22
Learned D-AMP: Principled Neural Network based Compressive Image Recovery Christopher A. Metzler, Ali Mousavi, Richard G. Baraniuk Rice University NIPS 2017 Presenter: Guoyin Wang January 4, 2019 Christopher A. Metzler, Ali Mousavi, Richard G. Baraniuk LD-AMP January 4, 2019 1 / 22

Learned D-AMP: Principled Neural Network based Compressive …lcarin/Guoyin1.4.2019.pdf · 2019. 1. 4. · Learned D-AMP: Principled Neural Network based Compressive Image Recovery

  • Upload
    others

  • View
    1

  • Download
    0

Embed Size (px)

Citation preview

Page 1: Learned D-AMP: Principled Neural Network based Compressive …lcarin/Guoyin1.4.2019.pdf · 2019. 1. 4. · Learned D-AMP: Principled Neural Network based Compressive Image Recovery

Learned D-AMP: Principled Neural Network basedCompressive Image Recovery

Christopher A. Metzler, Ali Mousavi, Richard G. Baraniuk

Rice University

NIPS 2017

Presenter: Guoyin Wang

January 4, 2019

Christopher A. Metzler, Ali Mousavi, Richard G. Baraniuk (Rice)LD-AMP January 4, 2019 1 / 22

Page 2: Learned D-AMP: Principled Neural Network based Compressive …lcarin/Guoyin1.4.2019.pdf · 2019. 1. 4. · Learned D-AMP: Principled Neural Network based Compressive Image Recovery

Overview

1 Major Contribution

2 ModelProblem DescriptionAlgorithmsTraining Network

3 Experiments

Christopher A. Metzler, Ali Mousavi, Richard G. Baraniuk (Rice)LD-AMP January 4, 2019 2 / 22

Page 3: Learned D-AMP: Principled Neural Network based Compressive …lcarin/Guoyin1.4.2019.pdf · 2019. 1. 4. · Learned D-AMP: Principled Neural Network based Compressive Image Recovery

Major Contribution

Unrolling: a process to turn an iterative algorithm (D-AMP) into adeep neural net (LD-AMP) which is interpretable and maintainconvergence guarantees.Efficiently train a deep neural network.Outperform the state-of-the-art BM3D-AMP and NLR-CS algorithmsin terms of both accuracy and run time on compressive imagingproblem.

Christopher A. Metzler, Ali Mousavi, Richard G. Baraniuk (Rice)LD-AMP January 4, 2019 3 / 22

Page 4: Learned D-AMP: Principled Neural Network based Compressive …lcarin/Guoyin1.4.2019.pdf · 2019. 1. 4. · Learned D-AMP: Principled Neural Network based Compressive Image Recovery

Compressive Imaging Problem

Linear measurements y ∈ Rm of the signal of interest x ∈ Rn iscaptured via y = Ax + ε, where A ∈ Rm×n is a measurement matrixand ε ∈ Rm is noise.Image Inverse Problems: given the measurements y and themeasurement matrix A, a computational imaging system seeks torecover x .Compressive Sensing (CS): when m < n this problem is ill-posedinverse problem, and prior knowledge about x must be used torecovery the signal, such as fact that x ∈ C , where C is the set of allnatural images.

Christopher A. Metzler, Ali Mousavi, Richard G. Baraniuk (Rice)LD-AMP January 4, 2019 4 / 22

Page 5: Learned D-AMP: Principled Neural Network based Compressive …lcarin/Guoyin1.4.2019.pdf · 2019. 1. 4. · Learned D-AMP: Principled Neural Network based Compressive Image Recovery

Compressive Imaging Problem

When no measurement noise ε presented, we want to find the imagexo at the intersection of the set C and the affine subspace{x |y = Ax}The optimization formulation:

argminx‖y − Ax‖22 subject to x ∈ C . (1)

Christopher A. Metzler, Ali Mousavi, Richard G. Baraniuk (Rice)LD-AMP January 4, 2019 5 / 22

Page 6: Learned D-AMP: Principled Neural Network based Compressive …lcarin/Guoyin1.4.2019.pdf · 2019. 1. 4. · Learned D-AMP: Principled Neural Network based Compressive Image Recovery

IT and AMP

Low cost iterative algorithm are proposed to solve this problem:

Iterative Thresholding (IT) Algorithm

IT Algorithmz t = y − Ax t ,

x t+1 = η(x t + AHz t).η(·) = Thresholding non-linearity (2)

Christopher A. Metzler, Ali Mousavi, Richard G. Baraniuk (Rice)LD-AMP January 4, 2019 6 / 22

Page 7: Learned D-AMP: Principled Neural Network based Compressive …lcarin/Guoyin1.4.2019.pdf · 2019. 1. 4. · Learned D-AMP: Principled Neural Network based Compressive Image Recovery

IT and AMP

Effective noise νt = x t + AHz t − xo should be i.i.d Gaussian, but ITAlgorithm fails to maintain this property.

