Resembled Generative Adversarial Networks: Two Domains with Similar Attributes
This addresses a limitation in GANs for cross-domain generation without requiring input images, though it appears incremental over prior work like CoGAN.
The paper tackles the problem of generating data for two different domains simultaneously while ensuring they resemble each other, proposing Resembled GAN to handle a wide range of structural and semantic similarities, with experimental verification on various datasets.
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.