arXiv subjects

Xin Yuan

Publications and source records attributed to Xin Yuan.

At least 217 records · Page 12Linked to original sources

arXiv2020

Re-identification = Retrieval + Verification: Back to Essence and Forward with a New Metric

Re-identification (re-ID) is currently investigated as a closed-world image retrieval task, and evaluated by retrieval based metrics. The algorithms return ranking lists to users, but cannot tell which images are the true target. In essence, current re-ID overemphasizes the importance of retrieval but underemphasizes that of verification, \textit{i.e.}, all returned images are considered as the target. On the other hand, re-ID should also include the scenario that the query identity does not appear in the gallery. To this end, we go back to the essence of re-ID, \textit{i.e.}, a combination of retrieval and verification in an open-set setting, and put forward a new metric, namely, Genuine Open-set re-ID Metric (GOM). GOM explicitly balances the effect of performing retrieval and verification into a single unified metric. It can also be decomposed into a family of sub-metrics, enabling a clear analysis of re-ID performance. We evaluate the effectiveness of GOM on the re-ID benchmarks, showing its ability to capture important aspects of re-ID performance that have not been taken into account by established metrics so far. Furthermore, we show GOM scores excellent in aligning with human visual evaluation of re-ID performance. Related codes are available at https://github.com/YuanXinCherry/Person-reID-Evaluation

cs.CV↗

arXiv2020

CryptMPI: A Fast Encrypted MPI Library

The cloud infrastructure must provide security for High-Performance Computing (HPC) applications of sensitive data to execute in such an environment. However, supporting security in the communication infrastructure of today's public cloud is challenging, because current networks for data centers are so fast that adding encryption can incur very significant overheads. In this work, we introduce CryptMPI, a high performance encrypted MPI library that supports communication with both integrity and privacy. We present the techniques in CryptMPI and report our benchmarking results using micro-benchmarks and NAS parallel benchmarks. The evaluation results indicate that the aforementioned techniques are effective in improving the performance of encrypted communication.

cs.DC↗

arXiv2020

Performance Evaluation and Modeling of Cryptographic Libraries for MPI Communications

In order for High-Performance Computing (HPC) applications with data security requirements to execute in the public cloud, the cloud infrastructure must ensure the privacy and integrity of data. To meet this goal, we consider incorporating encryption in the Message Passing Interface (MPI) library. We empirically evaluate four contemporary cryptographic libraries, OpenSSL, BoringSSL, Libsodium, and CryptoPP using micro-benchmarks and NAS parallel benchmarks on two different networking technologies, 10Gbps Ethernet and 40Gbps InfiniBand. We also develop accurate models that allow us to reason about the performance of encrypted MPI communication in different situations and give guidance on how to improve encrypted MPI performance.

cs.DC↗

arXiv2020

ADCC: An Effective and Intelligent Attention Dense Color Constancy System for Studying Images in Smart Cities

As a novel method eliminating chromatic aberration on objects, computational color constancy has becoming a fundamental prerequisite for many computer vision applications. Among algorithms performing this task, the learning-based ones have achieved great success in recent years. However, they fail to fully consider the spatial information of images, leaving plenty of room for improvement of the accuracy of illuminant estimation. In this paper, by exploiting the spatial information of images, we propose a color constancy algorithm called Attention Dense Color Constancy (ADCC) using convolutional neural network (CNN). Specifically, based on the 2D log-chrominance histograms of the input images as well as their specially augmented ones, ADCC estimates the illuminant with a self-attention DenseNet. The augmented images help to tell apart the edge gradients, edge pixels and non-edge ones in log-histogram, which contribute significantly to the feature extraction and color-ambiguity elimination, thereby advancing the accuracy of illuminant estimation. Simulations and experiments on benchmark datasets demonstrate that the proposed algorithm is effective for illuminant estimation compared to the state-of-the-art methods. Thus, ADCC offers great potential in promoting applications of smart cities, such as smart camera, where color is an important factor for distinguishing objects.

cs.CV↗

arXiv2020

Spatial--spectral FFPNet: Attention-Based Pyramid Network for Segmentation and Classification of Remote Sensing Images

