Quaternion Generative Adversarial Networks

Abstract

Latest Generative Adversarial Networks (GANs) are gathering outstanding results through a large-scale training, thus employing models composed of millions of parameters requiring extensive computational capabilities. Building such huge models undermines their replicability and increases the training instability. Moreover, multi-channel data, such as images or audio, are usually processed by realvalued convolutional networks that flatten and concatenate the input, often losing intra-channel spatial relations. To address these issues related to complexity and information loss, we propose a family of quaternion-valued generative adversarial networks (QGANs). QGANs exploit the properties of quaternion algebra, e.g., the Hamilton product, that allows to process channels as a single entity and capture internal latent relations, while reducing by a factor of 4 the overall number of parameters. We show how to design QGANs and to extend the proposed approach even to advanced models.We compare the proposed QGANs with real-valued counterparts on several image generation benchmarks. Results show that QGANs are able to obtain better FID scores than real-valued GANs and to generate visually pleasing images. Furthermore, QGANs save up to 75% of the training parameters. We believe these results may pave the way to novel, more accessible, GANs capable of improving performance and saving computational resources.

arXiv commentAccepted as a Chapter for the SPRINGER book "Generative Adversarial Learning: Architectures and Applications"

References in corpus (14)

• Batch Normalization: Accelerating Deep Network Training by Reducing Internal Covariate Shift
• Auto-Encoding Variational Bayes
• Unsupervised Representation Learning with Deep Convolutional Generative Adversarial Networks
• GANs Trained by a Two Time-Scale Update Rule Converge to a Local Nash Equilibrium
• Large Scale GAN Training for High Fidelity Natural Image Synthesis
• Spectral Normalization for Generative Adversarial Networks
• Self-Attention Generative Adversarial Networks
• A Review on Generative Adversarial Networks: Algorithms, Theory, and Applications
• Quaternion Involutions
• Quaternion Convolutional Neural Networks for Heterogeneous Image Processing
• Quaternion Recurrent Neural Networks
• Quaternion Convolutional Neural Networks for Detection and Localization of 3D Sound Events
• Lipschitz Generative Adversarial Nets
• Compressing deep quaternion neural networks with targeted regularization

Cited by in corpus (4)

• PHNNs: Lightweight Neural Networks via Parameterized Hypercomplex Convolutions
• Learning Speech Emotion Representations in the Quaternion Domain
• Color Image Inpainting via Robust Pure Quaternion Matrix Completion: Error Bound and Weighted Loss
• Hypercomplex Image-to-Image Translation