Resembled Generative Adversarial Networks: Two Domains with Similar Attributes

Abstract

We propose a novel algorithm, namely Resembled Generative Adversarial Networks (GAN), that generates two different domain data simultaneously where they resemble each other. Although recent GAN algorithms achieve the great success in learning the cross-domain relationship, their application is limited to domain transfers, which requires the input image. The first attempt to tackle the data generation of two domains was proposed by CoGAN. However, their solution is inherently vulnerable for various levels of domain similarities. Unlike CoGAN, our Resembled GAN implicitly induces two generators to match feature covariance from both domains, thus leading to share semantic attributes. Hence, we effectively handle a wide range of structural and semantic similarities between various two domains. Based on experimental analysis on various datasets, we verify that the proposed algorithm is effective for generating two domains with similar attributes.

arXiv commentAccepted at BMVC 2018

References in corpus (11)

• Unsupervised Representation Learning with Deep Convolutional Generative Adversarial Networks
• Prototypical Networks for Few-shot Learning
• Unpaired Image-to-Image Translation using Cycle-Consistent Adversarial Networks
• Conditional Image Synthesis With Auxiliary Classifier GANs
• Toward Multimodal Image-to-Image Translation
• Density estimation using Real NVP
• Unsupervised Image-to-Image Translation Networks
• Variational Approaches for Auto-Encoding Generative Adversarial Networks
• Many Paths to Equilibrium: GANs Do Not Need to Decrease a Divergence At Every Step
• MGGAN: Solving Mode Collapse using Manifold Guided Training
• Feature Transfer Learning for Deep Face Recognition with Under-Represented Data