Learning Generative Models of Structured Signals from Their Superposition Using GANs with Application to Denoising and Demixing

2019/02/12 by Mohammadreza Soltani, Soltani, Mohammadreza, Swayambhoo Jain +3
Computer Science · Physics and Astronomy · #FOS: Computer and information sciences #Generative Adversarial Networks and Image Synthesis #Image and Signal Denoising Methods #Machine Learning (cs.LG) #Machine Learning (stat.ML) #Model Reduction and Neural Networks

paper · pdf · doi:10.48550/arxiv.1902.04664

openalex publication_date 2019/02/12 · openalex created_date 2019/02/21 · openalex updated_date 2026/07/28

Abstract

Recently, Generative Adversarial Networks (GANs) have emerged as a popular alternative for modeling complex high dimensional distributions. Most of the existing works implicitly assume that the clean samples from the target distribution are easily available. However, in many applications, this assumption is violated. In this paper, we consider the observation setting when the samples from target distribution are given by the superposition of two structured components and leverage GANs for learning the structure of the components. We propose two novel frameworks: denoising-GAN and demixing-GAN. The denoising-GAN assumes access to clean samples from the second component and try to learn the other distribution, whereas demixing-GAN learns the distribution of the components at the same time. Through extensive numerical experiments, we demonstrate that proposed frameworks can generate clean samples from unknown distributions, and provide competitive performance in tasks such as denoising, demixing, and compressive sensing.

Citations

• Auto-Encoding Variational Bayes
• Simultaneous cartoon and texture image inpainting using morphological component analysis (MCA)
• Atomic Decomposition by Basis Pursuit
• Approximation Algorithms for Model-Based Compressive Sensing
• Robust principal component analysis?
• Image Denoising Via Sparse and Redundant Representations Over Learned Dictionaries
• Learning a Probabilistic Latent Space of Object Shapes via 3D Generative-Adversarial Modeling
• NIPS 2016 Tutorial: Generative Adversarial Networks
• Iterative Thresholding for Demixing Structured Superpositions in High\n Dimensions
• Compressed Sensing using Generative Models
• BEGAN: Boundary Equilibrium Generative Adversarial Networks
• Fashion-MNIST: a Novel Image Dataset for Benchmarking Machine Learning Algorithms
• InfoGAN: Interpretable Representation Learning by Information Maximizing Generative Adversarial Nets

Related

• Structure-preserving GANs
• Ways of Conditioning Generative Adversarial Networks
• Forward Super-Resolution: How Can GANs Learn Hierarchical Generative Models for Real-World Distributions
• Leveraging Contaminated Datasets to Learn Clean-Data Distribution with Purified Generative Adversarial Networks
• Generative Adversarial Networks (GANs): An Overview of Theoretical Model, Evaluation Metrics, and Recent Developments