arXiv subjects

Jun Liu

Publications and source records attributed to Jun Liu.

At least 721 records · Page 40Linked to original sources

arXiv2020

Bi-directional Dermoscopic Feature Learning and Multi-scale Consistent Decision Fusion for Skin Lesion Segmentation

Accurate segmentation of skin lesion from dermoscopic images is a crucial part of computer-aided diagnosis of melanoma. It is challenging due to the fact that dermoscopic images from different patients have non-negligible lesion variation, which causes difficulties in anatomical structure learning and consistent skin lesion delineation. In this paper, we propose a novel bi-directional dermoscopic feature learning (biDFL) framework to model the complex correlation between skin lesions and their informative context. By controlling feature information passing through two complementary directions, a substantially rich and discriminative feature representation is achieved. Specifically, we place biDFL module on the top of a CNN network to enhance high-level parsing performance. Furthermore, we propose a multi-scale consistent decision fusion (mCDF) that is capable of selectively focusing on the informative decisions generated from multiple classification layers. By analysis of the consistency of the decision at each position, mCDF automatically adjusts the reliability of decisions and thus allows a more insightful skin lesion delineation. The comprehensive experimental results show the effectiveness of the proposed method on skin lesion segmentation, achieving state-of-the-art performance consistently on two publicly available dermoscopic image databases.

cs.CV↗

arXiv2020

Training ASR models by Generation of Contextual Information

Supervised ASR models have reached unprecedented levels of accuracy, thanks in part to ever-increasing amounts of labelled training data. However, in many applications and locales, only moderate amounts of data are available, which has led to a surge in semi- and weakly-supervised learning research. In this paper, we conduct a large-scale study evaluating the effectiveness of weakly-supervised learning for speech recognition by using loosely related contextual information as a surrogate for ground-truth labels. For weakly supervised training, we use 50k hours of public English social media videos along with their respective titles and post text to train an encoder-decoder transformer model. Our best encoder-decoder models achieve an average of 20.8% WER reduction over a 1000 hours supervised baseline, and an average of 13.4% WER reduction when using only the weakly supervised encoder for CTC fine-tuning. Our results show that our setup for weak supervision improved both the encoder acoustic representations as well as the decoder language generation abilities.

cs.CL↗

arXiv2020

Deep Convolutional Neural Networks with Spatial Regularization, Volume and Star-shape Priori for Image Segmentation

We use Deep Convolutional Neural Networks (DCNNs) for image segmentation problems. DCNNs can well extract the features from natural images. However, the classification functions in the existing network architecture of CNNs are simple and lack capabilities to handle important spatial information in a way that have been done for many well-known traditional variational models. Prior such as spatial regularity, volume prior and object shapes cannot be well handled by existing DCNNs. We propose a novel Soft Threshold Dynamics (STD) framework which can easily integrate many spatial priors of the classical variational models into the DCNNs for image segmentation. The novelty of our method is to interpret the softmax activation function as a dual variable in a variational problem, and thus many spatial priors can be imposed in the dual space. From this viewpoint, we can build a STD based framework which can enable the outputs of DCNNs to have many special priors such as spatial regularity, volume constraints and star-shape priori. The proposed method is a general mathematical framework and it can be applied to any semantic segmentation DCNNs. To show the efficiency and accuracy of our method, we applied it to the popular DeepLabV3+ image segmentation network, and the experiments results show that our method can work efficiently on data-driven image segmentation DCNNs.

cs.CV↗

arXiv2020

Instant single-pixel imaging: on-chip real-time implementation based on instant ghost imaging algorithm

Single-pixel imaging (SPI) uses a single-pixel detector to create an image of an object. SPI relies on a computer to construct an image, thus increasing both the size and cost of SPI and limiting its application. We developed instant single-pixel imaging (ISPI), an on-chip SPI system that implements real-time imaging at a rate of 25 fps. ISPI uses the instant ghost imaging algorithm we proposed which leverages signal differences for image creation. It does not require a computer, which greatly reduces its cost and size. The reconstruct time of ISPI for image creation is almost zero because little processing is required after signal detection. ISPI paves the way for the practical application of SPI.