We consider the problem of segmentation and classification of high-resolution and hyperspectral remote sensing images. Unlike conventional natural (RGB) images, the inherent large scale and complex structures of remote sensing images pose major challenges such as spatial object distribution diversity and spectral information extraction when existing models are directly applied for image classification. In this study, we develop an attention-based pyramid network for segmentation and classification of remote sensing datasets. Attention mechanisms are used to develop the following modules: i) a novel and robust attention-based multi-scale fusion method effectively fuses useful spatial or spectral information at different and same scales; ii) a region pyramid attention mechanism using region-based attention addresses the target geometric size diversity in large-scale remote sensing images; and iii cross-scale attention} in our adaptive atrous spatial pyramid pooling network adapts to varied contents in a feature-embedded space. Different forms of feature fusion pyramid frameworks are established by combining these attention-based modules. First, a novel segmentation framework, called the heavy-weight spatial feature fusion pyramid network (FFPNet), is proposed to address the spatial problem of high-resolution remote sensing images. Second, an end-to-end spatial--spectral FFPNet is presented for classifying hyperspectral images. Experiments conducted on ISPRS Vaihingen and ISPRS Potsdam high-resolution datasets demonstrate the competitive segmentation accuracy achieved by the proposed heavy-weight spatial FFPNet. Furthermore, experiments on the Indian Pines and the University of Pavia hyperspectral datasets indicate that the proposed spatial--spectral FFPNet outperforms the current state-of-the-art methods in hyperspectral image classification.

cs.CV↗

arXiv2020

Plug-and-Play Algorithms for Large-scale Snapshot Compressive Imaging

Snapshot compressive imaging (SCI) aims to capture the high-dimensional (usually 3D) images using a 2D sensor (detector) in a single snapshot. Though enjoying the advantages of low-bandwidth, low-power and low-cost, applying SCI to large-scale problems (HD or UHD videos) in our daily life is still challenging. The bottleneck lies in the reconstruction algorithms; they are either too slow (iterative optimization algorithms) or not flexible to the encoding process (deep learning based end-to-end networks). In this paper, we develop fast and flexible algorithms for SCI based on the plug-and-play (PnP) framework. In addition to the widely used PnP-ADMM method, we further propose the PnP-GAP (generalized alternating projection) algorithm with a lower computational workload and prove the convergence of PnP-GAP under the SCI hardware constraints. By employing deep denoising priors, we first time show that PnP can recover a UHD color video ($3840\times 1644\times 48$ with PNSR above 30dB) from a snapshot 2D measurement. Extensive results on both simulation and real datasets verify the superiority of our proposed algorithm. The code is available at https://github.com/liuyang12/PnP-SCI.

eess.IV↗

arXiv2020

The Power of Triply Complementary Priors for Image Compressive Sensing

Recent works that utilized deep models have achieved superior results in various image restoration applications. Such approach is typically supervised which requires a corpus of training images with distribution similar to the images to be recovered. On the other hand, the shallow methods which are usually unsupervised remain promising performance in many inverse problems, \eg, image compressive sensing (CS), as they can effectively leverage non-local self-similarity priors of natural images. However, most of such methods are patch-based leading to the restored images with various ringing artifacts due to naive patch aggregation. Using either approach alone usually limits performance and generalizability in image restoration tasks. In this paper, we propose a joint low-rank and deep (LRD) image model, which contains a pair of triply complementary priors, namely \textit{external} and \textit{internal}, \textit{deep} and \textit{shallow}, and \textit{local} and \textit{non-local} priors. We then propose a novel hybrid plug-and-play (H-PnP) framework based on the LRD model for image CS. To make the optimization tractable, a simple yet effective algorithm is proposed to solve the proposed H-PnP based image CS problem. Extensive experimental results demonstrate that the proposed H-PnP algorithm significantly outperforms the state-of-the-art techniques for image CS recovery such as SCSNet and WNNM.

eess.IV↗

arXiv2020

Various Total Variation for Snapshot Video Compressive Imaging

Sampling high-dimensional images is challenging due to limited availability of sensors; scanning is usually necessary in these cases. To mitigate this challenge, snapshot compressive imaging (SCI) was proposed to capture the high-dimensional (usually 3D) images using a 2D sensor (detector). Via novel optical design, the {\em measurement} captured by the sensor is an encoded image of multiple frames of the 3D desired signal. Following this, reconstruction algorithms are employed to retrieve the high-dimensional data. Though various algorithms have been proposed, the total variation (TV) based method is still the most efficient one due to a good trade-off between computational time and performance. This paper aims to answer the question of which TV penalty (anisotropic TV, isotropic TV and vectorized TV) works best for video SCI reconstruction? Various TV denoising and projection algorithms are developed and tested for video SCI reconstruction on both simulation and real datasets.

eess.IV↗

arXiv2020

Snapshot Interferometric 3D Imaging by Compressive Sensing and Deep Learning

We demonstrate single-shot compressive three-dimensional (3D) $(x, y, z)$ imaging based on interference coding. The depth dimension of the object is encoded into the interferometric spectra of the light field, resulting a $(x, y, λ)$ datacube which is subsequently measured by a single-shot spectrometer. By implementing a compression ratio up to $400$, we are able to reconstruct $1G$ voxels from a 2D measurement. Both an optimization based compressive sensing algorithm and a deep learning network are developed for 3D reconstruction from a single 2D coded measurement. Due to the fast acquisition speed, our approach is able to capture volumetric activities at native camera frame rates, enabling 4D (volumetric-temporal) visualization of dynamic scenes.

