PyTorchKR Papers

최신 논문

총 549편
태그·기간 등 상세 필터

카테고리 탐색

로그인 후 이 태그 구독

arXiv:2101.01234

On the Fourier transform of a quantitative trait: Implications for compressive sensing

This paper explores the genotype-phenotype relationship. It outlines conditions under which the dependence of a quantitative trait on the genome might be predictable, based on measurement of a limited subset of genotypes. It uses the theory of real-valued Boolean functions in a systematic way to translate trait data into the Fourier domain. Important trait features, such as the roughness of the trait landscape or the modularity of a trait have a simple Fourier interpretation. Ruggedness at a gene location corresponds to high sensitivity to mutation, while a modular organization of gene activity reduces such sensitivity. Traits where rugged loci are rare will naturally compress gene data in the Fourier domain, leading to a sparse representation of trait data, concentrated in identifiable, low-level coefficients. This Fourier representation of a trait organizes epistasis in a form which is isometric to the trait data. As Fourier matrices are known to be maximally incoherent with the standard basis, this permits employing compressive sensing techniques to work from data sets that are relatively small -- sometimes even of polynomial size -- compared to the exponentially large sets of possible genomes. This theory provides a theoretical underpinning for systematic use of Boolean function machinery to dissect the dependency of a trait on the genome and environment.

arXiv:2103.15368

Attention-guided Image Compression by Deep Reconstruction of Compressive Sensed Saliency Skeleton

We propose a deep learning system for attention-guided dual-layer image compression (AGDL). In the AGDL compression system, an image is encoded into two layers, a base layer and an attention-guided refinement layer. Unlike the existing ROI image compression methods that spend an extra bit budget equally on all pixels in ROI, AGDL employs a CNN module to predict those pixels on and near a saliency sketch within ROI that are critical to perceptual quality. Only the critical pixels are further sampled by compressive sensing (CS) to form a very compact refinement layer. Another novel CNN method is developed to jointly decode the two compression layers for a much refined reconstruction, while strictly satisfying the transmitted CS constraints on perceptually critical pixels. Extensive experiments demonstrate that the proposed AGDL system advances the state of the art in perception-aware image compression.

arXiv:2103.11554공식 코드 · Papers with Code

ISTA-Net++: Flexible Deep Unfolding Network for Compressive Sensing

While deep neural networks have achieved impressive success in image compressive sensing (CS), most of them lack flexibility when dealing with multi-ratio tasks and multi-scene images in practical applications. To tackle these challenges, we propose a novel end-to-end flexible ISTA-unfolding deep network, dubbed ISTA-Net++, with superior performance and strong flexibility. Specifically, by developing a dynamic unfolding strategy, our model enjoys the adaptability of handling CS problems with different ratios, i.e., multi-ratio tasks, through a single model. A cross-block strategy is further utilized to reduce blocking artifacts and enhance the CS recovery quality. Furthermore, we adopt a balanced dataset for training, which brings more robustness when reconstructing images of multiple scenes. Extensive experiments on four datasets show that ISTA-Net++ achieves state-of-the-art results in terms of both quantitative metrics and visual quality. Considering its flexibility, effectiveness and practicability, our model is expected to serve as a suitable baseline in future CS research. The source code is available on https://github.com/jianzhangcs/ISTA-Netpp.

arXiv:2103.07609공식 코드 · Papers with Code

Untrained networks for compressive lensless photography

Compressive lensless imagers enable novel applications in an extremely compact device, requiring only a phase or amplitude mask placed close to the sensor. They have been demonstrated for 2D and 3D microscopy, single-shot video, and single-shot hyperspectral imaging; in each of these cases, a compressive-sensing-based inverse problem is solved in order to recover a 3D data-cube from a 2D measurement. Typically, this is accomplished using convex optimization and hand-picked priors. Alternatively, deep learning-based reconstruction methods offer the promise of better priors, but require many thousands of ground truth training pairs, which can be difficult or impossible to acquire. In this work, we propose the use of untrained networks for compressive image recovery. Our approach does not require any labeled training data, but instead uses the measurement itself to update the network weights. We demonstrate our untrained approach on lensless compressive 2D imaging as well as single-shot high-speed video recovery using the camera's rolling shutter, and single-shot hyperspectral imaging. We provide simulation and experimental verification, showing that our method results in improved image quality over existing methods.