Approximate Message Passing (AMP) Algorithm

AMP Algorithm

bt = nz t−1〈η′(x t−1 + AHz t−1)〉m ,

z t = y − Ax t + bt ,

x t+1 = η(x t + AHz t). (3)

where 〈·〉 denotes the average of a vector, η′ represents the derivative of ηand b is Onsager correction term which removes the bias.

Christopher A. Metzler, Ali Mousavi, Richard G. Baraniuk (Rice)LD-AMP January 4, 2019 7 / 22

Page 8: Learned D-AMP: Principled Neural Network based Compressive …lcarin/Guoyin1.4.2019.pdf · 2019. 1. 4. · Learned D-AMP: Principled Neural Network based Compressive Image Recovery

D-IT and D-AMP

Nonlinear function η can be replaced by a powerful denoiser.Say xo + σz is a noisy observation of a natural image, with xo ∈ C ,z ∼ N(0, I) and σ as the standard deviation of the noise.Denoiser Dσ would simply find the point in the set C that is closestto the observation xo + σz

Dσ(xo + σz) = argminx‖xo + σz − x‖22 subject to x ∈ C . (4)

Such denoiser is a projection onto C , ideally should return estimate xcloser to xo than xo + σz .

Christopher A. Metzler, Ali Mousavi, Richard G. Baraniuk (Rice)LD-AMP January 4, 2019 8 / 22

Page 9: Learned D-AMP: Principled Neural Network based Compressive …lcarin/Guoyin1.4.2019.pdf · 2019. 1. 4. · Learned D-AMP: Principled Neural Network based Compressive Image Recovery

D-IT and D-AMP

Denoising-based IT (D-IT) Algorithm

D-IT Algorithm z t = y − Ax t ,

x t+1 = Dσ̂t (x t + AHz t). (5)

where σ̂t is the estimated standard deviation of effective noise νt . Notethat

Dσ̂t (x t + AHz t) = Dσ̂t (xo + νt) (6)

Christopher A. Metzler, Ali Mousavi, Richard G. Baraniuk (Rice)LD-AMP January 4, 2019 9 / 22

Page 10: Learned D-AMP: Principled Neural Network based Compressive …lcarin/Guoyin1.4.2019.pdf · 2019. 1. 4. · Learned D-AMP: Principled Neural Network based Compressive Image Recovery

D-IT and D-AMP

Denoising-based AMP (D-AMP) Algorithm

D-AMP Algorithmbt = z t−1divDσ̂t−1(x t−1 + AHz t−1)

m ,

z t = y − Ax t + bt ,

σ̂t = ‖z t‖2√m ,

x t+1 = Dσ̂t (x t + AHz t). (7)

‖zt‖2√m serves as a useful and accurate estimate of the standard deviation of

νt and typically, D-AMP algorithms use a Monte-Carlo approximation forthe divergence divD(·).

Christopher A. Metzler, Ali Mousavi, Richard G. Baraniuk (Rice)LD-AMP January 4, 2019 10 / 22

Page 11: Learned D-AMP: Principled Neural Network based Compressive …lcarin/Guoyin1.4.2019.pdf · 2019. 1. 4. · Learned D-AMP: Principled Neural Network based Compressive Image Recovery

D-IT and D-AMP

(a) D-IT Iterations (b) D-AMP Iterations

Figure: Reconstruction behavior of D-IT (left) and D-AMP (right) with anidealized denoiser. Because D-IT allows bias to build up over iterations of thealgorithm, its denoiser becomes ineffective at projecting onto the set C of allnatural images. The Onsager correction term enables D-AMP to avoid this issue.