eess.IV↗

arXiv2020

A Benchmark for Sparse Coding: When Group Sparsity Meets Rank Minimization

Sparse coding has achieved a great success in various image processing tasks. However, a benchmark to measure the sparsity of image patch/group is missing since sparse coding is essentially an NP-hard problem. This work attempts to fill the gap from the perspective of rank minimization. More details please see the manuscript....

cs.CV↗

arXiv2020

From Rank Estimation to Rank Approximation: Rank Residual Constraint for Image Restoration

In this paper, we propose a novel approach to the rank minimization problem, termed rank residual constraint (RRC) model. Different from existing low-rank based approaches, such as the well-known nuclear norm minimization (NNM) and the weighted nuclear norm minimization (WNNM), which estimate the underlying low-rank matrix directly from the corrupted observations, we progressively approximate the underlying low-rank matrix via minimizing the rank residual. Through integrating the image nonlocal self-similarity (NSS) prior with the proposed RRC model, we apply it to image restoration tasks, including image denoising and image compression artifacts reduction. Towards this end, we first obtain a good reference of the original image groups by using the image NSS prior, and then the rank residual of the image groups between this reference and the degraded image is minimized to achieve a better estimate to the desired image. In this manner, both the reference and the estimated image are updated gradually and jointly in each iteration. Based on the group-based sparse representation model, we further provide a theoretical analysis on the feasibility of the proposed RRC model. Experimental results demonstrate that the proposed RRC model outperforms many state-of-the-art schemes in both the objective and perceptual quality.

cs.CV↗

arXiv2020

Waveform Optimization for MIMO Joint Communication and Radio Sensing Systems with Training Overhead

In this paper, we study optimal waveform design to maximize mutual information (MI) for a joint communication and (radio) sensing (JCAS, a.k.a., radar-communication) multi-input multi-output (MIMO) downlink system. We consider a typical packet-based signal structure which includes training and data symbols. We first derive the conditional MI for both sensing and communication under correlated channels by considering the training overhead and channel estimation error (CEE). Then, we derive a lower bound for the channel estimation error and optimize the power allocation between the training and data symbols to minimize the CEE. Based on the optimal power allocation, we provide optimal waveform design methods for three scenarios, including maximizing MI for communication only and for sensing only, and maximizing a weighted sum MI for both communication and sensing. We also present extensive simulation results that provide insights on waveform design and validate the effectiveness of the proposed designs.

eess.SP↗

arXiv2020

Image Compression Based on Compressive Sensing: End-to-End Comparison with JPEG

We present an end-to-end image compression system based on compressive sensing. The presented system integrates the conventional scheme of compressive sampling and reconstruction with quantization and entropy coding. The compression performance, in terms of decoded image quality versus data rate, is shown to be comparable with JPEG and significantly better at the low rate range. We study the parameters that influence the system performance, including (i) the choice of sensing matrix, (ii) the trade-off between quantization and compression ratio, and (iii) the reconstruction algorithms. We propose an effective method to jointly control the quantization step and compression ratio in order to achieve near optimal quality at any given bit rate. Furthermore, our proposed image compression system can be directly used in the compressive sensing camera, e.g. the single pixel camera, to construct a hardware compressive sampling system.

cs.CV↗

arXiv2020

A realistic phase screen model for forward multiple-scattering media

Existing random phase screen (RPS) models for forward multiple-scattering media fail to incorporate ballistic light. In this letter, we redesign the angular spectrum of the screen by means of Monte-Carlo simulation based on an assumption that a single screen should represent all the scattering events a photon experiences between two adjacent screens. Three examples demonstrate that the proposed model exhibits more realistic optical properties than conventional RPS models in terms of attenuation of ballistic light, evolution of beam profile and angular memory effect. The proposed model also provides the flexibility to balance the computing accuracy, speed and memory usage by tuning the screen spacing.

physics.optics↗

arXiv2019

Pairwise-based Multi-Attribute Decision Making Approach for Wireless Network

In the wireless network applications, such as routing decision, network selection, etc., the Multi-Attribute Decision Making (MADM) has been widely used. The MADM approach can address the multi-objective decision making issues effectively.However, when the parameters vary greatly, the traditionalMADM algorithm is not effective anymore. To solve this problem,in this paper, we propose the pairwise-based MADM algorithm.In the PMADM, only two nodes utilities are calculated and compared each time. The PMADM algorithm is much more accurate than the traditional MADM algorithm. Moreover, we also prove that our PMADM algorithm is sensitive to the parameters which vary seriously and in-sensitive to the parameters which change slightly. This property is better than that of the traditional MADM algorithm. Additionally, the PMADM algorithm is more stable than the traditional MADM algorithm. For reducing the computational complexity of the PMADM algorithm, we propose the low-complexity PMADM algorithm. For analyzing the computational complexity of the lPMADM algorithm, we propose the tree-based decomposing algorithm in this paper. The lPMADM algorithm has the same properties and performances as that of the PMADM algorithm; however, it is simpler than the PMADM algorithm. The simulation results show that the PMADM and lPMADM algorithms are much more effective than the traditional MADM algorithm.

