arXiv subjects

Jing Zhang

Publications and source records attributed to Jing Zhang.

At least 829 records · Page 46Linked to original sources

arXiv2020

Registration of multi-view point sets under the perspective of expectation-maximization

Registration of multi-view point sets is a prerequisite for 3D model reconstruction. To solve this problem, most of previous approaches either partially explore available information or blindly utilize unnecessary information to align each point set, which may lead to the undesired results or introduce extra computation complexity. To this end, this paper consider the multi-view registration problem as a maximum likelihood estimation problem and proposes a novel multi-view registration approach under the perspective of Expectation-Maximization (EM). The basic idea of our approach is that different data points are generated by the same number of Gaussian mixture models (GMMs). For each data point in one point set, its nearest neighbors can be searched from other well-aligned point sets. Then, we can suppose this data point is generated by the special GMM, which is composed of each nearest neighbor adhered with one Gaussian distribution. Based on this assumption, it is reasonable to define the likelihood function including all rigid transformations, which requires to be estimated for multi-view registration. Subsequently, the EM algorithm is utilized to maximize the likelihood function so as to estimate all rigid transformations. Finally, the proposed approach is tested on several bench mark data sets and compared with some state-of-the-art algorithms. Experimental results illustrate its super performance on accuracy, robustness and efficiency for the registration of multi-view point sets.

cs.CV↗

arXiv2020

JarKA: Modeling Attribute Interactions for Cross-lingual Knowledge Alignment

Abstract. Cross-lingual knowledge alignment is the cornerstone in building a comprehensive knowledge graph (KG), which can benefit various knowledge-driven applications. As the structures of KGs are usually sparse, attributes of entities may play an important role in aligning the entities. However, the heterogeneity of the attributes across KGs prevents from accurately embedding and comparing entities. To deal with the issue, we propose to model the interactions between attributes, instead of globally embedding an entity with all the attributes. We further propose a joint framework to merge the alignments inferred from the attributes and the structures. Experimental results show that the proposed model outperforms the state-of-art baselines by up to 38.48% HitRatio@1. The results also demonstrate that our model can infer the alignments between attributes, relationships and values, in addition to entities.

cs.CL↗

arXiv2020

A regression-based method for detecting publication bias in multivariate meta-analysis

Publication bias occurs when the publication of research results depends not only on the quality of the research but also on its nature and direction. The consequence is that published studies may not be truly representative of all valid studies undertaken, and this bias may threaten the validity of systematic reviews and meta-analyses - on which evidence-based medicine increasingly relies. Multivariate meta-analysis has recently received increasing attention for its ability reducing potential bias and improving statistical efficiency by borrowing information across outcomes. However, detecting and accounting for publication bias are more challenging in multivariate meta-analysis setting because some studies may be completely unpublished whereas some studies may selectively report part of multiple outcomes. In this paper, we propose a score test for jointly testing publication bias for multiple outcomes, which is novel to the multivariate setting. The proposed test is a natural multivariate extension of the univariate Egger's test, and can handle the above mentioned scenarios simultaneously, It accounts for correlations among multivariate outcomes, while allowing different types of outcomes, and can borrow information across outcomes. The proposed test is shown to be more powerful than the Egger's test, Begg's test and Trim and Fill method through simulation studies. Two data analyses are given to illustrate the performance of the proposed test in practice.

stat.ME↗

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↗

arXiv2020

SK-Unet: an Improved U-net Model with Selective Kernel for the Segmentation of Multi-sequence Cardiac MR

In the clinical environment, myocardial infarction (MI) as one com-mon cardiovascular disease is mainly evaluated based on the late gadolinium enhancement (LGE) cardiac magnetic resonance images (CMRIs). The auto-matic segmentations of left ventricle (LV), right ventricle (RV), and left ven-tricular myocardium (LVM) in the LGE CMRIs are desired for the aided diag-nosis in clinic. To accomplish this segmentation task, this paper proposes a modified U-net architecture by combining multi-sequence CMRIs, including the cine, LGE, and T2-weighted CMRIs. The cine and T2-weighted CMRIs are used to assist the segmentation in the LGE CMRIs. In this segmentation net-work, the squeeze-and-excitation residual (SE-Res) and selective kernel (SK) modules are inserted in the down-sampling and up-sampling stages, respective-ly. The SK module makes the obtained feature maps more informative in both spatial and channel-wise space, and attains more precise segmentation result. The utilized dataset is from the MICCAI challenge (MS-CMRSeg 2019), which is acquired from 45 patients including three CMR sequences. The cine and T2-weighted CMRIs acquired from 35 patients and the LGE CMRIs acquired from 5 patients are labeled. Our method achieves the mean dice score of 0.922 (LV), 0.827 (LVM), and 0.874 (RV) in the LGE CMRIs.