eess.IV↗

arXiv2020

Volume Preserving Image Segmentation with Entropic Regularization Optimal Transport and Its Applications in Deep Learning

Image segmentation with a volume constraint is an important prior for many real applications. In this work, we present a novel volume preserving image segmentation algorithm, which is based on the framework of entropic regularized optimal transport theory. The classical Total Variation (TV) regularizer and volume preserving are integrated into a regularized optimal transport model, and the volume and classification constraints can be regarded as two measures preserving constraints in the optimal transport problem. By studying the dual problem, we develop a simple and efficient dual algorithm for our model. Moreover, to be different from many variational based image segmentation algorithms, the proposed algorithm can be directly unrolled to a new Volume Preserving and TV regularized softmax (VPTV-softmax) layer for semantic segmentation in the popular Deep Convolution Neural Network (DCNN). The experiment results show that our proposed model is very competitive and can improve the performance of many semantic segmentation nets such as the popular U-net.

cs.CV↗

arXiv2020

HLO: Half-kernel Laplacian Operator for Surface Smoothing

This paper presents a simple yet effective method for feature-preserving surface smoothing. Through analyzing the differential property of surfaces, we show that the conventional discrete Laplacian operator with uniform weights is not applicable to feature points at which the surface is non-differentiable and the second order derivatives do not exist. To overcome this difficulty, we propose a Half-kernel Laplacian Operator (HLO) as an alternative to the conventional Laplacian. Given a vertex v, HLO first finds all pairs of its neighboring vertices and divides each pair into two subsets (called half windows); then computes the uniform Laplacians of all such subsets and subsequently projects the computed Laplacians to the full-window uniform Laplacian to alleviate flipping and degeneration. The half window with least regularization energy is then chosen for v. We develop an iterative approach to apply HLO for surface denoising. Our method is conceptually simple and easy to use because it has a single parameter, i.e., the number of iterations for updating vertices. We show that our method can preserve features better than the popular uniform Laplacian-based denoising and it significantly alleviates the shrinkage artifact. Extensive experimental results demonstrate that HLO is better than or comparable to state-of-the-art techniques both qualitatively and quantitatively and that it is particularly good at handling meshes with high noise. We will make our source code publicly available.

cs.CG↗

arXiv2019

Joint Embedding Learning of Educational Knowledge Graphs

As an efficient model for knowledge organization, the knowledge graph has been widely adopted in several fields, e.g., biomedicine, sociology, and education. And there is a steady trend of learning embedding representations of knowledge graphs to facilitate knowledge graph construction and downstream tasks. In general, knowledge graph embedding techniques aim to learn vectorized representations which preserve the structural information of the graph. And conventional embedding learning models rely on structural relationships among entities and relations. However, in educational knowledge graphs, structural relationships are not the focus. Instead, rich literals of the graphs are more valuable. In this paper, we focus on this problem and propose a novel model for embedding learning of educational knowledge graphs. Our model considers both structural and literal information and jointly learns embedding representations. Three experimental graphs were constructed based on an educational knowledge graph which has been applied in real-world teaching. We conducted two experiments on the three graphs and other common benchmark graphs. The experimental results proved the effectiveness of our model and its superiority over other baselines when processing educational knowledge graphs.

