PyTorchKR Papers

최신 논문

총 549편
태그·기간 등 상세 필터

카테고리 탐색

로그인 후 이 태그 구독

arXiv:1707.02244

GPU-Accelerated Algorithms for Compressed Signals Recovery with Application to Astronomical Imagery Deblurring

Compressive sensing promises to enable bandwidth-efficient on-board compression of astronomical data by lifting the encoding complexity from the source to the receiver. The signal is recovered off-line, exploiting GPUs parallel computation capabilities to speedup the reconstruction process. However, inherent GPU hardware constraints limit the size of the recoverable signal and the speedup practically achievable. In this work, we design parallel algorithms that exploit the properties of circulant matrices for efficient GPU-accelerated sparse signals recovery. Our approach reduces the memory requirements, allowing us to recover very large signals with limited memory. In addition, it achieves a tenfold signal recovery speedup thanks to ad-hoc parallelization of matrix-vector multiplications and matrix inversions. Finally, we practically demonstrate our algorithms in a typical application of circulant matrices: deblurring a sparse astronomical image in the compressed domain.

arXiv:1707.03386

DeepCodec: Adaptive Sensing and Recovery via Deep Convolutional Neural Networks

In this paper we develop a novel computational sensing framework for sensing and recovering structured signals. When trained on a set of representative signals, our framework learns to take undersampled measurements and recover signals from them using a deep convolutional neural network. In other words, it learns a transformation from the original signals to a near-optimal number of undersampled measurements and the inverse transformation from measurements to signals. This is in contrast to traditional compressive sensing (CS) systems that use random linear measurements and convex optimization or iterative algorithms for signal recovery. We compare our new framework with $\ell_1$-minimization from the phase transition point of view and demonstrate that it outperforms $\ell_1$-minimization in the regions of phase transition plot where $\ell_1$-minimization cannot recover the exact solution. In addition, we experimentally demonstrate how learning measurements enhances the overall recovery performance, speeds up training of recovery framework, and leads to having fewer parameters to learn.

arXiv:1707.09926

A Framework for Super-Resolution of Scalable Video via Sparse Reconstruction of Residual Frames

This paper introduces a framework for super-resolution of scalable video based on compressive sensing and sparse representation of residual frames in reconnaissance and surveillance applications. We exploit efficient compressive sampling and sparse reconstruction algorithms to super-resolve the video sequence with respect to different compression rates. We use the sparsity of residual information in residual frames as the key point in devising our framework. Moreover, a controlling factor as the compressibility threshold to control the complexity-performance trade-off is defined. Numerical experiments confirm the efficiency of the proposed framework in terms of the compression rate as well as the quality of reconstructed video sequence in terms of PSNR measure. The framework leads to a more efficient compression rate and higher video quality compared to other state-of-the-art algorithms considering performance-complexity trade-offs.

arXiv:1708.04669

Convolutional Neural Networks for Non-iterative Reconstruction of Compressively Sensed Images

Traditional algorithms for compressive sensing recovery are computationally expensive and are ineffective at low measurement rates. In this work, we propose a data driven non-iterative algorithm to overcome the shortcomings of earlier iterative algorithms. Our solution, ReconNet, is a deep neural network, whose parameters are learned end-to-end to map block-wise compressive measurements of the scene to the desired image blocks. Reconstruction of an image becomes a simple forward pass through the network and can be done in real-time. We show empirically that our algorithm yields reconstructions with higher PSNRs compared to iterative algorithms at low measurement rates and in presence of measurement noise. We also propose a variant of ReconNet which uses adversarial loss in order to further improve reconstruction quality. We discuss how adding a fully connected layer to the existing ReconNet architecture allows for jointly learning the measurement matrix and the reconstruction algorithm in a single network. Experiments on real data obtained from a block compressive imager show that our networks are robust to unseen sensor noise. Finally, through an experiment in object tracking, we show that even at very low measurement rates, reconstructions using our algorithm possess rich semantic content that can be used for high level inference.

arXiv:1704.07023

Group-based Sparse Representation for Image Compressive Sensing Reconstruction with Non-Convex Regularization

