Latent Normalizing Flows for Many-to-Many Cross-Domain Mappings

Abstract

Learned joint representations of images and text form the backbone of several important cross-domain tasks such as image captioning. Prior work mostly maps both domains into a common latent representation in a purely supervised fashion. This is rather restrictive, however, as the two domains follow distinct generative processes. Therefore, we propose a novel semi-supervised framework, which models shared information between domains and domain-specific information separately. The information shared between the domains is aligned with an invertible neural network. Our model integrates normalizing flow-based priors for the domain-specific information, which allows us to learn diverse many-to-many mappings between the two domains. We demonstrate the effectiveness of our model on diverse tasks, including image captioning and text-to-image synthesis.

Published as a conference paper at ICLR 2020

References in corpus (6)

• Variational Lossy Autoencoder
• TAC-GAN - Text Conditioned Auxiliary Classifier Generative Adversarial Network
• MirrorGAN: Learning Text-to-image Generation by Redescription
• Latent Normalizing Flows for Discrete Sequences
• Semantics Disentangling for Text-to-Image Generation
• M3D-GAN: Multi-Modal Multi-Domain Translation with Universal Attention

Cited by in corpus (2)

• Diverse Image Captioning with Context-Object Split Latent Spaces
• Cross-Domain Latent Modulation for Variational Transfer Learning