arXiv subjects

Jie Wen

Publications and source records attributed to Jie Wen.

69 records · Page 4Linked to original sources

arXiv2022

Global-Supervised Contrastive Loss and View-Aware-Based Post-Processing for Vehicle Re-Identification

In this paper, we propose a Global-Supervised Contrastive loss and a view-aware-based post-processing (VABPP) method for the field of vehicle re-identification. The traditional supervised contrastive loss calculates the distances of features within the batch, so it has the local attribute. While the proposed Global-Supervised Contrastive loss has new properties and has good global attributes, the positive and negative features of each anchor in the training process come from the entire training set. The proposed VABPP method is the first time that the view-aware-based method is used as a post-processing method in the field of vehicle re-identification. The advantages of VABPP are that, first, it is only used during testing and does not affect the training process. Second, as a post-processing method, it can be easily integrated into other trained re-id models. We directly apply the view-pair distance scaling coefficient matrix calculated by the model trained in this paper to another trained re-id model, and the VABPP method greatly improves its performance, which verifies the feasibility of the VABPP method.

cs.CV↗

arXiv2022

ACTIVE:Augmentation-Free Graph Contrastive Learning for Partial Multi-View Clustering

In this paper, we propose an augmentation-free graph contrastive learning framework, namely ACTIVE, to solve the problem of partial multi-view clustering. Notably, we suppose that the representations of similar samples (i.e., belonging to the same cluster) and their multiply views features should be similar. This is distinct from the general unsupervised contrastive learning that assumes an image and its augmentations share a similar representation. Specifically, relation graphs are constructed using the nearest neighbours to identify existing similar samples, then the constructed inter-instance relation graphs are transferred to the missing views to build graphs on the corresponding missing data. Subsequently, two main components, within-view graph contrastive learning (WGC) and cross-view graph consistency learning (CGC), are devised to maximize the mutual information of different views within a cluster. The proposed approach elevates instance-level contrastive learning and missing data inference to the cluster-level, effectively mitigating the impact of individual missing data on clustering. Experiments on several challenging datasets demonstrate the superiority of our proposed methods.

cs.CV↗

arXiv2021

Automated assessment of disease severity of COVID-19 using artificial intelligence with synthetic chest CT

Background: Triage of patients is important to control the pandemic of coronavirus disease 2019 (COVID-19), especially during the peak of the pandemic when clinical resources become extremely limited. Purpose: To develop a method that automatically segments and quantifies lung and pneumonia lesions with synthetic chest CT and assess disease severity in COVID-19 patients. Materials and Methods: In this study, we incorporated data augmentation to generate synthetic chest CT images using public available datasets (285 datasets from "Lung Nodule Analysis 2016"). The synthetic images and masks were used to train a 2D U-net neural network and tested on 203 COVID-19 datasets to generate lung and lesion segmentations. Disease severity scores (DL: damage load; DS: damage score) were calculated based on the segmentations. Correlations between DL/DS and clinical lab tests were evaluated using Pearson's method. A p-value < 0.05 was considered as statistical significant. Results: Automatic lung and lesion segmentations were compared with manual annotations. For lung segmentation, the median values of dice similarity coefficient, Jaccard index and average surface distance, were 98.56%, 97.15% and 0.49 mm, respectively. The same metrics for lesion segmentation were 76.95%, 62.54% and 2.36 mm, respectively. Significant (p << 0.05) correlations were found between DL/DS and percentage lymphocytes tests, with r-values of -0.561 and -0.501, respectively. Conclusion: An AI system that based on thoracic radiographic and data augmentation was proposed to segment lung and lesions in COVID-19 patients. Correlations between imaging findings and clinical lab tests suggested the value of this system as a potential tool to assess disease severity of COVID-19.

eess.IV↗

arXiv2021

Unsupervised COVID-19 Lesion Segmentation in CT Using Cycle Consistent Generative Adversarial Network

