domain-Specific Mappings for Generative Adversarial Style Transfer
• ClsGAN: Selective Attribute Editing Model Based On Classification Adversarial Network