arXiv:2103.06804

Improved Coherence Index-Based Bound in Compressive Sensing

Within the Compressive Sensing (CS) paradigm, sparse signals can be reconstructed based on a reduced set of measurements. Reliability of the solution is determined by the uniqueness condition. With its mathematically tractable and feasible calculation, coherence index is one of very few CS metrics with a considerable practical importance. In this paper, we propose an improvement of the coherence based uniqueness relation for the matching pursuit algorithms. Starting from a simple and intuitive derivation of the standard uniqueness condition based on the coherence index, we derive a less conservative coherence index-based lower bound for signal sparsity. The results are generalized to the uniqueness condition of the $l_0$-norm minimization for a signal represented in two orthonormal bases.

arXiv:2103.05535

A Probabilistic Bayesian Approach to Recover $R_2^*$ map and Phase Images for Quantitative Susceptibility Mapping

Purpose: Undersampling is used to reduce the scan time for high-resolution 3D magnetic resonance imaging. In order to achieve better image quality and avoid manual parameter tuning, we propose a probabilistic Bayesian approach to recover $R_2^*$ map and phase images for quantitative susceptibility mapping (QSM), while allowing automatic parameter estimation from undersampled data. Theory: Sparse prior on the wavelet coefficients of images is interpreted from a Bayesian perspective as sparsity-promoting distribution. A novel nonlinear approximate message passing (AMP) framework that incorporates a mono-exponential decay model is proposed. The parameters are treated as unknown variables and jointly estimated with image wavelet coefficients. Results: The proposed AMP with parameter estimation (AMP-PE) approach successfully recovers $R_2^*$ maps and phase images for QSM across various undersampling rates. It is more computationally efficient, and performs better than the state-of-the-art $l_1$-norm regularization (L1) approach in general, except a few cases where the L1 approach performs as well as AMP-PE. Conclusion: AMP-PE achieves better performance by drawing information from both the sparse prior and the mono-exponential decay model. It does not require parameter tuning, and works with a clinical, prospective undersampling scheme where parameter tuning is often impossible or difficult due to the lack of ground-truth image.

arXiv:2103.03191공식 코드 · Papers with Code

Generalization Bounds for Sparse Random Feature Expansions

Random feature methods have been successful in various machine learning tasks, are easy to compute, and come with theoretical accuracy bounds. They serve as an alternative approach to standard neural networks since they can represent similar function spaces without a costly training phase. However, for accuracy, random feature methods require more measurements than trainable parameters, limiting their use for data-scarce applications or problems in scientific machine learning. This paper introduces the sparse random feature expansion to obtain parsimonious random feature models. Specifically, we leverage ideas from compressive sensing to generate random feature expansions with theoretical guarantees even in the data-scarce setting. In particular, we provide generalization bounds for functions in a certain class (that is dense in a reproducing kernel Hilbert space) depending on the number of samples and the distribution of features. The generalization bounds improve with additional structural conditions, such as coordinate sparsity, compact clusters of the spectrum, or rapid spectral decay. In particular, by introducing sparse features, i.e. features with random sparse weights, we provide improved bounds for low order functions. We show that the sparse random feature expansions outperforms shallow networks in several scientific machine learning tasks.

arXiv:2103.03089공식 코드 · Papers with Code

Memory-Efficient Network for Large-scale Video Compressive Sensing

Video snapshot compressive imaging (SCI) captures a sequence of video frames in a single shot using a 2D detector. The underlying principle is that during one exposure time, different masks are imposed on the high-speed scene to form a compressed measurement. With the knowledge of masks, optimization algorithms or deep learning methods are employed to reconstruct the desired high-speed video frames from this snapshot measurement. Unfortunately, though these methods can achieve decent results, the long running time of optimization algorithms or huge training memory occupation of deep networks still preclude them in practical applications. In this paper, we develop a memory-efficient network for large-scale video SCI based on multi-group reversible 3D convolutional neural networks. In addition to the basic model for the grayscale SCI system, we take one step further to combine demosaicing and SCI reconstruction to directly recover color video from Bayer measurements. Extensive results on both simulation and real data captured by SCI cameras demonstrate that our proposed model outperforms previous state-of-the-art with less memory and thus can be used in large-scale problems. The code is at https://github.com/BoChenGroup/RevSCI-net.