Patch-based sparse representation modeling has shown great potential in image compressive sensing (CS) reconstruction. However, this model usually suffers from some limits, such as dictionary learning with great computational complexity, neglecting the relationship among similar patches. In this paper, a group-based sparse representation method with non-convex regularization (GSR-NCR) for image CS reconstruction is proposed. In GSR-NCR, the local sparsity and nonlocal self-similarity of images is simultaneously considered in a unified framework. Different from the previous methods based on sparsity-promoting convex regularization, we extend the non-convex weighted Lp (0 < p < 1) penalty function on group sparse coefficients of the data matrix, rather than conventional L1-based regularization. To reduce the computational complexity, instead of learning the dictionary with a high computational complexity from natural images, we learn the principle component analysis (PCA) based dictionary for each group. Moreover, to make the proposed scheme tractable and robust, we have developed an efficient iterative shrinkage/thresholding algorithm to solve the non-convex optimization problem. Experimental results demonstrate that the proposed method outperforms many state-of-the-art techniques for image CS reconstruction.

arXiv:1708.07450

Bayesian Compressive Sensing Using Normal Product Priors

In this paper, we introduce a new sparsity-promoting prior, namely, the "normal product" prior, and develop an efficient algorithm for sparse signal recovery under the Bayesian framework. The normal product distribution is the distribution of a product of two normally distributed variables with zero means and possibly different variances. Like other sparsity-encouraging distributions such as the Student's $t$-distribution, the normal product distribution has a sharp peak at origin, which makes it a suitable prior to encourage sparse solutions. A two-stage normal product-based hierarchical model is proposed. We resort to the variational Bayesian (VB) method to perform the inference. Simulations are conducted to illustrate the effectiveness of our proposed algorithm as compared with other state-of-the-art compressed sensing algorithms.

arXiv:1709.01230

On the Suboptimality of Proximal Gradient Descent for $\ell^{0}$ Sparse Approximation

We study the proximal gradient descent (PGD) method for $\ell^{0}$ sparse approximation problem as well as its accelerated optimization with randomized algorithms in this paper. We first offer theoretical analysis of PGD showing the bounded gap between the sub-optimal solution by PGD and the globally optimal solution for the $\ell^{0}$ sparse approximation problem under conditions weaker than Restricted Isometry Property widely used in compressive sensing literature. Moreover, we propose randomized algorithms to accelerate the optimization by PGD using randomized low rank matrix approximation (PGD-RMA) and randomized dimension reduction (PGD-RDR). Our randomized algorithms substantially reduces the computation cost of the original PGD for the $\ell^{0}$ sparse approximation problem, and the resultant sub-optimal solution still enjoys provable suboptimality, namely, the sub-optimal solution to the reduced problem still has bounded gap to the globally optimal solution to the original problem.

arXiv:1609.08281공식 코드 · Papers with Code

An Efficient Method for Robust Projection Matrix Design

Our objective is to efficiently design a robust projection matrix $\Phi$ for the Compressive Sensing (CS) systems when applied to the signals that are not exactly sparse. The optimal projection matrix is obtained by mainly minimizing the average coherence of the equivalent dictionary. In order to drop the requirement of the sparse representation error (SRE) for a set of training data as in [15] [16], we introduce a novel penalty function independent of a particular SRE matrix. Without requiring of training data, we can efficiently design the robust projection matrix and apply it for most of CS systems, like a CS system for image processing with a conventional wavelet dictionary in which the SRE matrix is generally not available. Simulation results demonstrate the efficiency and effectiveness of the proposed approach compared with the state-of-the-art methods. In addition, we experimentally demonstrate with natural images that under similar compression rate, a CS system with a learned dictionary in high dimensions outperforms the one in low dimensions in terms of reconstruction accuracy. This together with the fact that our proposed method can efficiently work in high dimension suggests that a CS system can be potentially implemented beyond the small patches in sparsity-based image processing.

