Algorithm Unrolling: Interpretable, Efficient Deep Learning for Signal and Image Processing

Monga, Vishal; Li, Yuelong; Eldar, Yonina C.

doi:10.1109/msp.2020.3016905

Cited by 845 publications

(483 citation statements)

References 75 publications

Supporting

Mentioning

482

Contrasting

Unclassified

Order By: Relevance

“…Specifically, the first 20 samples constitute the training set and the rest constitute the test set. Later experiments will demonstrate that a small training set is adequate as unfolded deep networks have the potential to developing efficient high-performance architectures from reasonably sized training sets [22].…”

Section: Resultsmentioning

confidence: 98%

“…To tackle the aforementioned problems, we modified 2D-ADMM and expanded it into 2D-ADN. There are similarities between deep networks and iterative algorithms [22] such as 2D-ADMM. Particularly, the matrix multiplication is similar to the linear mapping of the deep network, the shrinkage function is similar to the nonlinear operation, and the adjustable parameters are similar to network parameters.…”

Section: Structure Of 2d-adnmentioning

confidence: 99%

“…Such methods effectively solve the difficulties in: (1) setting proper parameters for model-driven methods; (2) clearly explaining the physical meaning of the network; and (3) generating a large number of training samples to avoid overfitting for data-driven methods. A common technique to expand the modeldriven methods is unrolling [22], which utilizes a finite-layer hierarchical architecture to implement iterations. As a typical imaging network, the deep ADMM network [23] uses measured data for effective training, which is usually limited due to observation conditions, and autofocusing is not considered for sparse aperture ISAR imaging.…”

Section: Introductionmentioning

confidence: 99%

See 2 more Smart Citations

High-Resolution ISAR Imaging and Autofocusing via 2D-ADMM-Net

Bai

Zhou

2021

Remote Sensing

View full text Add to dashboard Cite

A deep-learning architecture, dubbed as the 2D-ADMM-Net (2D-ADN), is proposed in this article. It provides effective high-resolution 2D inverse synthetic aperture radar (ISAR) imaging under scenarios of low SNRs and incomplete data, by combining model-based sparse reconstruction and data-driven deep learning. Firstly, mapping from ISAR images to their corresponding echoes in the wavenumber domain is derived. Then, a 2D alternating direction method of multipliers (ADMM) is unrolled and generalized to a deep network, where all adjustable parameters in the reconstruction layers, nonlinear transform layers, and multiplier update layers are learned by an end-to-end training through back-propagation. Since the optimal parameters of each layer are learned separately, 2D-ADN exhibits more representation flexibility and preferable reconstruction performance than model-driven methods. Simultaneously, it is able to better facilitate ISAR imaging with limited training samples than data-driven methods owing to its simple structure and small number of adjustable parameters. Additionally, benefiting from the good performance of 2D-ADN, a random phase error estimation method is proposed, through which well-focused imaging can be acquired. It is demonstrated by experiments that although trained by only a few simulated images, the 2D-ADN shows good adaptability to measured data and favorable imaging results with a clear background can be obtained in a short time.

show abstract

Section: Resultsmentioning

confidence: 98%

Section: Structure Of 2d-adnmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

High-Resolution ISAR Imaging and Autofocusing via 2D-ADMM-Net

Bai

Zhou

2021

Remote Sensing

View full text Add to dashboard Cite

show abstract

“…where λ is a sparsity-enforcing parameter, and the norm constraints are to avoid scaling ambiguity. Following a similar approach to [17,23,24], we construct an autoencoder where its encoder maps z n into a sparse filter x n by unfolding T iterations of a variant of accelerated proximal gradient algorithm, FISTA [22], for sparse recovery. Specifically, each unfolding layer performs the following iteration…”

Section: Network Architecturementioning

confidence: 99%

Unfolding Neural Networks for Compressive Multichannel Blind Deconvolution

Tolooshams

Mulleti

et al. 2021

ICASSP 2021 - 2021 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)

Self Cite

View full text Add to dashboard Cite

We propose a learned-structured unfolding neural network for the problem of compressive sparse multichannel blind-deconvolution. In this problem, each channel's measurements are given as convolution of a common source signal and sparse filter. Unlike prior works where the compression is achieved either through random projections or by applying a fixed structured compression matrix, this paper proposes to learn the compression matrix from data. Given the full measurements, the proposed network is trained in an unsupervised fashion to learn the source and estimate sparse filters. Then, given the estimated source, we learn a structured compression operator while optimizing for signal reconstruction and sparse filter recovery. The efficient structure of the compression allows its practical hardware implementation. The proposed neural network is an autoencoder constructed based on an unfolding approach: upon training, the encoder maps the compressed measurements into an estimate of sparse filters using the compression operator and the source, and the linear convolutional decoder reconstructs the full measurements. We demonstrate that our method is superior to classical structured compressive sparse multichannel blind-deconvolution methods in terms of accuracy and speed of sparse filter recovery.

show abstract

“…Images have become ubiquitous in all the elds which basically means that vast amount of information can be extracted from imagery. While image classi cation has now become prevalent in elds like computer vision, self-driving cars, robotics, etc., it is fairly new in the eld of microstructures [1][2][3].…”

Section: Introductionmentioning

confidence: 99%

Deep Convolutional Neural Network Algorithm for Prediction of the Mechanical Properties of Friction Stir Welded Copper Joints from its Microstructures

Mishra¹,

Suman

2021

Preprint

View full text Add to dashboard Cite

Convolutional Neural Network (CNN) is a special type of Artificial Neural Network which takes input in the form of an image. Like Artificial Neural Network they consist of weights that are estimated during training, neurons (activation functions), and an objective (loss function). CNN is finding various applications in image recognition, semantic segmentation, object detection, and localization. The present work deals with the prediction of the welding efficiency of the Friction Stir Welded joints on the basis of microstructure images by carrying out training on 3000 microstructure images and further testing on 300 microstructure images. The obtained results showed an accuracy of 80 % on the validation dataset.

show abstract

Algorithm Unrolling: Interpretable, Efficient Deep Learning for Signal and Image Processing

Cited by 845 publications

References 75 publications

High-Resolution ISAR Imaging and Autofocusing via 2D-ADMM-Net

High-Resolution ISAR Imaging and Autofocusing via 2D-ADMM-Net

Unfolding Neural Networks for Compressive Multichannel Blind Deconvolution

Deep Convolutional Neural Network Algorithm for Prediction of the Mechanical Properties of Friction Stir Welded Copper Joints from its Microstructures

Contact Info

Product

Resources

About