cs.NI↗

arXiv2019

Solving inverse problems via auto-encoders

Compressed sensing (CS) is about recovering a structured signal from its under-determined linear measurements. Starting from sparsity, recovery methods have steadily moved towards more complex structures. Emerging machine learning tools such as generative functions that are based on neural networks are able to learn general complex structures from training data. This makes them potentially powerful tools for designing CS algorithms. Consider a desired class of signals $\cal Q$, ${\cal Q}\subset{R}^n$, and a corresponding generative function $g:{\cal U}^k\rightarrow {R}^n$, ${\cal U}\subset {R}$, such that $\sup_{{\bf x}\in {\cal Q}}\min_{{\bf u}\in{\cal U}^k}{1\over \sqrt{n}}\|g({\bf u})-{\bf x}\|\leq δ$. A recovery method based on $g$ seeks $g({\bf u})$ with minimum measurement error. In this paper, the performance of such a recovery method is studied, under both noisy and noiseless measurements. In the noiseless case, roughly speaking, it is proven that, as $k$ and $n$ grow without bound and $δ$ converges to zero, if the number of measurements ($m$) is larger than the input dimension of the generative model ($k$), then asymptotically, almost lossless recovery is possible. Furthermore, the performance of an efficient iterative algorithm based on projected gradient descent is studied. In this case, an auto-encoder is used to define and enforce the source structure at the projection step. The auto-encoder is defined by encoder and decoder (generative) functions $f:{R}^n\to{\cal U}^k$ and $g:{\cal U}^k\to{R}^n$, respectively. We theoretically prove that, roughly, given $m>40k\log{1\over δ}$ measurements, such an algorithm converges to the vicinity of the desired result, even in the presence of additive white Gaussian noise. Numerical results exploring the effectiveness of the proposed method are presented.

cs.IT↗

arXiv2019

Game Theory based Joint Task Offloading and Resources Allocation Algorithm for Mobile Edge Computing

Mobile edge computing (MEC) has emerged for reducing energy consumption and latency by allowing mobile users to offload computationally intensive tasks to the MEC server. Due to the spectrum reuse in small cell network, the inter-cell interference has a great effect on MEC performances. In this paper, for reducing the energy consumption and latency of MEC, we propose a game theory based approach to join task offloading decision and resources allocation together in the MEC system. In this algorithm, the offloading decision, the CPU capacity adjustment, the transmission power control, and the network interference management of mobile users are regarded as a game. In this game, based on the best response strategy, each mobile user makes their own utility maximum rather than the utility of the whole system. We prove that this game is an exact potential game and the Nash equilibrium (NE) of this game exists. For reaching the NE, the best response approach is applied. We calculate the best response of these three variables. Moreover, we investigate the properties of this algorithm, including the convergence, the computational complexity, and the Price of anarchy (PoA). The theoretical analysis shows that the inter-cell interference affects on the performances of MEC greatly. The NE of this game is Pareto efficiency. Finally, we evaluate the performances of this algorithm by simulation. The simulation results illustrate that this algorithm is effective in improving the performances of the multi-user MEC system.

cs.NI↗

arXiv2019

The Network-based Candidate Forwarding Set Optimization Approach for Opportunistic Routing in Wireless Sensor Network

In wireless sensor networks (WSNs), the opportunistic routing has better performances on packet delivery probability than the deterministic routing. For reducing the transmission delay and duplicate transmission in opportunistic routing, the candidate forwarding set optimization technology is proposed. This technology is crucial to opportunistic routing. The prior arts have limitations on improving the routing performances. Therefore, in this paper, we propose the concept of the network-based approach to address the disadvantages of prior arts. In the network-based approach, the nodes in the candidate forwarding set are divided into different fully connected relay networks. For the forwarding nodes in CFS, more than one relay network can be constructed and only one relay network can be chosen as the final relay network. So, first, we propose the fully connected relay network judgment algorithm to judge whether the chosen network is fully connected or not. Next, the properties of these networks are investigated. In this algorithm, the relay network selection takes the packet delivery probability between the sender and the relay networks, the transmission delay, and the forwarding priorities of nodes in relay networks into account to choose the most effective relay network. The nodes in this relay network will be chosen as final forwarding nodes. By these, the transmission delay and duplicate transmission are reduced while the efficiency of opportunistic routing is kept. Based on these innovations, the proposed algorithm can improve network performances greater than that of ExOR and SOAR.

cs.NI↗