eess.IV↗

arXiv2020

Ensemble emotion recognizing with multiple modal physiological signals

Physiological signals that provide the objective repression of human affective states are attracted increasing attention in the emotion recognition field. However, the single signal is difficult to obtain completely and accurately description for emotion. Multiple physiological signals fusing models, building the uniform classification model by means of consistent and complementary information from different emotions to improve recognition performance. Original fusing models usually choose the particular classification method to recognition, which is ignoring different distribution of multiple signals. Aiming above problems, in this work, we propose an emotion classification model through multiple modal physiological signals for different emotions. Features are extracted from EEG, EMG, EOG signals for characterizing emotional state on valence and arousal levels. For characterization, four bands filtering theta, beta, alpha, gamma for signal preprocessing are adopted and three Hjorth parameters are computing as features. To improve classification performance, an ensemble classifier is built. Experiments are conducted on the benchmark DEAP datasets. For the two-class task, the best result on arousal is 94.42\%, the best result on valence is 94.02\%, respectively. For the four-class task, the highest average classification accuracy is 90.74, and it shows good stability. The influence of different peripheral physiological signals for results is also analyzed in this paper.

cs.LG↗

arXiv2019

Deep Time-Frequency Representation and Progressive Decision Fusion for ECG Classification

Early recognition of abnormal rhythms in ECG signals is crucial for monitoring and diagnosing patients' cardiac conditions, increasing the success rate of the treatment. Classifying abnormal rhythms into exact categories is very challenging due to the broad taxonomy of rhythms, noises and lack of large-scale real-world annotated data. Different from previous methods that utilize hand-crafted features or learn features from the original signal domain, we propose a novel ECG classification method by learning deep time-frequency representation and progressive decision fusion at different temporal scales in an end-to-end manner. First, the ECG wave signal is transformed into the time-frequency domain by using the Short-Time Fourier Transform. Next, several scale-specific deep convolutional neural networks are trained on ECG samples of a specific length. Finally, a progressive online decision fusion method is proposed to fuse decisions from the scale-specific models into a more accurate and stable one. Extensive experiments on both synthetic and real-world ECG datasets demonstrate the effectiveness and efficiency of the proposed method.

cs.LG↗

arXiv2019

Monochromatic Sumset Without the use of large cardinals

We show in this note that in the forcing extension by $Add(ω,\beth_ω)$, the following Ramsey property holds: for any $r\in ω$ and any $f: \mathbb{R}\to r$, there exists an infinite $X\subset \mathbb{R}$ such that $X+X$ is monochromatic under $f$. We also show the Ramsey statement above is true in $\mathrm{ZFC}$ when $r=2$. This answers two questions by Komjáth, Leader, Russell, Shelah, Soukup and Vidnyánszky.

math.LO↗

arXiv2019

Category Anchor-Guided Unsupervised Domain Adaptation for Semantic Segmentation

Unsupervised domain adaptation (UDA) aims to enhance the generalization capability of a certain model from a source domain to a target domain. UDA is of particular significance since no extra effort is devoted to annotating target domain samples. However, the different data distributions in the two domains, or \emph{domain shift/discrepancy}, inevitably compromise the UDA performance. Although there has been a progress in matching the marginal distributions between two domains, the classifier favors the source domain features and makes incorrect predictions on the target domain due to category-agnostic feature alignment. In this paper, we propose a novel category anchor-guided (CAG) UDA model for semantic segmentation, which explicitly enforces category-aware feature alignment to learn shared discriminative features and classifiers simultaneously. First, the category-wise centroids of the source domain features are used as guided anchors to identify the active features in the target domain and also assign them pseudo-labels. Then, we leverage an anchor-based pixel-level distance loss and a discriminative loss to drive the intra-category features closer and the inter-category features further apart, respectively. Finally, we devise a stagewise training mechanism to reduce the error accumulation and adapt the proposed model progressively. Experiments on both the GTA5$\rightarrow $Cityscapes and SYNTHIA$\rightarrow $Cityscapes scenarios demonstrate the superiority of our CAG-UDA model over the state-of-the-art methods. The code is available at \url{https://github.com/RogerZhangzz/CAG_UDA}.