cs.CL↗

arXiv2019

Enhanced LMMSE Estimation Capable of Selecting Parameters

In the linear minimum mean square error (LMMSE) estimation for orthogonal frequency division multiplexing (OFDM) systems, the problem about the determination of the algorithm's parameters, especially those related with channel frequency response (CFR) correlation, has not been readily solved yet. Although many approaches have been proposed to determine the statistic parameters, it is hard to choose the best one within those approaches in the design phase, since every approach has its own most suitable application conditions and the real channel condition is unpredictable. In this paper, we propose an enhance LMMSE estimation capable of selecting parameters by itself. To this end, sampled noise MSE is first proposed to evaluate the practical performance of interpolation. Based on this evaluation index, a novel parameter comparison scheme is proposed to determine the parameters which can endow LMMSE estimation best performance within a parameter set. After that, the structure of the enhanced LMMSE is illustrated, and it is applied in OFDM systems. Besides, the issues about theoretical analysis on accuracy of the parameter comparison scheme, the parameter set design and algorithm complexity are explained in detail. At last, our analyses and performance of the proposed estimation method are demonstrated by simulation experiments.

eess.SP↗

arXiv2019

D-SPIDER-SFO: A Decentralized Optimization Algorithm with Faster Convergence Rate for Nonconvex Problems

Decentralized optimization algorithms have attracted intensive interests recently, as it has a balanced communication pattern, especially when solving large-scale machine learning problems. Stochastic Path Integrated Differential Estimator Stochastic First-Order method (SPIDER-SFO) nearly achieves the algorithmic lower bound in certain regimes for nonconvex problems. However, whether we can find a decentralized algorithm which achieves a similar convergence rate to SPIDER-SFO is still unclear. To tackle this problem, we propose a decentralized variant of SPIDER-SFO, called decentralized SPIDER-SFO (D-SPIDER-SFO). We show that D-SPIDER-SFO achieves a similar gradient computation cost---that is, $\mathcal{O}(ε^{-3})$ for finding an $ε$-approximate first-order stationary point---to its centralized counterpart. To the best of our knowledge, D-SPIDER-SFO achieves the state-of-the-art performance for solving nonconvex optimization problems on decentralized networks in terms of the computational cost. Experiments on different network configurations demonstrate the efficiency of the proposed method.

cs.LG↗

arXiv2019

Extended Answer and Uncertainty Aware Neural Question Generation

In this paper, we study automatic question generation, the task of creating questions from corresponding text passages where some certain spans of the text can serve as the answers. We propose an Extended Answer-aware Network (EAN) which is trained with Word-based Coverage Mechanism (WCM) and decodes with Uncertainty-aware Beam Search (UBS). The EAN represents the target answer by its surrounding sentence with an encoder, and incorporates the information of the extended answer into paragraph representation with gated paragraph-to-answer attention to tackle the problem of the inadequate representation of the target answer. To reduce undesirable repetition, the WCM penalizes repeatedly attending to the same words at different time-steps in the training stage. The UBS aims to seek a better balance between the model confidence in copying words from an input text paragraph and the confidence in generating words from a vocabulary. We conduct experiments on the SQuAD dataset, and the results show our approach achieves significant performance improvement.

cs.CL↗

arXiv2019

Single-shot fourth-order auto-correlator

The temporal contrast is one of the most important parameters of an ultra-high intense laser pulse. Third-order auto-correlator or cross-correlator have been widely used to characterize the temporal contrast of an ultra-intense laser pulse in the past decades. Here, a novel and simple single-shot fourth-order auto-correlator to characterize the temporal contrast with higher time resolution and better pulse contrast fidelity in comparison to third-order correlators is proposed. The single-shot fourth-order autocorrelation consists of a frequency degenerate four-wave mixing process and a sum-frequency mixing process. The proof-of-principle experiments show that a dynamic range of approximately 10^11 compared with the noise level, a time resolution of approximately 160 fs, and a time window of 65 ps can be successfully obtained using the novel single-shot fourth-order auto-correlator, which is the highest dynamic range with simultaneous high time resolution for single-shot temporal contrast measurement so far. Furthermore, the temporal contrast of laser pulse from a PW laser system is successfully measured in single-shot with a dynamic range of about 2*10^10 and simultaneous a time resolution of 160 fs.

