ADMM-DAD net: a deep unfolding network for analysis compressed sensing

  title={ADMM-DAD net: a deep unfolding network for analysis compressed sensing},
  author={Vasiliki (Vicky) Kouni and Georgios Paraskevopoulos and Holger Rauhut and George C. Alexandropoulos},
In this paper, we propose a new deep unfolding neural network based on the ADMM algorithm for analysis Compressed Sensing. The proposed network jointly learns a redundant analysis operator for sparsification and reconstructs the signal of interest. We compare our proposed network with a state-of-the-art unfolded ISTA decoder, that also learns an orthogonal sparsifier. Moreover, we consider not only image, but also speech datasets as test examples. Computational experiments demonstrate that our… 

Figures and Tables from this paper

Generalization Error Bounds for Iterative Recovery Algorithms Unfolded as Neural Networks
This work introduces a general class of neural networks suitable for sparse reconstruction from few linear measurements, and derives generalization bounds by analyzing the Rademacher complexity of hypothesis classes consisting of such deep networks, that also take into account the thresholding parameters.
Generalization error bounds for DECONET: a deep unfolded network for analysis Compressive Sensing
In this paper, we propose a new deep unfolding neural network – based on a state-of-the-art optimization algorithm – for analysis Compressed Sensing. The proposed network called Decoding Network


A Robust Deep Unfolded Network for Sparse Signal Recovery from Noisy Binary Measurements
The proposed DeepFPC-`2 network, designed by unfolding the iterations of the fixed-point continuation (FPC) algorithm with one-sided `2-norm, shows higher signal reconstruction accuracy and convergence speed than the traditional FPC- `2 algorithm.
ISTA-Net: Interpretable Optimization-Inspired Deep Network for Image Compressive Sensing
This paper proposes a novel structured deep network, dubbed ISTA-Net, which is inspired by the Iterative Shrinkage-Thresholding Algorithm (ISTA) for optimizing a general $$ norm CS reconstruction model and develops an effective strategy to solve the proximal mapping associated with the sparsity-inducing regularizer using nonlinear transforms.
DeepCodec: Adaptive sensing and recovery via deep convolutional neural networks
A novel computational sensing framework for sensing and recovering structured signals that learns a transformation from the original signals to a near-optimal number of undersampled measurements and the inverse transformation from measurements to signals.
Deep unfolding for multichannel source separation
A multichannel Gaussian mixture model (MCGMM) is unfolded, resulting in a deep MCGMM computational network that directly processes complex-valued frequency-domain multich channel audio and has an architecture defined explicitly by a generative model, thus combining the advantages of deep networks and model-based approaches.
ADMM-Net: A Deep Learning Approach for Compressive Sensing MRI
Due to the combination of the advantages in model-based approach and deep learning approach, the ADMM-Nets achieve state-of-the-art reconstruction accuracies with fast computational speed.
Joint Sparse Recovery Using Deep Unfolding With Application to Massive Random Access
  • Anand P. Sabulal, S. Bhashyam
  • Computer Science
    ICASSP 2020 - 2020 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)
  • 2020
Numerical results for a massive random access system show that the proposed modification to the MMV-ADM method and deep unfolding provide significant improvement in convergence and estimation performance.
DAGAN: Deep De-Aliasing Generative Adversarial Networks for Fast Compressed Sensing MRI Reconstruction
This paper provides a deep learning-based strategy for reconstruction of CS-MRI, and bridges a substantial gap between conventional non-learning methods working only on data from a single image, and prior knowledge from large training data sets.
Deep ADMM-Net for Compressive Sensing MRI
Experiments on MRI image reconstruction under different sampling ratios in k-space demonstrate that the proposed novel ADMM-Net algorithm significantly improves the baseline ADMM algorithm and achieves high reconstruction accuracies with fast computational speed.
Trainable ISTA for Sparse Signal Recovery
A novel sparse signal recovery algorithm called Trainable ISTA (TISTA), which consists of two estimation units such as a linear estimation unit and a minimum mean squared error estimator-based shrinkage unit, which includes adjustable variables controlling a step size and the error variance for the MMSE shrinkage.
The original fixed-point continuation algorithm is extended to obtain better practical results, derive appropriate choices forM and under a given measurement model, and present numerical results for a variety of compressed sensing problems.