cs.CV↗

arXiv2019

Some remarks on uncountable rainbow Ramsey theory

We discuss the rainbow Ramsey theorems at limit cardinals and successors of singular cardinals, addressing some questions in \cite{MR2354904} and \cite{MR2902230}. In particular, we show for inaccessible $κ$, $κ\to^{poly}(κ)^2_{2-bdd}$ does not characterize weak compactness and for singular $κ$, $\mathrm{GCH}+\square_κ$ implies $κ^+\not\to^{poly} (η)^2_{<κ-bdd}$ for any $η\geq cf(κ)^+$ and $κ^+\to^{poly} (ν)^2_{<κ-bdd}$ for any $ν<cf(κ)^+$. We also provide a simplified construction of a model for $ω_2\not\to^{poly} (ω_1)^2_{2-bdd}$ originally constructed in \cite{MR2902230} and show the witnessing coloring is indestructible under strongly proper forcings but destructible under some c.c.c forcing. Finally, we conclude with some remarks and questions on possible generalizations to rainbow partition relations for triples.

math.LO↗

arXiv2019

Grapy-ML: Graph Pyramid Mutual Learning for Cross-dataset Human Parsing

Human parsing, or human body part semantic segmentation, has been an active research topic due to its wide potential applications. In this paper, we propose a novel GRAph PYramid Mutual Learning (Grapy-ML) method to address the cross-dataset human parsing problem, where the annotations are at different granularities. Starting from the prior knowledge of the human body hierarchical structure, we devise a graph pyramid module (GPM) by stacking three levels of graph structures from coarse granularity to fine granularity subsequently. At each level, GPM utilizes the self-attention mechanism to model the correlations between context nodes. Then, it adopts a top-down mechanism to progressively refine the hierarchical features through all the levels. GPM also enables efficient mutual learning. Specifically, the network weights of the first two levels are shared to exchange the learned coarse-granularity information across different datasets. By making use of the multi-granularity labels, Grapy-ML learns a more discriminative feature representation and achieves state-of-the-art performance, which is demonstrated by extensive experiments on the three popular benchmarks, e.g. CIHP dataset. The source code is publicly available at https://github.com/Charleshhy/Grapy-ML.

cs.CV↗

arXiv2019

Progressive Retinex: Mutually Reinforced Illumination-Noise Perception Network for Low Light Image Enhancement

Contrast enhancement and noise removal are coupled problems for low-light image enhancement. The existing Retinex based methods do not take the coupling relation into consideration, resulting in under or over-smoothing of the enhanced images. To address this issue, this paper presents a novel progressive Retinex framework, in which illumination and noise of low-light image are perceived in a mutually reinforced manner, leading to noise reduction low-light enhancement results. Specifically, two fully pointwise convolutional neural networks are devised to model the statistical regularities of ambient light and image noise respectively, and to leverage them as constraints to facilitate the mutual learning process. The proposed method not only suppresses the interference caused by the ambiguity between tiny textures and image noises, but also greatly improves the computational efficiency. Moreover, to solve the problem of insufficient training data, we propose an image synthesis strategy based on camera imaging model, which generates color images corrupted by illumination-dependent noises. Experimental results on both synthetic and real low-light images demonstrate the superiority of our proposed approaches against the State-Of-The-Art (SOTA) low-light enhancement methods.

eess.IV↗

arXiv2019

Spatiotemporal graph states from a single optical parametric oscillator

An experimental scheme is proposed for building massively multipartite entangled states using both the spatial and the frequency modes of an optical parametric oscillator. We provide analytical forms of the entangled states using the squeezed eigenmodes of Heisenberg equations, a.k.a. the nullifiers of the corresponding graph state. This scheme can generate, in parallel, several cluster states described by sparsely connected, bicolorable graph states, usable for one-way quantum computing. We indicate the experimentally accessible quantum graphs, depending on the squeezing parameter.