Christopher A. Metzler, Ali Mousavi, Richard G. Baraniuk (Rice)LD-AMP January 4, 2019 11 / 22

Page 12: Learned D-AMP: Principled Neural Network based Compressive …lcarin/Guoyin1.4.2019.pdf · 2019. 1. 4. · Learned D-AMP: Principled Neural Network based Compressive Image Recovery

Unrolling Process

Example: IT Algorithm:

IT Algorithmz t = y − Ax t ,

x t+1 = η(x t + AHz t).η(·) = Thresholding non-linearity

Christopher A. Metzler, Ali Mousavi, Richard G. Baraniuk (Rice)LD-AMP January 4, 2019 12 / 22

Page 13: Learned D-AMP: Principled Neural Network based Compressive …lcarin/Guoyin1.4.2019.pdf · 2019. 1. 4. · Learned D-AMP: Principled Neural Network based Compressive Image Recovery

Unrolling Process

z t = y − Ax t ,

x t+1 = η(x t + AHz t).z t+1 = y − Ax t+1,

x t+2 = η(x t+1 + AHz t+1).

Feed training data, i.e., (xo, yo) pairs as label-input pairs, feedsforward through the network, calculate errors and backpropagate.The free parameters of η are leaned during training.

Christopher A. Metzler, Ali Mousavi, Richard G. Baraniuk (Rice)LD-AMP January 4, 2019 13 / 22

Page 14: Learned D-AMP: Principled Neural Network based Compressive …lcarin/Guoyin1.4.2019.pdf · 2019. 1. 4. · Learned D-AMP: Principled Neural Network based Compressive Image Recovery

Unroll D-AMP

Unroll D-AMP

bl =z l−1divDl

σ̂l−1(x l−1 + AHz l−1)m ,

z l = y − Ax l + bl ,

σ̂l = ‖z l‖2√m ,

x l+1 = Dlσ̂l (x l + AHz l). (8)

Christopher A. Metzler, Ali Mousavi, Richard G. Baraniuk (Rice)LD-AMP January 4, 2019 14 / 22

Page 15: Learned D-AMP: Principled Neural Network based Compressive …lcarin/Guoyin1.4.2019.pdf · 2019. 1. 4. · Learned D-AMP: Principled Neural Network based Compressive Image Recovery

CNN-based Denoiser

A denoiser that easily propagates gradients is needed.Denoising Convolutional Neural Network (DnCNN) satisfies this andis more accurate and far faster than competing techniques like BM3D.

Consists of 16 to 20 CNN layers.First layer uses 64 3× 3× c filters (c is number of color channels).Next 14 to 18 layers use 64 3× 3× 64 filters + batch normalization.Final layer uses c 3× 64 filters to reconstruct.

Christopher A. Metzler, Ali Mousavi, Richard G. Baraniuk (Rice)LD-AMP January 4, 2019 15 / 22

Page 16: Learned D-AMP: Principled Neural Network based Compressive …lcarin/Guoyin1.4.2019.pdf · 2019. 1. 4. · Learned D-AMP: Principled Neural Network based Compressive Image Recovery

Learned D-AMP

LDAMP Neural Network

bl =z l−1divDl

w l−1(σ̂l−1)(xl−1 + AHz l−1)

m ,

z l = y − Ax l + bl ,

σ̂l = ‖z l‖2√m ,

x l+1 = Dlw l (σ̂l )(x

l + AHz l). (9)

where Dlw l (σ̂l ) to indicate that layer l of the network uses denoiser Dl , that

this denoiser depends on its weights/biases w l , and that these weightsmay be a function of the estimated standard deviation of the noise σ̂l .

Christopher A. Metzler, Ali Mousavi, Richard G. Baraniuk (Rice)LD-AMP January 4, 2019 16 / 22

Page 17: Learned D-AMP: Principled Neural Network based Compressive …lcarin/Guoyin1.4.2019.pdf · 2019. 1. 4. · Learned D-AMP: Principled Neural Network based Compressive Image Recovery

Leaned D-AMP

Figure: Two layers of the LDAMP neural network. When used with the DnCNNdenoiser, each denoiser block is a 16 to 20 convolutional-layer neural network.

LD-IT network is nearly identical but does not compute Onsagercorrection term.