arXiv:1708.09477

A Compressive Sensing Approach to Community Detection with Applications

The community detection problem for graphs asks one to partition the n vertices V of a graph G into k communities, or clusters, such that there are many intracluster edges and few intercluster edges. Of course this is equivalent to finding a permutation matrix P such that, if A denotes the adjacency matrix of G, then PAP^T is approximately block diagonal. As there are k^n possible partitions of n vertices into k subsets, directly determining the optimal clustering is clearly infeasible. Instead one seeks to solve a more tractable approximation to the clustering problem. In this paper we reformulate the community detection problem via sparse solution of a linear system associated with the Laplacian of a graph G and then develop a two-stage approach based on a thresholding technique and a compressive sensing algorithm to find a sparse solution which corresponds to the community containing a vertex of interest in G. Crucially, our approach results in an algorithm which is able to find a single cluster of size n_0 in O(nlog(n)n_0) operations and all k clusters in fewer than O(n^2ln(n)) operations. This is a marked improvement over the classic spectral clustering algorithm, which is unable to find a single cluster at a time and takes approximately O(n^3) operations to find all k clusters. Moreover, we are able to provide robust guarantees of success for the case where G is drawn at random from the Stochastic Block Model, a popular model for graphs with clusters. Extensive numerical results are also provided, showing the efficacy of our algorithm on both synthetic and real-world data sets.

arXiv:1710.01244

Adaptive Measurement Network for CS Image Reconstruction

Conventional compressive sensing (CS) reconstruction is very slow for its characteristic of solving an optimization problem. Convolu- tional neural network can realize fast processing while achieving compa- rable results. While CS image recovery with high quality not only de- pends on good reconstruction algorithms, but also good measurements. In this paper, we propose an adaptive measurement network in which measurement is obtained by learning. The new network consists of a fully-connected layer and ReconNet. The fully-connected layer which has low-dimension output acts as measurement. We train the fully-connected layer and ReconNet simultaneously and obtain adaptive measurement. Because the adaptive measurement fits dataset better, in contrast with random Gaussian measurement matrix, under the same measuremen- t rate, it can extract the information of scene more efficiently and get better reconstruction results. Experiments show that the new network outperforms the original one.

arXiv:1710.00109

Reconstruction from Periodic Nonlinearities, With Applications to HDR Imaging

We consider the problem of reconstructing signals and images from periodic nonlinearities. For such problems, we design a measurement scheme that supports efficient reconstruction; moreover, our method can be adapted to extend to compressive sensing-based signal and image acquisition systems. Our techniques can be potentially useful for reducing the measurement complexity of high dynamic range (HDR) imaging systems, with little loss in reconstruction quality. Several numerical experiments on real data demonstrate the effectiveness of our approach.

arXiv:1710.02236

Primal-Dual Optimization Algorithms over Riemannian Manifolds: an Iteration Complexity Analysis

In this paper we study nonconvex and nonsmooth multi-block optimization over Riemannian manifolds with coupled linear constraints. Such optimization problems naturally arise from machine learning, statistical learning, compressive sensing, image processing, and tensor PCA, among others. We develop an ADMM-like primal-dual approach based on decoupled solvable subroutines such as linearized proximal mappings. First, we introduce the optimality conditions for the afore-mentioned optimization models. Then, the notion of $\epsilon$-stationary solutions is introduced as a result. The main part of the paper is to show that the proposed algorithms enjoy an iteration complexity of $O(1/\epsilon^2)$ to reach an $\epsilon$-stationary solution. For prohibitively large-size tensor or machine learning models, we present a sampling-based stochastic algorithm with the same iteration complexity bound in expectation. In case the subproblems are not analytically solvable, a feasible curvilinear line-search variant of the algorithm based on retraction operators is proposed. Finally, we show specifically how the algorithms can be implemented to solve a variety of practical problems such as the NP-hard maximum bisection problem, the $\ell_q$ regularized sparse tensor principal component analysis and the community detection problem. Our preliminary numerical results show great potentials of the proposed methods.

arXiv:1703.01398

Sparse Depth Sensing for Resource-Constrained Robots

We consider the case in which a robot has to navigate in an unknown environment but does not have enough on-board power or payload to carry a traditional depth sensor (e.g., a 3D lidar) and thus can only acquire a few (point-wise) depth measurements. We address the following question: is it possible to reconstruct the geometry of an unknown environment using sparse and incomplete depth measurements? Reconstruction from incomplete data is not possible in general, but when the robot operates in man-made environments, the depth exhibits some regularity (e.g., many planar surfaces with only a few edges); we leverage this regularity to infer depth from a small number of measurements. Our first contribution is a formulation of the depth reconstruction problem that bridges robot perception with the compressive sensing literature in signal processing. The second contribution includes a set of formal results that ascertain the exactness and stability of the depth reconstruction in 2D and 3D problems, and completely characterize the geometry of the profiles that we can reconstruct. Our third contribution is a set of practical algorithms for depth reconstruction: our formulation directly translates into algorithms for depth estimation based on convex programming. In real-world problems, these convex programs are very large and general-purpose solvers are relatively slow. For this reason, we discuss ad-hoc solvers that enable fast depth reconstruction in real problems. The last contribution is an extensive experimental evaluation in 2D and 3D problems, including Monte Carlo runs on simulated instances and testing on multiple real datasets. Empirical results confirm that the proposed approach ensures accurate depth reconstruction, outperforms interpolation-based strategies, and performs well even when the assumption of structured environment is violated.