COVID-19 has become a global pandemic and is still posing a severe health risk to the public. Accurate and efficient segmentation of pneumonia lesions in CT scans is vital for treatment decision-making. We proposed a novel unsupervised approach using cycle consistent generative adversarial network (cycle-GAN) which automates and accelerates the process of lesion delineation. The workflow includes lung volume segmentation, "synthetic" healthy lung generation, infected and healthy image subtraction, and binary lesion mask creation. The lung volume volume was firstly delineated using a pre-trained U-net and worked as the input for the later network. The cycle-GAN was developed to generate synthetic "healthy" lung CT images from infected lung images. After that, the pneumonia lesions are extracted by subtracting the synthetic "healthy" lung CT images from the "infected" lung CT images. A median filter and K-means clustering were then applied to contour the lesions. The auto segmentation approach was validated on two public datasets (Coronacases and Radiopedia). The Dice coefficients reached 0.748 and 0.730, respectively, for the Coronacases and Radiopedia datasets. Meanwhile, the precision and sensitivity for lesion segmentationdetection are 0.813 and 0.735 for the Coronacases dataset, and 0.773 and 0.726 for the Radiopedia dataset. The performance is comparable to existing supervised segmentation networks and outperforms previous unsupervised ones. The proposed unsupervised segmentation method achieved high accuracy and efficiency in automatic COVID-19 lesion delineation. The segmentation result can serve as a baseline for further manual modification and a quality assurance tool for lesion diagnosis. Furthermore, due to its unsupervised nature, the result is not influenced by physicians' experience which otherwise is crucial for supervised methods.

eess.IV↗

arXiv2021

Applications And Potentials Of Intelligent Swarms For Magnetospheric Studies

Earth's magnetosphere is vital for today's technologically dependent society. To date, numerous design studies have been conducted and over a dozen science missions have own to study the magnetosphere. However, a majority of these solutions relied on large monolithic satellites, which limited the spatial resolution of these investigations, as did the technological limitations of the past. To counter these limitations, we propose the use of a satellite swarm carrying numerous and distributed payloads for magnetospheric measurements. Our mission is named APIS (Applications and Potentials of Intelligent Swarms), which aims to characterize fundamental plasma processes in the Earth's magnetosphere and measure the effect of the solar wind on our magnetosphere. We propose a swarm of 40 CubeSats in two highly-elliptical orbits around the Earth, which perform radio tomography in the magnetotail at 8-12 Earth Radii (RE) downstream, and the subsolar magnetosphere at 8-12RE upstream. In addition, in-situ measurements of the magnetic and electric fields, plasma density will be performed by on-board instruments. In this article, we present an outline of previous missions and designs for magnetospheric studies, along with the science drivers and motivation for the APIS mission. Furthermore, preliminary design results are included to show the feasibility of such a mission. The science requirements drive the APIS mission design, the mission operation and the system requirements. In addition to the various science payloads, critical subsystems of the satellites are investigated e.g., navigation, communication, processing and power systems. We summarize our findings, along with the potential next steps to strengthen our design study.

astro-ph.IM↗

arXiv2020

Vehicle Re-identification Based on Dual Distance Center Loss

Recently, deep learning has been widely used in the field of vehicle re-identification. When training a deep model, softmax loss is usually used as a supervision tool. However, the softmax loss performs well for closed-set tasks, but not very well for open-set tasks. In this paper, we sum up five shortcomings of center loss and solved all of them by proposing a dual distance center loss (DDCL). Especially we solve the shortcoming that center loss must combine with the softmax loss to supervise training the model, which provides us with a new perspective to examine the center loss. In addition, we verify the inconsistency between the proposed DDCL and softmax loss in the feature space, which makes the center loss no longer be limited by the softmax loss in the feature space after removing the softmax loss. To be specifically, we add the Pearson distance on the basis of the Euclidean distance to the same center, which makes all features of the same class be confined to the intersection of a hypersphere and a hypercube in the feature space. The proposed Pearson distance strengthens the intra-class compactness of the center loss and enhances the generalization ability of center loss. Moreover, by designing a Euclidean distance threshold between all center pairs, which not only strengthens the inter-class separability of center loss, but also makes the center loss (or DDCL) works well without the combination of softmax loss. We apply DDCL in the field of vehicle re-identification named VeRi-776 dataset and VehicleID dataset. And in order to verify its good generalization ability, we also verify it in two datasets commonly used in the field of person re-identification named MSMT17 dataset and Market1501 dataset.

cs.CV↗

arXiv2020

Fast library-driven approach for implementation of the voxel spread function technique for correcting magnetic field inhomogeneity artifacts

Purpose: Previously-developed Voxel Spread Function (VSF) method (Yablonskiy, et al, MRM, 2013;70:1283) provides means to correct artifacts induced by macroscopic magnetic field inhomogeneities in the images obtained by multi-Gradient-Recalled-Echo (mGRE) techniques. The goal of this study is to develop a library-driven approach for fast VSF implementation. Methods: The VSF approach describes the contribution of the magnetic field inhomogeneity effects on the mGRE signal decay in terms of the F-function calculated from mGRE phase and magnitude images. A pre-calculated library accounting for a variety of background field gradients caused by magnetic field inhomogeneities was used herein to speed up calculation of the F-function and to generate quantitative R2* maps from the mGRE data collected from two healthy volunteers. Results: As compared with direct calculation of the F-function based on a voxel-wise approach, the new library-driven method substantially reduces computational time from several hours to few minutes, while, at the same time, providing similar accuracy of R2* mapping. Conclusion: The new procedure proposed in this study provides a fast post-processing algorithm that can be incorporated in the quantitative analysis of mGRE data to account for background field inhomogeneity artifacts, thus can facilitate the applications of mGRE-based quantitative techniques in clinical practices.

