8. Subset Selection in Regression (Monographs on Statistics and Applied Probability, no. 40). By A. J. Miller. ISBN 0 412 35380 6. Chapman and Hall, London, 1990. 240 pp. £25.00.

Subset Selection in Regression

Algorithms and applications

A Fixed-Point Continuation Method for L_1-Regularization with Application to Compressed Sensing

Deep learning is transforming most areas of science and technology, including electron microscopy. This review paper offers a practical perspective aimed at developers with limited familiarity. For context, we review popular applications of deep learning in electron microscopy. Following, we discuss hardware and software needed to get started with deep learning and interface with electron microscopes. We then review neural network components, popular architectures, and their optimization. Finally, we discuss future directions of deep learning in electron microscopy.

Review: Deep Learning in Electron Microscopy

Deep neural networks have attained great success in handling high dimensional data, especially images. However, generating naturalistic images containing ginormous subjects for different tasks like image classification, segmentation, object detection, reconstruction, etc., is continued to be a difficult task. Generative modelling has the potential to learn any kind of data distribution in an unsupervised manner. Variational autoencoder (VAE), autoregressive models, and generative adversarial network (GAN) are the popular generative modelling approaches that generate data distributions. Among these, GANs have gained much attention from the research community in recent years in terms of generating quality images and data augmentation. In this context, we collected research articles that employed GANs for solving various tasks from popular databases and summarized them based on their application. The main objective of this article is to present the nuts and bolts of GANs, state-of-the-art related work and its applications, evaluation metrics, challenges involved in training GANs, and benchmark datasets that would benefit naive and enthusiastic researchers who are interested in working on GANs.

Generative adversarial networks: a survey on applications and challenges

Massive multiple-input multiple-output (M-MIMO) is one of the main 5G-enabling technologies that promise to increase cell throughput and reduce multiuser interference. However, these abilities rely on exploiting the channel state information (CSI) feedback at base stations (BSs). One critical challenge is that the user equipment (UE) needs to return a large amount of channel information to the base station, creating a large signaling overhead. In this letter, we propose a framework based on deep learning, which is able to efficiently compress and recover the feedback CSI. The encoder learns the most suitable compressed codeword corresponding to the CSI. The decoder decompresses this codeword at the receiving BS end using a Generative Adversarial Network (GAN). A novel objective function is proposed and used to train the Deep Convolutional Generative Adversarial Network (DCGAN) to improve the performance of our proposed framework. Simulation results demonstrate that the proposed framework outperforms traditional compressive sensing-based methods and provides remarkably robust performance for the outdoor channels.

Massive MIMO CSI Feedback Based on Generative Adversarial Network

Recently, there have been significant advances in image super-resolution based on generative adversarial networks (GANs) to achieve breakthroughs in generating more images with high subjective quality. However, there are remaining challenges needs to be met, such as simultaneously recovering the finer texture details for large upscaling factors and mitigating the geometric transformation effects. In this paper, we propose a novel robust super-resolution GAN (i.e. namely RSR-GAN) which can simultaneously perform both the geometric transformation and recovering the finer texture details. Specifically, since the performance of the generator depends on the discreminator, we propose a novel discriminator design by incorporating the spatial transformer module with residual learning to improve the discrimination of fake and true images through removing the geometric noise, in order to enhance the super-resolution of geometric corrected images. Finally, to further improve the perceptual quality, we introduce an additional DCT loss term into the existing loss function. Extensive experiments, measured by both PSNR and SSIM measurements, show that our proposed method achieves a high level of robustness against a number of geometric transformations, including rotation, translation, a combination of rotation and scaling effects, and a cobmination of rotaion, transalation and scaling effects. Benchmarked by the existing state-of-the-arts SR methods, our proposed delivers superior performances on a wide range of datasets which are publicly available and widely adopted across research communities.

/pdf/spatial-transformer-generative-adversarial-network-for-7ggn9b8njf.pdf

Spatial Transformer Generative Adversarial Network for Robust Image Super-Resolution

Sparse signal processing has become central in many communications and multimedia processing applications. Techniques such as Compressed Sensing(CS) and Sparse Fast Fourier Transform (SFFT) provide good quality of the restored signal even when the signal is not completely sparse even also at high compression ratio. In this work, we examine the effect of taking the perceptual properties of the audio signal into account while performing both CS and SFFT. The improved perceptual signal quality by Mean Opinion Score (MOS) is verified.

Perceptual Compressed Sensing and perceptual Sparse Fast Fourier Transform for audio signal compression

In general, existing research on single image super-resolution does not consider the practical application that, when image transmission is over noisy channels, the effect of any possible geometric transformations could incur significant quality loss and distortions. To address this problem, we present a new and robust super-resolution method in this paper, where a robust spatially-transformed deep learning framework is established to simultaneously perform both the geometric transformation and the single image super-resolution. The proposed seamlessly integrates deep residual learning based spatial transform module with a very deep super-resolution module to achieve a robust and improved single image super-resolution. In comparison with the existing state of the arts, our proposed robust single image super-resolution has a number of novel features, including 1) content-characterized deep features are extracted out of the input LR images to identify the incurred geometric transformations, and hence transformation parameters can be optimized to influence and control the super-resolution process; 2) the effects of any geometric transformations can be automatically corrected at the output without compromise on the quality of final super-resolved images; and 3) compared with the existing research reported in the literature, our proposed achieves the advantage that HR images can be recovered from those down-sampled LR images corrupted by a number of different geometric transformations. The extensive experiments, measured by both the peak-signal-to-noise-ratio and the similar structure index measurement, show that our proposed method achieves a high level of robustness against a number of geometric transformations, including scaling, translations, and rotations. Benchmarked by the existing state-of-the-arts SR methods, our proposed delivers superior performances on a wide range of datasets which are publicly available and widely adopted across relevant research communities.

/pdf/a-very-deep-spatial-transformer-towards-robust-single-image-2i03h0rg33.pdf

A Very Deep Spatial Transformer Towards Robust Single Image Super-Resolution

In this paper, we propose two approaches to generate a high resolution (HR) image from a low resolution (LR) version. It is commonly referred as single-image super-resolution(SISR). Our approaches are inspired by the spatial transformer (ST) module and Very Deep Convolutional Network (VDSR). The spatial transformer module is the neural network originally used for geometric transformations of images, while the VDSR is for image super-resolution. In the first approach, we propose to add the ST module with the VDSR to generate HR images. The use of the spatial transform with VDSR makes the network more robust to the geometric transformations. We propose the second approach to replace the convolutional neural network (CNN) used in the ST module with VDSR network. The replacement of CNN leads to improvements in the performance of ST module. The simulation results confirm that the feasibility of combing ST module and VDSR for super-resolution reconstruction, where the performance of the combination of ST module and VDSR is comparable to the VDSR alone in terms of Peak signal-to-noise ratio (PSNR) and structural Similarity Index Measurement (SSIM). Hence, the revised spatial transformer network can be used in the future for simultaneous geometric transformation and image super-resolution, which solve the practical applications of image super-resolution in real life.

Hossam M. Kasem

Papers

Massive MIMO CSI Feedback Based on Generative Adversarial Network

Spatial Transformer Generative Adversarial Network for Robust Image Super-Resolution

Perceptual Compressed Sensing and perceptual Sparse Fast Fourier Transform for audio signal compression

A Very Deep Spatial Transformer Towards Robust Single Image Super-Resolution

Revised Spatial Transformer Network towards Improved Image Super-resolutions