Deep probabilistic subsampling for task-adaptive compressed sensing

The field of deep learning is commonly concerned with optimizing predictive models using large pre-acquired datasets of densely sampled datapoints or signals. In this work, we demonstrate that the deep learning paradigm can be extended to incorporate a subsampling scheme that is jointly optimized under a desired minimum sample rate. We present Deep Probabilistic Subsampling (DPS), a widely applicable framework for task-adaptive compressed sensing that enables end-to end optimization of an optimal subset of signal samples with a subsequent model that performs a required task. We demonstrate strong performance on reconstruction and classification tasks of a toy dataset, MNIST, and CIFAR10 under stringent subsampling rates in both the pixel and the spatial frequency domain. Due to the task-agnostic nature of the framework, DPS is directly applicable to all real-world domains that benefit from sample rate reduction.

[1]  B. Brookes,et al.  Statistical Theory of Extreme Values and Some Practical Applications , 1955, The Mathematical Gazette.

[2]  Kurt Hornik,et al.  Neural networks and principal component analysis: Learning from examples without local minima , 1989, Neural Networks.

[3]  Geoffrey E. Hinton,et al.  Autoencoders, Minimum Description Length and Helmholtz Free Energy , 1993, NIPS.

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

[5]  Ronald J. Williams,et al.  Simple Statistical Gradient-Following Algorithms for Connectionist Reinforcement Learning , 2004, Machine Learning.

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

[7]  Richard G. Baraniuk,et al.  Compressive Sensing , 2008, Computer Vision, A Reference Guide.

[8]  Lei Zhu,et al.  Compressed sensing based cone-beam computed tomography reconstruction with a first-order methoda). , 2010, Medical physics.

[9]  Yoshua Bengio,et al.  Understanding the difficulty of training deep feedforward neural networks , 2010, AISTATS.

[10]  Gitta Kutyniok,et al.  1 . 2 Sparsity : A Reasonable Assumption ? , 2012 .

[11]  Felix J. Herrmann,et al.  Fighting the Curse of Dimensionality: Compressive Sensing in Exploration Seismology , 2012, IEEE Signal Processing Magazine.

[12]  D. L. Donoho,et al.  Compressed sensing , 2006, IEEE Trans. Inf. Theory.

[13]  Yonina C. Eldar,et al.  Fourier-domain beamforming: the path to compressed ultrasound imaging , 2013, IEEE Transactions on Ultrasonics, Ferroelectrics, and Frequency Control.

[14]  Yoshua Bengio,et al.  Show, Attend and Tell: Neural Image Caption Generation with Visual Attention , 2015, ICML.

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

[16]  Yoshua Bengio,et al.  Neural Machine Translation by Jointly Learning to Align and Translate , 2014, ICLR.

[17]  Alexander M. Rush,et al.  Structured Attention Networks , 2017, ICLR.

[18]  Lukasz Kaiser,et al.  Attention is All you Need , 2017, NIPS.

[19]  Yee Whye Teh,et al.  The Concrete Distribution: A Continuous Relaxation of Discrete Random Variables , 2016, ICLR.

[20]  Christian Ledig,et al.  Photo-Realistic Single Image Super-Resolution Using a Generative Adversarial Network , 2016, 2017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR).

[21]  Yann Ollivier,et al.  The Description Length of Deep Learning models , 2018, NeurIPS.

[22]  Morteza Mardani,et al.  Neural Proximal Gradient Descent for Compressive Imaging , 2018, NeurIPS.

[23]  Stefan Roth,et al.  Neural Nearest Neighbors Networks , 2018, NeurIPS.

[24]  Bruce R. Rosen,et al.  Image reconstruction by domain-transform manifold learning , 2017, Nature.

[25]  A. Bronstein,et al.  PILOT: Physics-Informed Learned Optimal Trajectories for Accelerated MRI , 2019, ArXiv.

[26]  Mert R. Sabuncu,et al.  Learning-based Optimization of the Under-sampling Pattern in MRI , 2019, IPMI.

[27]  Taco S. Cohen,et al.  Video Compression With Rate-Distortion Autoencoders , 2019, 2019 IEEE/CVF International Conference on Computer Vision (ICCV).

[28]  Afshin Rostamizadeh,et al.  Learning a Compressed Sensing Measurement Matrix via Gradient Unrolling , 2018, ICML.

[29]  Max Welling,et al.  Stochastic Beams and Where to Find Them: The Gumbel-Top-k Trick for Sampling Sequences Without Replacement , 2019, ICML.

[30]  Stefano Ermon,et al.  Reparameterizable Subset Sampling via Continuous Relaxations , 2019, IJCAI.

[31]  Richard G. Baraniuk,et al.  A Data-Driven and Distributed Approach to Sparse Signal Representation and Recovery , 2019, International Conference on Learning Representations.