quant-ph↗

arXiv2019

Human Keypoint Detection by Progressive Context Refinement

Human keypoint detection from a single image is very challenging due to occlusion, blur, illumination and scale variance of person instances. In this paper, we find that context information plays an important role in addressing these issues, and propose a novel method named progressive context refinement (PCR) for human keypoint detection. First, we devise a simple but effective context-aware module (CAM) that can efficiently integrate spatial and channel context information to aid feature learning for locating hard keypoints. Then, we construct the PCR model by stacking several CAMs sequentially with shortcuts and employ multi-task learning to progressively refine the context information and predictions. Besides, to maximize PCR's potential for the aforementioned hard case inference, we propose a hard-negative person detection mining strategy together with a joint-training strategy by exploiting the unlabeled coco dataset and external dataset. Extensive experiments on the COCO keypoint detection benchmark demonstrate the superiority of PCR over representative state-of-the-art (SOTA) methods. Our single model achieves comparable performance with the winner of the 2018 COCO Keypoint Detection Challenge. The final ensemble model sets a new SOTA on this benchmark.

cs.CV↗

arXiv2019

MIOpen: An Open Source Library For Deep Learning Primitives

Deep Learning has established itself to be a common occurrence in the business lexicon. The unprecedented success of deep learning in recent years can be attributed to: abundance of data, availability of gargantuan compute capabilities offered by GPUs, and adoption of open-source philosophy by the researchers and industry. Deep neural networks can be decomposed into a series of different operators. MIOpen, AMD's open-source deep learning primitives library for GPUs, provides highly optimized implementations of such operators, shielding researchers from internal implementation details and hence, accelerating the time to discovery. This paper introduces MIOpen and provides details about the internal workings of the library and supported features. MIOpen innovates on several fronts, such as implementing fusion to optimize for memory bandwidth and GPU launch overheads, providing an auto-tuning infrastructure to overcome the large design space of problem configurations, and implementing different algorithms to optimize convolutions for different filter and input sizes. MIOpen is one of the first libraries to publicly support the bfloat16 data-type for convolutions, allowing efficient training at lower precision without the loss of accuracy.

cs.LG↗

arXiv2019

Joint Estimation of OD Demands and Cost Functions in Transportation Networks from Data

Existing work has tackled the problem of estimating Origin-Destination (OD) demands and recovering travel latency functions in transportation networks under the Wardropian assumption. The ultimate objective is to derive an accurate predictive model of the network to enable optimization and control. However, these two problems are typically treated separately and estimation is based on parametric models. In this paper, we propose a method to jointly recover nonparametric travel latency cost functions and estimate OD demands using traffic flow data. We formulate the problem as a bilevel optimization problem and develop an iterative first-order optimization algorithm to solve it. A numerical example using the Braess Network is presented to demonstrate the effectiveness of our method.

math.OC↗

arXiv2019

Some New Questions on Point-countable Covers and Sequence-covering Mappings

In this survey, 37 questions on point-countable covers and sequence-covering mappings are listed, in which some of these questions have been answered. These questions are mainly related to the theory of generalized metric spaces, involving point-countable covers, sequence-covering mappings, images of metric spaces and hereditarily closure-preserving families.

math.GN↗

arXiv2019

Optimal Sliced Latin Hypercube Designs with Slices of Arbitrary Run Sizes

Sliced Latin hypercube designs (SLHDs) are widely used in computer experiments with both quantitative and qualitative factors and in batches. Optimal SLHDs achieve better space-filling property on the whole experimental region. However, most existing methods for constructing optimal SLHDs have restriction on the run sizes. In this paper, we propose a new method for constructing SLHDs with arbitrary run sizes, and a new combined space-filling measurement describing the space-filling property for both the whole design and its slices. Furthermore, we develop general algorithms to search the optimal SLHD with arbitrary run sizes under the proposed measurement. Examples are presented to illustrate that effectiveness of the proposed methods.

math.ST↗