arXiv:1707.03164

Experimental comparison of single-pixel imaging algorithms

Single-pixel imaging (SPI) is a novel technique capturing 2D images using a photodiode, instead of conventional 2D array sensors. SPI owns high signal-to-noise ratio, wide spectrum range, low cost, and robustness to light scattering. Various algorithms have been proposed for SPI reconstruction, including the linear correlation methods, the alternating projection method (AP), and the compressive sensing based methods. However, there has been no comprehensive review discussing respective advantages, which is important for SPI's further applications and development. In this paper, we reviewed and compared these algorithms in a unified reconstruction framework. Besides, we proposed two other SPI algorithms including a conjugate gradient descent based method (CGD) and a Poisson maximum likelihood based method. Both simulations and experiments validate the following conclusions: to obtain comparable reconstruction accuracy, the compressive sensing based total variation regularization method (TV) requires the least measurements and consumes the least running time for small-scale reconstruction; the CGD and AP methods run fastest in large-scale cases; the TV and AP methods are the most robust to measurement noise. In a word, there are trade-offs between capture efficiency, computational complexity and robustness to noise among different SPI algorithms. We have released our source code for non-commercial use.

arXiv:1706.01014

Nonconvex penalties with analytical solutions for one-bit compressive sensing

One-bit measurements widely exist in the real world, and they can be used to recover sparse signals. This task is known as the problem of learning halfspaces in learning theory and one-bit compressive sensing (1bit-CS) in signal processing. In this paper, we propose novel algorithms based on both convex and nonconvex sparsity-inducing penalties for robust 1bit-CS. We provide a sufficient condition to verify whether a solution is globally optimal or not. Then we show that the globally optimal solution for positive homogeneous penalties can be obtained in two steps: a proximal operator and a normalization step. For several nonconvex penalties, including minimax concave penalty (MCP), $\ell_0$ norm, and sorted $\ell_1$ penalty, we provide fast algorithms for finding the analytical solutions by solving the dual problem. Specifically, our algorithm is more than $200$ times faster than the existing algorithm for MCP. Its efficiency is comparable to the algorithm for the $\ell_1$ penalty in time, while its performance is much better. Among these penalties, the sorted $\ell_1$ penalty is most robust to noise in different settings.

arXiv:1711.05712

CSWA: Aggregation-Free Spatial-Temporal Community Sensing

In this paper, we present a novel community sensing paradigm -- {C}ommunity {S}ensing {W}ithout {A}ggregation}. CSWA is designed to obtain the environment information (e.g., air pollution or temperature) in each subarea of the target area, without aggregating sensor and location data collected by community members. CSWA operates on top of a secured peer-to-peer network over the community members and proposes a novel \emph{Decentralized Spatial-Temporal Compressive Sensing} framework based on \emph{Parallelized Stochastic Gradient Descent}. Through learning the \emph{low-rank structure} via distributed optimization, CSWA approximates the value of the sensor data in each subarea (both covered and uncovered) for each sensing cycle using the sensor data locally stored in each member's mobile device. Simulation experiments based on real-world datasets demonstrate that CSWA exhibits low approximation error (i.e., less than $0.2 ^\circ$C in city-wide temperature sensing task and $10$ units of PM2.5 index in urban air pollution sensing) and performs comparably to (sometimes better than) state-of-the-art algorithms based on the data aggregation and centralized computation.