arXiv:2103.01786공식 코드 · Papers with Code

MetaSCI: Scalable and Adaptive Reconstruction for Video Compressive Sensing

To capture high-speed videos using a two-dimensional detector, video snapshot compressive imaging (SCI) is a promising system, where the video frames are coded by different masks and then compressed to a snapshot measurement. Following this, efficient algorithms are desired to reconstruct the high-speed frames, where the state-of-the-art results are achieved by deep learning networks. However, these networks are usually trained for specific small-scale masks and often have high demands of training time and GPU memory, which are hence {\bf \em not flexible} to $i$) a new mask with the same size and $ii$) a larger-scale mask. We address these challenges by developing a Meta Modulated Convolutional Network for SCI reconstruction, dubbed MetaSCI. MetaSCI is composed of a shared backbone for different masks, and light-weight meta-modulation parameters to evolve to different modulation parameters for each mask, thus having the properties of {\bf \em fast adaptation} to new masks (or systems) and ready to {\bf \em scale to large data}. Extensive simulation and real data results demonstrate the superior performance of our proposed approach. Our code is available at {\small\url{https://github.com/xyvirtualgroup/MetaSCI-CVPR2021}}.

arXiv:2103.00652공식 코드 · Papers with Code

OpenICS: Open Image Compressive Sensing Toolbox and Benchmark

We present OpenICS, an image compressive sensing toolbox that includes multiple image compressive sensing and reconstruction algorithms proposed in the past decade. Due to the lack of standardization in the implementation and evaluation of the proposed algorithms, the application of image compressive sensing in the real-world is limited. We believe this toolbox is the first framework that provides a unified and standardized implementation of multiple image compressive sensing algorithms. In addition, we also conduct a benchmarking study on the methods included in this framework from two aspects: reconstruction accuracy and reconstruction efficiency. We wish this toolbox and benchmark can serve the growing research community of compressive sensing and the industry applying image compressive sensing to new problems as well as developing new methods more efficiently. Code and models are available at https://github.com/PSCLab-ASU/OpenICS. The project is still under maintenance, and we will keep this document updated.

arXiv:2102.07507공식 코드 · Papers with Code

CLNet: Complex Input Lightweight Neural Network designed for Massive MIMO CSI Feedback

Unleashing the full potential of massive MIMO in FDD mode by reducing the overhead of CSI feedback has recently garnered attention. Numerous deep learning for massive MIMO CSI feedback approaches have demonstrated their efficiency and potential. However, most existing methods improve accuracy at the cost of computational complexity and the accuracy decreases significantly as the CSI compression rate increases. This paper presents a novel neural network CLNet tailored for CSI feedback problem based on the intrinsic properties of CSI. CLNet proposes a forge complex-valued input layer to process signals and utilizes attention mechanism to enhance the performance of the network. The experiment result shows that CLNet outperforms the state-of-the-art method by average accuracy improvement of 5.41\% in both outdoor and indoor scenarios with average 24.1\% less computational overhead. Codes for deep learning-based CSI feedback CLNet are available at GitHub.

arXiv:2102.05744

Faster Maximum Feasible Subsystem Solutions for Dense Constraint Matrices

Finding the largest cardinality feasible subset of an infeasible set of linear constraints is the Maximum Feasible Subsystem problem (MAX FS). Solving this problem is crucial in a wide range of applications such as machine learning and compressive sensing. Although MAX FS is NP-hard, useful heuristic algorithms exist, but these can be slow for large problems. We extend the existing heuristics for the case of dense constraint matrices to greatly increase their speed while preserving or improving solution quality. We test the extended algorithms on two applications that have dense constraint matrices: binary classification, and sparse recovery in compressive sensing. In both cases, speed is greatly increased with no loss of accuracy.