Christopher A. Metzler, Ali Mousavi, Richard G. Baraniuk (Rice)LD-AMP January 4, 2019 17 / 22

Page 18: Learned D-AMP: Principled Neural Network based Compressive …lcarin/Guoyin1.4.2019.pdf · 2019. 1. 4. · Learned D-AMP: Principled Neural Network based Compressive Image Recovery

Training LDIT and LDAMP

End-to-end training: Train all the weights of the networksimultaneously.Layer-by-layer training: Train a 1 AMP layer network to recover thesignal, fix these weights, add an AMP layer, and repeat until we havetrained a 10 layer network.Denoiser-by-denoiser training: Decouple the denoisers from therest of the network and train each on denoising problems at differentnoise levels.Later-by-layer training and denoiser-by-denoiser training for LDAMPare found minimum-mean-squared-error (MMSE) optimal.

Christopher A. Metzler, Ali Mousavi, Richard G. Baraniuk (Rice)LD-AMP January 4, 2019 18 / 22

Page 19: Learned D-AMP: Principled Neural Network based Compressive …lcarin/Guoyin1.4.2019.pdf · 2019. 1. 4. · Learned D-AMP: Principled Neural Network based Compressive Image Recovery

Experiments

Datasets Berkeley’s BSD-500 dataset, 400 images for training, 50 forvalidation, and 50 for testing.Evaluation Metric PSNR = 10 log10( 2552

mean((x̂−xo)2)) when the pixelrange is 0 to 255.

Christopher A. Metzler, Ali Mousavi, Richard G. Baraniuk (Rice)LD-AMP January 4, 2019 19 / 22

Page 20: Learned D-AMP: Principled Neural Network based Compressive …lcarin/Guoyin1.4.2019.pdf · 2019. 1. 4. · Learned D-AMP: Principled Neural Network based Compressive Image Recovery

Results

(a) Original Image (b) TVAL3 (26.4 dB, 6.85 sec) (c) BM3D-AMP (27.2 dB,75.04 sec)

(d) LDAMP (28.1 dB, 1.22sec)

Figure: Reconstructions of 512× 512 Boat test image sampled at a rate ofmn = 0.05 using coded diffraction pattern measurements and no measurementnoise. LDAMP’s reconstructions are noticeably cleaner and far faster than thecompeting methods.

Christopher A. Metzler, Ali Mousavi, Richard G. Baraniuk (Rice)LD-AMP January 4, 2019 20 / 22

Page 21: Learned D-AMP: Principled Neural Network based Compressive …lcarin/Guoyin1.4.2019.pdf · 2019. 1. 4. · Learned D-AMP: Principled Neural Network based Compressive Image Recovery

Results

Table: PSNRs and run times (sec) of 128× 128 reconstructions withi.i.d. Gaussian measurements and no measurement noise at various sampling rates.

Methodmn = 0.10 m

n = 0.15 mn = 0.20 m

n = 0.25

PSNR Time PSNR Time PSNR Time PSNR Time

TVAL3 21.5 2.2 22.8 2.9 24.0 3.6 25.0 4.3BM3D-AMP 23.1 4.8 25.1 4.4 26.6 4.2 27.9 4.1LDIT 20.1 0.3 20.7 0.4 21.1 0.4 21.7 0.5LDAMP 23.7 0.4 25.7 0.5 27.2 0.5 28.5 0.6NLR-CS 23.2 85.9 25.2 104.0 26.8 124.4 28.2 146.3

Christopher A. Metzler, Ali Mousavi, Richard G. Baraniuk (Rice)LD-AMP January 4, 2019 21 / 22

Page 22: Learned D-AMP: Principled Neural Network based Compressive …lcarin/Guoyin1.4.2019.pdf · 2019. 1. 4. · Learned D-AMP: Principled Neural Network based Compressive Image Recovery

Results

Table: PSNRs and run times (sec) of 128× 128 reconstructions with codeddiffraction measurements and no measurement noise at various sampling rates.

Methodmn = 0.10 m

n = 0.15 mn = 0.20 m

n = 0.25

PSNR Time PSNR Time PSNR Time PSNR Time

TVAL3 24.0 0.52 26.0 0.46 27.9 0.43 29.7 0.41BM3D-AMP 23.8 4.55 25.7 4.29 27.5 3.67 29.1 3.40LDIT 22.9 0.14 25.6 0.14 27.4 0.14 28.9 0.14LDAMP 25.3 0.26 27.4 0.26 28.9 0.27 30.5 0.26NLR-CS 21.6 87.82 22.8 87.43 25.1 87.18 26.4 86.87

Christopher A. Metzler, Ali Mousavi, Richard G. Baraniuk (Rice)LD-AMP January 4, 2019 22 / 22