Task-Aware Compressed Sensing with Generative Adversarial Networks

In recent years, neural network approaches have been widely adopted for machine learning tasks, with applications in computer vision. More recently, unsupervised generative models based on neural networks have been successfully applied to model data distributions via low-dimensional latent spaces. In this paper, we use Generative Adversarial Networks (GANs) to impose structure in compressed sensing problems, replacing the usual sparsity constraint. We propose to train the GANs in a task-aware fashion, specifically for reconstruction tasks. We also show that it is possible to train our model without using any (or much) non-compressed data. Finally, we show that the latent space of the GAN carries discriminative information and can further be regularized to generate input features for general inference tasks. We demonstrate the effectiveness of our method on a variety of reconstruction and classification problems.

[1]  Max Welling,et al.  Auto-Encoding Variational Bayes , 2013, ICLR.

[2]  Trevor Darrell,et al.  Adversarial Feature Learning , 2016, ICLR.

[3]  Xiaogang Wang,et al.  Deep Learning Face Attributes in the Wild , 2014, 2015 IEEE International Conference on Computer Vision (ICCV).

[4]  Augustus Odena,et al.  Semi-Supervised Learning with Generative Adversarial Networks , 2016, ArXiv.

[5]  Rémi Munos,et al.  Compressed Least-Squares Regression , 2009, NIPS.

[6]  Aaron C. Courville,et al.  Discriminative Regularization for Generative Models , 2016, ArXiv.

[7]  Marc Teboulle,et al.  A Fast Iterative Shrinkage-Thresholding Algorithm for Linear Inverse Problems , 2009, SIAM J. Imaging Sci..

[8]  Alexandros G. Dimakis,et al.  Compressed Sensing using Generative Models , 2017, ICML.

[9]  Yoshua Bengio,et al.  Generative Adversarial Nets , 2014, NIPS.

[10]  Thomas S. Huang,et al.  Image Super-Resolution Via Sparse Representation , 2010, IEEE Transactions on Image Processing.

[11]  Tom Goldstein,et al.  The Split Bregman Method for L1-Regularized Problems , 2009, SIAM J. Imaging Sci..

[12]  Pieter Abbeel,et al.  InfoGAN: Interpretable Representation Learning by Information Maximizing Generative Adversarial Nets , 2016, NIPS.

[13]  Simon Osindero,et al.  Conditional Generative Adversarial Nets , 2014, ArXiv.

[14]  Wotao Yin,et al.  Bregman Iterative Algorithms for (cid:2) 1 -Minimization with Applications to Compressed Sensing ∗ , 2008 .

[15]  Richard G. Baraniuk,et al.  The smashed filter for compressive classification and target recognition , 2007, Electronic Imaging.

[16]  Yoshua Bengio,et al.  Gradient-based learning applied to document recognition , 1998, Proc. IEEE.

[17]  Kyoung Mu Lee,et al.  Accurate Image Super-Resolution Using Very Deep Convolutional Networks , 2015, 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR).

[18]  Pavan K. Turaga,et al.  Direct inference on compressive measurements using convolutional neural networks , 2016, 2016 IEEE International Conference on Image Processing (ICIP).

[19]  E. Candès,et al.  Stable signal recovery from incomplete and inaccurate measurements , 2005, math/0503066.

[20]  Roland Vollgraf,et al.  Fashion-MNIST: a Novel Image Dataset for Benchmarking Machine Learning Algorithms , 2017, ArXiv.

[21]  Jimmy Ba,et al.  Adam: A Method for Stochastic Optimization , 2014, ICLR.

[22]  Soumith Chintala,et al.  Unsupervised Representation Learning with Deep Convolutional Generative Adversarial Networks , 2015, ICLR.

[23]  R. Calderbank.  Compressed Learning : Universal Sparse Dimensionality Reduction and Learning in the Measurement Domain , 2009 .

[24]  Piotr Indyk,et al.  A Nearly-Linear Time Framework for Graph-Structured Sparsity , 2015, ICML.

[25]  D. Donoho,et al.  Sparse MRI: The application of compressed sensing for rapid MR imaging , 2007, Magnetic resonance in medicine.

[26]  Xiaoou Tang,et al.  Image Super-Resolution Using Deep Convolutional Networks , 2014, IEEE Transactions on Pattern Analysis and Machine Intelligence.

[27]  Jost Tobias Springenberg,et al.  Unsupervised and Semi-supervised Learning with Categorical Generative Adversarial Networks , 2015, ICLR.

[28]  Aaron C. Courville,et al.  Adversarially Learned Inference , 2016, ICLR.

[29]  José M. Bioucas-Dias,et al.  A New TwIST: Two-Step Iterative Shrinkage/Thresholding Algorithms for Image Restoration , 2007, IEEE Transactions on Image Processing.

[30]  Y. C. Pati,et al.  Orthogonal matching pursuit: recursive function approximation with applications to wavelet decomposition , 1993, Proceedings of 27th Asilomar Conference on Signals, Systems and Computers.

[31]  Volkan Cevher,et al.  Model-Based Compressive Sensing , 2008, IEEE Transactions on Information Theory.

[32]  Volkan Cevher,et al.  Compressive Sensing for Background Subtraction , 2008, ECCV.

[33]  Ting Sun,et al.  Single-pixel imaging via compressive sampling , 2008, IEEE Signal Process. Mag..

[34]  Emmanuel J. Candès,et al.  Robust uncertainty principles: exact signal reconstruction from highly incomplete frequency information , 2004, IEEE Transactions on Information Theory.

[35]  Subarna Tripathi,et al.  Precise Recovery of Latent Vectors from Generative Adversarial Networks , 2017, ICLR.

[36]  Yann LeCun,et al.  Learning a similarity metric discriminatively, with application to face verification , 2005, 2005 IEEE Computer Society Conference on Computer Vision and Pattern Recognition (CVPR'05).

[37]  David L Donoho,et al.  Compressed sensing , 2006, IEEE Transactions on Information Theory.

[38]  Jian Wang,et al.  Reconstruction-free inference on compressive measurements , 2015, 2015 IEEE Conference on Computer Vision and Pattern Recognition Workshops (CVPRW).

[39]  E.J. Candes,et al.  An Introduction To Compressive Sampling , 2008, IEEE Signal Processing Magazine.

[40]  P. Bickel,et al.  SIMULTANEOUS ANALYSIS OF LASSO AND DANTZIG SELECTOR , 2008, 0801.1095.

[41]  M. Lustig,et al.  Compressed Sensing MRI , 2008, IEEE Signal Processing Magazine.