q-bio.QM↗

arXiv2020

Measurement of the neutron beam profile of the Back-n white neutron facility at CSNS with a Micromegas detector

The Back-n white neutron beam line, which uses back-streaming white neutrons from the spallation target of the China Spallation Neutron Source, is used for nuclear data measurements. A Micromegas-based neutron detector with two variants was specially developed to measure the beam spot distribution for this beam line. In this article, the design, fabrication, and characterization of the detector are described. The results of the detector performance tests are presented, which include the relative electron transparency, the gain and the gain uniformity, and the neutron beam profile reconstruction capability. The result of the first measurement of the Back-n neutron beam spot distribution is also presented.

physics.ins-det↗

arXiv2019

Measurements of differential and angle-integrated cross sections for the $^{10}$B($n, α$)$^{7}$Li reaction in the neutron energy range from 1.0 eV to 2.5 MeV

Differential and angle-integrated cross sections for the $^{10}$B($n, α$)$^{7}$Li, $^{10}$B($n, α$$_{0}$)$^{7}$Li and $^{10}$B($n, α$$_{1}$)$^{7}$Li$^{*}$ reactions have been measured at CSNS Back-n white neutron source. Two enriched (90%) $^{10}$B samples 5.0 cm in diameter and ~85.0 $μ$g/cm$^{2}$ in thickness each with an aluminum backing were prepared, and back-to-back mounted at the sample holder. The charged particles were detected using the silicon-detector array of the Light-charged Particle Detector Array (LPDA) system. The neutron energy E$_{n}$ was determined by TOF (time-of-flight) method, and the valid $α$ events were extracted from the E$_{n}$-Amplitude two-dimensional spectrum. With 15 silicon detectors, the differential cross sections of $α$-particles were measured from 19.2° to 160.8°. Fitted with the Legendre polynomial series, the ($n, α$) cross sections were obtained through integration. The absolute cross sections were normalized using the standard cross sections of the $^{10}$B($n, α$)$^{7}$Li reaction in the 0.3 - 0.5 MeV neutron energy region. The measurement neutron energy range for the $^{10}$B($n, α$)$^{7}$Li reaction is 1.0 eV $\le$ En < 2.5 MeV (67 energy points), and for the $^{10}$B($n, α$$_{0}$)$^{7}$Li and $^{10}$B($n, α$$_{1}$)$^{7}$Li$^{*}$ reactions is 1.0 eV $\le$ En < 1.0 MeV (59 energy points). The present results have been analyzed by the resonance reaction mechanism and the level structure of the $^{11}$B compound system, and compared with existing measurements and evaluations.

nucl-ex↗

arXiv2019

Enhanced CNN for image denoising

Owing to flexible architectures of deep convolutional neural networks (CNNs), CNNs are successfully used for image denoising. However, they suffer from the following drawbacks: (i) deep network architecture is very difficult to train. (ii) Deeper networks face the challenge of performance saturation. In this study, the authors propose a novel method called enhanced convolutional neural denoising network (ECNDNet). Specifically, they use residual learning and batch normalisation techniques to address the problem of training difficulties and accelerate the convergence of the network. In addition, dilated convolutions are used in the proposed network to enlarge the context information and reduce the computational cost. Extensive experiments demonstrate that the ECNDNet outperforms the state-of-the-art methods for image denoising.

cs.CV↗

arXiv2019

Adaptive Locality Preserving Regression

This paper proposes a novel discriminative regression method, called adaptive locality preserving regression (ALPR) for classification. In particular, ALPR aims to learn a more flexible and discriminative projection that not only preserves the intrinsic structure of data, but also possesses the properties of feature selection and interpretability. To this end, we introduce a target learning technique to adaptively learn a more discriminative and flexible target matrix rather than the pre-defined strict zero-one label matrix for regression. Then a locality preserving constraint regularized by the adaptive learned weights is further introduced to guide the projection learning, which is beneficial to learn a more discriminative projection and avoid overfitting. Moreover, we replace the conventional `Frobenius norm' with the special l21 norm to constrain the projection, which enables the method to adaptively select the most important features from the original high-dimensional data for feature extraction. In this way, the negative influence of the redundant features and noises residing in the original data can be greatly eliminated. Besides, the proposed method has good interpretability for features owing to the row-sparsity property of the l21 norm. Extensive experiments conducted on the synthetic database with manifold structure and many real-world databases prove the effectiveness of the proposed method.