arXiv:2102.06103공식 코드 · Papers with Code

Measuring Robustness in Deep Learning Based Compressive Sensing

Deep neural networks give state-of-the-art accuracy for reconstructing images from few and noisy measurements, a problem arising for example in accelerated magnetic resonance imaging (MRI). However, recent works have raised concerns that deep-learning-based image reconstruction methods are sensitive to perturbations and are less robust than traditional methods: Neural networks (i) may be sensitive to small, yet adversarially-selected perturbations, (ii) may perform poorly under distribution shifts, and (iii) may fail to recover small but important features in an image. In order to understand the sensitivity to such perturbations, in this work, we measure the robustness of different approaches for image reconstruction including trained and un-trained neural networks as well as traditional sparsity-based methods. We find, contrary to prior works, that both trained and un-trained methods are vulnerable to adversarial perturbations. Moreover, both trained and un-trained methods tuned for a particular dataset suffer very similarly from distribution shifts. Finally, we demonstrate that an image reconstruction method that achieves higher reconstruction quality, also performs better in terms of accurately recovering fine details. Our results indicate that the state-of-the-art deep-learning-based image reconstruction methods provide improved performance than traditional methods without compromising robustness.

arXiv:2101.08024

Scalable Deep Compressive Sensing

Deep learning has been used to image compressive sensing (CS) for enhanced reconstruction performance. However, most existing deep learning methods train different models for different subsampling ratios, which brings additional hardware burden. In this paper, we develop a general framework named scalable deep compressive sensing (SDCS) for the scalable sampling and reconstruction (SSR) of all existing end-to-end-trained models. In the proposed way, images are measured and initialized linearly. Two sampling masks are introduced to flexibly control the subsampling ratios used in sampling and reconstruction, respectively. To make the reconstruction model adapt to any subsampling ratio, a training strategy dubbed scalable training is developed. In scalable training, the model is trained with the sampling matrix and the initialization matrix at various subsampling ratios by integrating different sampling matrix masks. Experimental results show that models with SDCS can achieve SSR without changing their structure while maintaining good performance, and SDCS outperforms other SSR methods.

arXiv:2101.05130

DAEs for Linear Inverse Problems: Improved Recovery with Provable Guarantees

Generative priors have been shown to provide improved results over sparsity priors in linear inverse problems. However, current state of the art methods suffer from one or more of the following drawbacks: (a) speed of recovery is slow; (b) reconstruction quality is deficient; (c) reconstruction quality is contingent on a computationally expensive process of tuning hyperparameters. In this work, we address these issues by utilizing Denoising Auto Encoders (DAEs) as priors and a projected gradient descent algorithm for recovering the original signal. We provide rigorous theoretical guarantees for our method and experimentally demonstrate its superiority over existing state of the art methods in compressive sensing, inpainting, and super-resolution. We find that our algorithm speeds up recovery by two orders of magnitude (over 100x), improves quality of reconstruction by an order of magnitude (over 10x), and does not require tuning hyperparameters.

arXiv:2101.04027공식 코드 · Papers with Code

Covariance Estimation from Compressive Data Partitions using a Projected Gradient-based Algorithm

Compressive covariance estimation has arisen as a class of techniques whose aim is to obtain second-order statistics of stochastic processes from compressive measurements. Recently, these methods have been used in various image processing and communications applications, including denoising, spectrum sensing, and compression. Notice that estimating the covariance matrix from compressive samples leads to ill-posed minimizations with severe performance loss at high compression rates. In this regard, a regularization term is typically aggregated to the cost function to consider prior information about a particular property of the covariance matrix. Hence, this paper proposes an algorithm based on the projected gradient method to recover low-rank or Toeplitz approximations of the covariance matrix from compressive measurements. The algorithm divides the compressive measurements into data subsets projected onto different subspaces and accurately estimates the covariance matrix by solving a single optimization problem assuming that each data subset contains an approximation of the signal statistics. Furthermore, gradient filtering is included at every iteration of the proposed algorithm to minimize the estimation error. The error induced by the proposed splitting approach is analytically derived along with the convergence guarantees of the proposed method. The algorithm estimates the covariance matrix of hyperspectral images from synthetic and real compressive samples. Extensive simulations show that the proposed algorithm can effectively recover the covariance matrix of hyperspectral images from compressive measurements (8-15% approx). Moreover, simulations and theoretical results show that the filtering step reduces the recovery error up to twice the number of eigenvectors. Finally, an optical implementation is proposed, and real measurements are used to validate the theoretical findings.

arXiv:2012.12086

Unsupervised Spatial-spectral Network Learning for Hyperspectral Compressive Snapshot Reconstruction

