Randnet: Deep Learning with Compressed Measurements of Images

Chang, Thomas S.; Tolooshams, Bahareh; Ba, Demba

doi:10.1109/mlsp.2019.8918878

Cited by 11 publications

(8 citation statements)

References 10 publications

(31 reference statements)

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Deep unfolding was originally proposed by Greger and LeCun in [8], where a deep architecture was designed to learn to carry out the iterative soft thresholding algorithm (ISTA) for sparse recovery. Deep unfolded networks have since been applied in various applications in image denoising [7], [39], [40], sparse recovery [9], [25], [41], dictionary learning [42], [43], communications [19], [44]- [47], ultrasound [48], [49], and super resolution [50]- [52]. A recent review can be found in [7].…”

Section: A Deep Unfoldingmentioning

confidence: 99%

Model-Based Deep Learning

Shlezinger¹,

Whang²,

Eldar³

et al. 2020

Preprint

View full text Add to dashboard Cite

Signal processing, communications, and control have traditionally relied on classical statistical modeling techniques. Such model-based methods utilize mathematical formulations that represent the underlying physics, prior information and additional domain knowledge. Simple classical models are useful but sensitive to inaccuracies and may lead to poor performance when real systems display complex or dynamic behavior.On the other hand, purely data-driven approaches that are model-agnostic are becoming increasingly popular as datasets become abundant and the power of modern deep learning pipelines increases. Deep neural networks (DNNs) use generic architectures which learn to operate from data, and demonstrate excellent performance, especially for supervised problems. However, DNNs typically require massive amounts of data and immense computational resources, limiting their applicability for some signal processing scenarios.We are interested in hybrid techniques that combine principled mathematical models with data-driven systems to benefit from the advantages of both approaches. Such model-based deep learning methods exploit both partial domain knowledge, via mathematical structures designed for specific problems, as well as learning from limited data. In this article we survey the leading approaches for studying and designing model-based deep learning systems. We divide hybrid model-based/data-driven systems into categories based on their inference mechanism. We provide a comprehensive review of the leading approaches for combining model-based algorithms with deep learning in a systematic manner, along with concrete guidelines and detailed signal processing oriented examples from recent literature. Our aim is to facilitate the design and study of future systems on the intersection of signal processing and machine learning that incorporate the advantages of both domains.

show abstract

Section: A Deep Unfoldingmentioning

confidence: 99%

Model-Based Deep Learning

Shlezinger¹,

Whang²,

Eldar³

et al. 2020

Preprint

View full text Add to dashboard Cite

show abstract

“…This method's novelty is in the hardware-efficient design of the operator Φ capturing data information when compressing. This architecture reduces to RandNet [19] when Φ and Cs have no structure (e.g. Toeplitz) and c = 1.…”

Section: Network Architecturementioning

confidence: 99%

“…Recent works proposed model-based neural networks to address computational efficiency [17,18], but still require full measurements for recovery. To enable compression, Chang et al [19] proposed an autoencoder, called RandNet, for dictionary learning. In this work, compression is achieved by projecting data into a lower-dimensional space through a data-independent unstructured random matrix.…”

Section: Introductionmentioning

confidence: 99%

“…We propose a model-based neural network that learns a hardwareefficient, data-driven, and structured compression matrix to recover sparse filters from reduced measurements. Our approach takes inspiration from filter-based compression [12], learning compression operators [20], and the model-based compressed learning approach for S-MBD [19]. The architecture, which we call learned (L) structured (S) compressive multichannel blind-deconvolution network (LS-MBD), learns a filter for compression, recovers the unknown source, and estimates sparse filters.…”

Section: Introductionmentioning

confidence: 99%

“…The architecture, which we call learned (L) structured (S) compressive multichannel blind-deconvolution network (LS-MBD), learns a filter for compression, recovers the unknown source, and estimates sparse filters. In contrast to [12,19,20], LS-MBD improves in the following ways. In [12], a fixed and data-independent filter is used for compression, and the reconstruction is independent of the compression.…”

Section: Introductionmentioning

confidence: 99%

See 2 more Smart Citations

Unfolding Neural Networks for Compressive Multichannel Blind Deconvolution

Tolooshams¹,

Mulleti²,

Ba³

et al. 2020

Preprint

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

Efficient Visual Recognition: A Survey on Recent Advances and Brain-inspired Methodologies

Wu¹,

Wang²,

Lu³

et al. 2022

Mach. Intell. Res.

View full text Add to dashboard Cite

Visual recognition is currently one of the most important and active research areas in computer vision, pattern recognition, and even the general field of artificial intelligence. It has great fundamental importance and strong industrial needs, particularly the modern deep neural networks (DNNs) and some brain-inspired methodologies, have largely boosted the recognition performance on many concrete tasks, with the help of large amounts of training data and new powerful computation resources. Although recognition accuracy is usually the first concern for new progresses, efficiency is actually rather important and sometimes critical for both academic research and industrial applications. Moreover, insightful views on the opportunities and challenges of efficiency are also highly required for the entire community. While general surveys on the efficiency issue have been done from various perspectives, as far as we are aware, scarcely any of them focused on visual recognition systematically, and thus it is unclear which progresses are applicable to it and what else should be concerned. In this survey, we present the review of recent advances with our suggestions on the new possible directions towards improving the efficiency of DNN-related and brain-inspired visual recognition approaches, including efficient network compression and dynamic brain-inspired networks. We investigate not only from the model but also from the data point of view (which is not the case in existing surveys) and focus on four typical data types (images, video, points, and events). This survey attempts to provide a systematic summary via a comprehensive survey that can serve as a valuable reference and inspire both researchers and practitioners working on visual recognition problems.

show abstract

Randnet: Deep Learning with Compressed Measurements of Images

Cited by 11 publications

References 10 publications

Model-Based Deep Learning

Model-Based Deep Learning

Unfolding Neural Networks for Compressive Multichannel Blind Deconvolution

Efficient Visual Recognition: A Survey on Recent Advances and Brain-inspired Methodologies

Contact Info

Product

Resources

About