physics.optics↗

arXiv2019

Efficient Dynamic WFST Decoding for Personalized Language Models

We propose a two-layer cache mechanism to speed up dynamic WFST decoding with personalized language models. The first layer is a public cache that stores most of the static part of the graph. This is shared globally among all users. A second layer is a private cache that caches the graph that represents the personalized language model, which is only shared by the utterances from a particular user. We also propose two simple yet effective pre-initialization methods, one based on breadth-first search, and another based on a data-driven exploration of decoder states using previous utterances. Experiments with a calling speech recognition task using a personalized contact list demonstrate that the proposed public cache reduces decoding time by factor of three compared to decoding without pre-initialization. Using the private cache provides additional efficiency gains, reducing the decoding time by a factor of five.

cs.CL↗

arXiv2019

Real-Variable Characterizations of New Anisotropic Mixed-Norm Hardy Spaces

Let $\vec{p}\in(0,\infty)^n$ and $A$ be a general expansive matrix on $\mathbb{R}^n$. In this article, via the non-tangential grand maximal function, the authors first introduce the anisotropic mixed-norm Hardy spaces $H_A^{\vec{p}}(\mathbb{R}^n)$ associated with $A$ and then establish their radial or non-tangential maximal function characterizations. Moreover, the authors characterize $H_A^{\vec{p}}(\mathbb{R}^n)$, respectively, by means of atoms, finite atoms, Lusin area functions, Littlewood-Paley $g$-functions or $g_λ^\ast$-functions via first establishing an anisotropic Fefferman-Stein vector-valued inequality on the mixed-norm Lebesgue space $L^{\vec{p}}(\mathbb{R}^n)$. In addition, the authors also obtain the duality between $H_A^{\vec{p}}(\mathbb{R}^n)$ and the anisotropic mixed-norm Campanato spaces. As applications, the authors establish a criterion on the boundedness of sublinear operators from $H_A^{\vec{p}}(\mathbb{R}^n)$ into a quasi-Banach space. Applying this criterion, the authors then obtain the boundedness of anisotropic convolutional $δ$-type and non-convolutional $β$-order Calderón-Zygmund operators from $H_A^{\vec{p}}(\mathbb{R}^n)$ to itself [or to $L^{\vec{p}}(\mathbb{R}^n)$]. As a corollary, the boundedness of anisotropic convolutional $δ$-type Calderón-Zygmund operators on the mixed-norm Lebesgue space $L^{\vec{p}}(\mathbb{R}^n)$ with $\vec{p}\in(1,\infty)^n$ is also presented.

math.CA↗

arXiv2019

Nonlocal Patches based Gaussian Mixture Model for Image Inpainting

We consider the inpainting problem for noisy images. It is very challenge to suppress noise when image inpainting is processed. An image patches based nonlocal variational method is proposed to simultaneously inpainting and denoising in this paper. Our approach is developed on an assumption that the small image patches should be obeyed a distribution which can be described by a high dimension Gaussian Mixture Model. By a maximum a posteriori (MAP) estimation, we formulate a new regularization term according to the log-likelihood function of the mixture model. To optimize this regularization term efficiently, we adopt the idea of the Expectation Maximum (EM) algorithm. In which, the expectation step can give an adaptive weighting function which can be regarded as a nonlocal connections among pixels. Using this fact, we built a framework for non-local image inpainting under noise. Moreover, we mathematically prove the existence of minimizer for the proposed inpainting model. By using a spitting algorithm, the proposed model are able to realize image inpainting and denoising simultaneously. Numerical results show that the proposed method can produce impressive reconstructed results when the inpainting region is rather large.

cs.CV↗

arXiv2019

Design of reversible low-field magnetocaloric effect at room temperature in hexagonal MnMX ferromagnets