arXiv:1702.05743공식 코드 · Papers with Code

DR2-Net: Deep Residual Reconstruction Network for Image Compressive Sensing

Most traditional algorithms for compressive sensing image reconstruction suffer from the intensive computation. Recently, deep learning-based reconstruction algorithms have been reported, which dramatically reduce the time complexity than iterative reconstruction algorithms. In this paper, we propose a novel \textbf{D}eep \textbf{R}esidual \textbf{R}econstruction Network (DR$^{2}$-Net) to reconstruct the image from its Compressively Sensed (CS) measurement. The DR$^{2}$-Net is proposed based on two observations: 1) linear mapping could reconstruct a high-quality preliminary image, and 2) residual learning could further improve the reconstruction quality. Accordingly, DR$^{2}$-Net consists of two components, \emph{i.e.,} linear mapping network and residual network, respectively. Specifically, the fully-connected layer in neural network implements the linear mapping network. We then expand the linear mapping network to DR$^{2}$-Net by adding several residual learning blocks to enhance the preliminary image. Extensive experiments demonstrate that the DR$^{2}$-Net outperforms traditional iterative methods and recent deep learning-based methods by large margins at measurement rates 0.01, 0.04, 0.1, and 0.25, respectively. The code of DR$^{2}$-Net has been released on: https://github.com/coldrainyht/caffe\_dr2

arXiv:1706.03129

Measurement-Adaptive Sparse Image Sampling and Recovery

This paper presents an adaptive and intelligent sparse model for digital image sampling and recovery. In the proposed sampler, we adaptively determine the number of required samples for retrieving image based on space-frequency-gradient information content of image patches. By leveraging texture in space, sparsity locations in DCT domain, and directional decomposition of gradients, the sampler structure consists of a combination of uniform, random, and nonuniform sampling strategies. For reconstruction, we model the recovery problem as a two-state cellular automaton to iteratively restore image with scalable windows from generation to generation. We demonstrate the recovery algorithm quickly converges after a few generations for an image with arbitrary degree of texture. For a given number of measurements, extensive experiments on standard image-sets, infra-red, and mega-pixel range imaging devices show that the proposed measurement matrix considerably increases the overall recovery performance, or equivalently decreases the number of sampled pixels for a specific recovery quality compared to random sampling matrix and Gaussian linear combinations employed by the state-of-the-art compressive sensing methods. In practice, the proposed measurement-adaptive sampling/recovery framework includes various applications from intelligent compressive imaging-based acquisition devices to computer vision and graphics, and image processing technology. Simulation codes are available online for reproduction purposes.

arXiv:1711.09375

Compressive Sensing of Color Images Using Nonlocal Higher Order Dictionary

This paper addresses an ill-posed problem of recovering a color image from its compressively sensed measurement data. Differently from the typical 1D vector-based approach of the state-of-the-art methods, we exploit the nonlocal similarities inherently existing in images by treating each patch of a color image as a 3D tensor consisting of not only horizontal and vertical but also spectral dimensions. A group of nonlocal similar patches form a 4D tensor for which a nonlocal higher order dictionary is learned via higher order singular value decomposition. The multiple sub-dictionaries contained in the higher order dictionary decorrelate the group in each corresponding dimension, thus help the detail of color images to be reconstructed better. Furthermore, we promote sparsity of the final solution using a sparsity regularization based on a weight tensor. It can distinguish those coefficients of the sparse representation generated by the higher order dictionary which are expected to have large magnitude from the others in the optimization. Accordingly, in the iterative solution, it acts like a weighting process which is designed by approximating the minimum mean squared error filter for more faithful recovery. Experimental results confirm improvement by the proposed method over the state-of-the-art ones.

arXiv:1712.02423

Tomographic Reconstruction using Global Statistical Prior

Recent research in tomographic reconstruction is motivated by the need to efficiently recover detailed anatomy from limited measurements. One of the ways to compensate for the increasingly sparse sets of measurements is to exploit the information from templates, i.e., prior data available in the form of already reconstructed, structurally similar images. Towards this, previous work has exploited using a set of global and patch based dictionary priors. In this paper, we propose a global prior to improve both the speed and quality of tomographic reconstruction within a Compressive Sensing framework. We choose a set of potential representative 2D images referred to as templates, to build an eigenspace; this is subsequently used to guide the iterative reconstruction of a similar slice from sparse acquisition data. Our experiments across a diverse range of datasets show that reconstruction using an appropriate global prior, apart from being faster, gives a much lower reconstruction error when compared to the state of the art.