cs.CV↗

arXiv2018

Incomplete Multi-view Clustering via Graph Regularized Matrix Factorization

Clustering with incomplete views is a challenge in multi-view clustering. In this paper, we provide a novel and simple method to address this issue. Specifically, the proposed method simultaneously exploits the local information of each view and the complementary information among views to learn the common latent representation for all samples, which can greatly improve the compactness and discriminability of the obtained representation. Compared with the conventional graph embedding methods, the proposed method does not introduce any extra regularization term and corresponding penalty parameter to preserve the local structure of data, and thus does not increase the burden of extra parameter selection. By imposing the orthogonal constraint on the basis matrix of each view, the proposed method is able to handle the out-of-sample. Moreover, the proposed method can be viewed as a unified framework for multi-view learning since it can handle both incomplete and complete multi-view clustering and classification tasks. Extensive experiments conducted on several multi-view datasets prove that the proposed method can significantly improve the clustering performance.

cs.CV↗

arXiv2016

Local Multiple Directional Pattern of Palmprint Image

Lines are the most essential and discriminative features of palmprint images, which motivate researches to propose various line direction based methods for palmprint recognition. Conventional methods usually capture the only one of the most dominant direction of palmprint images. However, a number of points in palmprint images have double or even more than two dominant directions because of a plenty of crossing lines of palmprint images. In this paper, we propose a local multiple directional pattern (LMDP) to effectively characterize the multiple direction features of palmprint images. LMDP can not only exactly denote the number and positions of dominant directions but also effectively reflect the confidence of each dominant direction. Then, a simple and effective coding scheme is designed to represent the LMDP and a block-wise LMDP descriptor is used as the feature space of palmprint images in palmprint recognition. Extensive experimental results demonstrate the superiority of the LMDP over the conventional powerful descriptors and the state-of-the-art direction based methods in palmprint recognition.

cs.CV↗

arXiv2014

A dedicated high resolution PET imager for plant sciences

PET provides in vivo molecular and functional imaging capability that is crucial to studying the interaction of plant with changing environment at the whole-plant level. We have developed a dedicated plant PET imager that features high spatial resolution, housed in a fully controlled environment provided by a plant growth chamber (PGC). The system currently contains two types of detector modules: 84 microPET R4 block detectors with 2.2 mm crystals to provide a large detecting area; and 32 Inveon block detectors with 1.5 mm crystals to provide higher spatial resolution. Outputs of the four microPET block detectors in a modular housing are concatenated by a custom printed circuit board to match the output characteristics of an Inveon detector. All the detectors are read out by QuickSilver electronics. The detector modules are configured to full rings with a 15 cm diameter trans-axial field of view (FOV) for dynamic tomographic imaging of small plants. Potentially, the Inveon detectors can be reconfigured to quarter-rings to get a 25 cm FOV using step-and-shoot motion. The imager contains 2 linear stages to position detectors at different heights for multi-bed scanning, and 2 rotation stages to collect coincidence events from all angles. The PET system has been built and integrated into the PGC. The system has a typical energy resolution of 15% for Inveon blocks and 24% for R4 blocks; timing resolution of 1.8 ns; and sensitivity of 1.3%,1.4%,3.0% measured at center of FOV, 5 cm off to R4 half-ring and 5 cm off to Inveon half-ring, respectively(with a 350-650 KeV energy and 3.1 ns timing window). System spatial resolution is similar to that of commercial microPET sytems, with 1.25 mm rod sources in the micro-Derenzo phantom resolved using ML-EM algorithm. Preliminary imaging experiments using different plants labeled with 11C-CO2 produced high-quality dynamic PET images.

physics.ins-det↗

arXiv2014

Operator Preparation and Characteristic Analysis of Open Quantum Systems Based on the Lyapunov Control Method

The control laws based on quantum Lyapunov control method are designed to prepare operators for two level open quantum systems in this paper. A novel Lyapunov function is proposed according to a matrix logarithm function. The higher accuracy and faster convergence of the novel Lyapunov function proposed are analyzed by comparing with the operator distance . We adopt three control fields, and design two types of control law forms. The first form is to use one control law to offset the influence of the dissipation, while the other one is to use all three control laws to offset the dissipation. Moreover, the robustness of the system Hamiltonian with uncertainty is further investigated to comprehend the performances of control laws. NOT gates are prepared by the designed control laws for open quantum systems as well as closed quantum systems in numerical experiments to verify the superiority of, in which the performance indexes of distance and fidelity are compared and analyzed.

math-ph↗