Hyperspectral compressive imaging takes advantage of compressive sensing theory to achieve coded aperture snapshot measurement without temporal scanning, and the entire three-dimensional spatial-spectral data is captured by a two-dimensional projection during a single integration period. Its core issue is how to reconstruct the underlying hyperspectral image using compressive sensing reconstruction algorithms. Due to the diversity in the spectral response characteristics and wavelength range of different spectral imaging devices, previous works are often inadequate to capture complex spectral variations or lack the adaptive capacity to new hyperspectral imagers. In order to address these issues, we propose an unsupervised spatial-spectral network to reconstruct hyperspectral images only from the compressive snapshot measurement. The proposed network acts as a conditional generative model conditioned on the snapshot measurement, and it exploits the spatial-spectral attention module to capture the joint spatial-spectral correlation of hyperspectral images. The network parameters are optimized to make sure that the network output can closely match the given snapshot measurement according to the imaging model, thus the proposed network can adapt to different imaging settings, which can inherently enhance the applicability of the network. Extensive experiments upon multiple datasets demonstrate that our network can achieve better reconstruction results than the state-of-the-art methods.

arXiv:2012.02081

Compressive Sensing Approaches for Sparse Distribution Estimation Under Local Privacy

Recent years, local differential privacy (LDP) has been adopted by many web service providers like Google \cite{erlingsson2014rappor}, Apple \cite{apple2017privacy} and Microsoft \cite{bolin2017telemetry} to collect and analyse users' data privately. In this paper, we consider the problem of discrete distribution estimation under local differential privacy constraints. Distribution estimation is one of the most fundamental estimation problems, which is widely studied in both non-private and private settings. In the local model, private mechanisms with provably optimal sample complexity are known. However, they are optimal only in the worst-case sense; their sample complexity is proportional to the size of the entire universe, which could be huge in practice. In this paper, we consider sparse or approximately sparse (e.g.\ highly skewed) distribution, and show that the number of samples needed could be significantly reduced. This problem has been studied recently \cite{acharya2021estimating}, but they only consider strict sparse distributions and the high privacy regime. We propose new privatization mechanisms based on compressive sensing. Our methods work for approximately sparse distributions and medium privacy, and have optimal sample and communication complexity.

arXiv:2011.00278

Defect Detection by MIMO Wireless Sensing based on Weighted Low-Rank plus Sparse Recovery

We present a compressive sensing based defect detection by multiple input multiple output (MIMO) wireless radar. Here, defects are inside a layered material structure, therefore, due to reflections from the surface of the layered material structure the defect detection is challenging. By utilizing a low-rank nature of the reflections of the layered material structure and sparse nature of the defects, we propose a method based on rank minimization and sparse recovery. To improve the accuracy in the recovery of low-rank and sparse components, we propose a non-convex approach based on the iteratively reweighted nuclear norm and iteratively reweighted $\ell_1-$norm algorithm. Our numerical results show that the proposed method is able to demix and recover the signalling responses of the defects and layered structure successfully from substantially reduced number of observations. Further, the proposed approach outperforms the state-of-the-art clutter reduction approaches

arXiv:2010.15618

Sampling and Reconstruction of Sparse Signals in Shift-Invariant Spaces: Generalized Shannon's Theorem Meets Compressive Sensing

This paper introduces a novel framework and corresponding methods for sampling and reconstruction of sparse signals in shift-invariant (SI) spaces. We reinterpret the random demodulator, a system that acquires sparse bandlimited signals, as a system for the acquisition of linear combinations of the samples in the SI setting with the box function as the sampling kernel. The sparsity assumption is exploited by the compressive sensing (CS) paradigm for a recovery of the SI samples from a reduced set of measurements. The SI samples are subsequently filtered by a discrete-time correction filter to reconstruct expansion coefficients of the observed signal. Furthermore, we offer a generalization of the proposed framework to other compactly supported sampling kernels that span a wider class of SI spaces. The generalized method embeds the correction filter in the CS optimization problem which directly reconstructs expansion coefficients of the signal. Both approaches recast an inherently continuous-domain inverse problem in a set of finite-dimensional CS problems in an exact way. Finally, we conduct numerical experiments on signals in polynomial B-spline spaces whose expansion coefficients are assumed to be sparse in a certain transform domain. The coefficients can be regarded as parametric models of an underlying continuous-time signal, obtained from a reduced set of measurements. Such continuous signal representations are particularly suitable for signal processing without converting them into samples.