Learning Generative Prior with Latent Space Sparsity Constraints
Not on the map. Why?
Abstract (arXiv)
We address the problem of compressed sensing using a deep generative prior model and consider both linear and learned nonlinear sensing mechanisms, where the nonlinear one involves either a fully connected neural network or a convolutional neural network. Recently, it has been argued that the distribution of natural images do not lie in a single manifold but rather lie in a union of several submanifolds. We propose a sparsity-driven latent space sampling (SDLSS) framework and develop a proximal meta-learning (PML) algorithm to enforce sparsity in the latent space. SDLSS allows the range-space of the generator to be considered as a union-of-submanifolds. We also derive the sample complexity bounds within the SDLSS framework for the linear measurement model. The results demonstrate that for a higher degree of compression, the SDLSS method is more efficient than the state-of-the-art method. We first consider a comparison between linear and nonlinear sensing mechanisms on Fashion-MNIST dataset and show that the learned nonlinear version is superior to the linear one. Subsequent comparisons with the deep compressive sensing (DCS) framework proposed in the literature are reported. We also consider the effect of the dimension of the latent space and the sparsity factor in validating the SDLSS framework. Performance quantification is carried out by employing three objective metrics: peak signal-to-noise ratio (PSNR), structural similarity index metric (SSIM), and reconstruction error (RE).
Key facts. Cited by 1 paper in the map (data through 14 Oct 2026). Builds on 24 of its 51 references that are in the map. First posted on arXiv 25 May 2021.
Builds on
24 of 51 references.
References · 24
- 2017Model-Agnostic Meta-Learning for Fast Adaptation of Deep Networkscited by 4,897
- 2017Fashion-MNIST: a Novel Image Dataset for Benchmarking Machine Learning Algorithmscited by 4,349
- 2014Deep Learning Face Attributes in the Wildcited by 3,693
- 2015Unsupervised Representation Learning with Deep Convolutional Generative Adversarial Networkscited by 2,054
- 2017Deep Image Priorcited by 1,098
- 2016InfoGAN: Interpretable Representation Learning by Information Maximizing Generative Adversarial Netscited by 860
- 2017Compressed Sensing using Generative Modelscited by 339
- 2019Image Processing Using Multi-Code GAN Priorcited by 185
- 2018Deep Decoder: Concise Image Representations from Untrained Non-convolutional Networkscited by 120
- 2019Invertible generative models for inverse problems: mitigating representation error and dataset biascited by 94
- 2017DeLiGAN : Generative Adversarial Networks for Diverse and Limited Datacited by 77
- 2018Solving Linear Inverse Problems Using GAN Priors: An Algorithm with Provable Guaranteescited by 58
12 more
- 2019Deep Compressed Sensingcited by 46
- 2017Global Guarantees for Enforcing Deep Generative Priors by Empirical Riskcited by 37
- 2019Image-Adaptive GAN based Reconstructioncited by 36
- 2018Modeling Sparse Deviations for Compressed Sensing using Generative Modelscited by 33
- 2018Disconnected Manifold Learning for Generative Adversarial Networkscited by 27
- 2019Information-Theoretic Lower Bounds for Compressive Sensing with Generative Modelscited by 25
- 2020Compressible Latent-Space Invertible Networks for Generative Model-Constrained Image Reconstructioncited by 19
- 2018Learning Sparse Latent Representations with the Deep Copula Information Bottleneckcited by 9
- 2018Latent Convolutional Modelscited by 6
- 2019Fast Compressive Sensing Recovery Using Generative Models with Structured Latent Variablescited by 5
- 2015Learning optimal nonlinearities for iterative thresholding algorithmscited by 4
- 2020Subspace Embeddings Under Nonlinear Transformationscited by 4
Built on by
Citing papers per year: 2024: 1.
1 paper.