On Conditioning GANs to Hierarchical Ontologies

by   Hamid Eghbal-zadeh, et al.
Software Competence Center Hagenberg
Johannes Kepler University Linz

The recent success of Generative Adversarial Networks (GAN) is a result of their ability to generate high quality images from a latent vector space. An important application is the generation of images from a text description, where the text description is encoded and further used in the conditioning of the generated image. Thus the generative network has to additionally learn a mapping from the text latent vector space to a highly complex and multi-modal image data distribution, which makes the training of such models challenging. To handle the complexities of fashion image and meta data, we propose Ontology Generative Adversarial Networks (O-GANs) for fashion image synthesis that is conditioned on an hierarchical fashion ontology in order to improve the image generation fidelity. We show that the incorporation of the ontology leads to better image quality as measured by Fréchet Inception Distance and Inception Score. Additionally, we show that the O-GAN achieves better conditioning results evaluated by implicit similarity between the text and the generated image.


Pixel-wise Conditioned Generative Adversarial Networks for Image Synthesis and Completion

Generative Adversarial Networks (GANs) have proven successful for unsupe...

High Quality Bidirectional Generative Adversarial Networks

Generative adversarial networks (GANs) have achieved outstanding success...

Is Generator Conditioning Causally Related to GAN Performance?

Recent work (Pennington et al, 2017) suggests that controlling the entir...

Factor Decomposed Generative Adversarial Networks for Text-to-Image Synthesis

Prior works about text-to-image synthesis typically concatenated the sen...

On the Evaluation of Conditional GANs

Conditional Generative Adversarial Networks (cGANs) are finding increasi...

Exploring Sparse MoE in GANs for Text-conditioned Image Synthesis

Due to the difficulty in scaling up, generative adversarial networks (GA...

Logo Synthesis and Manipulation with Clustered Generative Adversarial Networks

Designing a logo for a new brand is a lengthy and tedious back-and-forth...

Please sign up or login with your details

Forgot password? Click here to reset