Giant magnetocaloric effect is widely achieved in hexagonal MnMX-based (M = Co or Ni, X = Si or Ge) ferromagnets at their first-order magnetostructural transition. However, the thermal hysteresis and the low sensitivity of the magnetostructural transition to the magnetic field inevitably lead to a sizeable irreversibility of the low-field magnetocaloric effect. In this work, we show an alternative way to realize a reversible low-field magnetocaloric effect in MnMX-based alloys by taking advantage of the second-order phase transition. With introducing Cu into Co in MnCoGe alloy, the martensitic transition is stabilized at high temperature, while the Curie temperature of the orthorhombic phase is reduced to room temperature. As a result, a second-order magnetic transition with negligible thermal hysteresis and a large magnetization change can be observed, enabling a large reversible magnetocaloric effect. By both calorimetric and direct measurements, a reversible adiabatic temperature change of about 1 K is obtained under a field change of 0-1 T at 304 K, which is larger than that obtained in a first-order magnetostructural transition. To get a better insight into the origin of these experimental results, first-principles calculations are carried out to characterize the chemical bonds and the magnetic exchange interaction. Our work provides a new understanding of the MnCoGe alloy and indicates a feasible route to improve the reversibility of the low-field magnetocaloric effect in the MnMX system.

cond-mat.mtrl-sci↗

arXiv2019

A Thermal Resistance Network Model for Heat Conduction of Amorphous Polymers

Thermal conductivities (TCs) of the vast majority of amorphous polymers are in a very narrow range, 0.1 $\sim$ 0.5 Wm$^{-1}$K$^{-1}$, although single polymer chains possess TC of orders-of-magnitude higher. Entanglement of polymer chains plays an important role in determining the TC of bulk polymers. We propose a thermal resistance network (TRN) model for TC in amorphous polymers taking into account the entanglement of molecular chains. Our model explains well the physical origin of universally low TC observed in amorphous polymers. The empirical formulae of pressure and temperature dependence of TC can be successfully reproduced from our model not only in solid polymers but also in polymer melts. We further quantitatively explain the anisotropic TC in oriented polymers.

cond-mat.soft↗

arXiv2019

Structured Query Construction via Knowledge Graph Embedding

In order to facilitate the accesses of general users to knowledge graphs, an increasing effort is being exerted to construct graph-structured queries of given natural language questions. At the core of the construction is to deduce the structure of the target query and determine the vertices/edges which constitute the query. Existing query construction methods rely on question understanding and conventional graph-based algorithms which lead to inefficient and degraded performances facing complex natural language questions over knowledge graphs with large scales. In this paper, we focus on this problem and propose a novel framework standing on recent knowledge graph embedding techniques. Our framework first encodes the underlying knowledge graph into a low-dimensional embedding space by leveraging generalized local knowledge graphs. Given a natural language question, the learned embedding representations of the knowledge graph are utilized to compute the query structure and assemble vertices/edges into the target query. Extensive experiments were conducted on the benchmark dataset, and the results demonstrate that our framework outperforms state-of-the-art baseline models regarding effectiveness and efficiency.

cs.AI↗

arXiv2019

Interstellar Scintillation Monitoring of the RadioAstron Blazars

The RadioAstron space radio telescope provides a unique opportunity to study the extreme brightness temperatures ($\mathrm{T_B }$) in AGNs with unprecedented long baselines of up to 28 Earth diameters. Since interstellar scintillation (ISS) may affect the visibilities observed with space VLBI (sVLBI), a complementary ground based flux density monitoring of the RadioAstron targets, which is performed near in time to the VLBI observation, could be beneficial. The combination/comparison with the sVLBI data can help to unravel the relative influence of source intrinsic and ISS induced effects, which in the end may alter the conclusions on the $\mathrm{T_B }$ measurements from sVLBI. Since 2013, a dedicated monitoring program has been ongoing to observe the ISS of RadioAstron AGN targets with a number of radio telescopes. Here we briefly introduce the program and present results from the statistical analysis of the Effelsberg monitoring data. We discuss the possible effects of ISS on $\mathrm{T_B }$ measurements for the RadioAstron target B0529+483 as a case study.

astro-ph.GA↗