arXiv subjects

Kun Zhao

Publications and source records attributed to Kun Zhao.

At least 91 records · Page 5Linked to original sources

arXiv2020

PrognoseNet: A Generative Probabilistic Framework for Multimodal Position Prediction given Context Information

The ability to predict multiple possible future positions of the ego-vehicle given the surrounding context while also estimating their probabilities is key to safe autonomous driving. Most of the current state-of-the-art Deep Learning approaches are trained on trajectory data to achieve this task. However trajectory data captured by sensor systems is highly imbalanced, since by far most of the trajectories follow straight lines with an approximately constant velocity. This poses a huge challenge for the task of predicting future positions, which is inherently a regression problem. Current state-of-the-art approaches alleviate this problem only by major preprocessing of the training data, e.g. resampling, clustering into anchors etc. In this paper we propose an approach which reformulates the prediction problem as a classification task, allowing for powerful tools, e.g. focal loss, to combat the imbalance. To this end we design a generative probabilistic model consisting of a deep neural network with a Mixture of Gaussian head. A smart choice of the latent variable allows for the reformulation of the log-likelihood function as a combination of a classification problem and a much simplified regression problem. The output of our model is an estimate of the probability density function of future positions, hence allowing for prediction of multiple possible positions while also estimating their probabilities. The proposed approach can easily incorporate context information and does not require any preprocessing of the data.

cs.CV↗

arXiv2020

Large Time Behavior and Diffusion Limit for a System of Balance Laws From Chemotaxis in Multi-dimensions

We consider the Cauchy problem for a system of balance laws derived from a chemotaxis model with singular sensitivity in multiple space dimensions. Utilizing energy methods, we first prove the global well-posedness of classical solutions to the Cauchy problem when only the energy of the first order spatial derivatives of the initial data is sufficiently small, and the solutions are shown to converge to the prescribed constant equilibrium states as time goes to infinity. Then we prove that the solutions of the fully dissipative model converge to those of the corresponding partially dissipative model when the chemical diffusion coefficient tends to zero.

math.AP↗

arXiv2020

The existence of optimal control for continuous-time Markov decision processes in random environments

In this work, we investigate the optimal control problem for continuous-time Markov decision processes with the random impact of the environment. We provide conditions to show the existence of optimal controls under finite-horizon criteria. Under appropriate conditions, the value function is continuous and satisfies the dynamic programming principle. These results are established by introducing some restriction on the regularity of the optimal controls and by developing a new compactification method for continuous-time Markov decision processes, which is originally used to solve the optimal control problem for jump-diffusion processes.

math.OC↗

arXiv2020

Learning to Estimate Driver Drowsiness from Car Acceleration Sensors using Weakly Labeled Data

This paper addresses the learning task of estimating driver drowsiness from the signals of car acceleration sensors. Since even drivers themselves cannot perceive their own drowsiness in a timely manner unless they use burdensome invasive sensors, obtaining labeled training data for each timestamp is not a realistic goal. To deal with this difficulty, we formulate the task as a weakly supervised learning. We only need to add labels for each complete trip, not for every timestamp independently. By assuming that some aspects of driver drowsiness increase over time due to tiredness, we formulate an algorithm that can learn from such weakly labeled data. We derive a scalable stochastic optimization method as a way of implementing the algorithm. Numerical experiments on real driving datasets demonstrate the advantages of our algorithm against baseline methods.

cs.LG↗

arXiv2020

SOS: Selective Objective Switch for Rapid Immunofluorescence Whole Slide Image Classification

The difficulty of processing gigapixel whole slide images (WSIs) in clinical microscopy has been a long-standing barrier to implementing computer aided diagnostic systems. Since modern computing resources are unable to perform computations at this extremely large scale, current state of the art methods utilize patch-based processing to preserve the resolution of WSIs. However, these methods are often resource intensive and make significant compromises on processing time. In this paper, we demonstrate that conventional patch-based processing is redundant for certain WSI classification tasks where high resolution is only required in a minority of cases. This reflects what is observed in clinical practice; where a pathologist may screen slides using a low power objective and only switch to a high power in cases where they are uncertain about their findings. To eliminate these redundancies, we propose a method for the selective use of high resolution processing based on the confidence of predictions on downscaled WSIs --- we call this the Selective Objective Switch (SOS). Our method is validated on a novel dataset of 684 Liver-Kidney-Stomach immunofluorescence WSIs routinely used in the investigation of autoimmune liver disease. By limiting high resolution processing to cases which cannot be classified confidently at low resolution, we maintain the accuracy of patch-level analysis whilst reducing the inference time by a factor of 7.74.

cs.CV↗

arXiv2020

Inorganic photovoltaic cells based on BiFeO3: spontaneous polarization, lattice matching, light polarization and their relationship to photovoltaic performance

Inorganic ferroelectric perovskite oxides are more stable than hybrid perovskites. However, their solar energy harvest efficiency is not so good. Here, by constructing a series of BiFeO3 based devices (solar cells), we investigated three factors that influence the photovoltaic performance, including spontaneous polarization, terminated ions species in the interface between BiFeO3 and the electrode, and polarized light irradiation. This work was carried out in the framework of density functional theory combined with non-equilibrium Green's function theory under built in electric field or finite bias. The results showed that 1. the photocurrent is larger only under a suitable electronic band gap rather than larger spontaneous polarization; 2. the photocurrent reaches the largest in Bi ions terminated interface than in the case of Fe ion or O ion with SrTiO3 electrode; 3. the photocurrent could be largely enhanced if the polarized direction of the monochromatic light is perpendicular to the spontaneous polarization direction. The results would deepen the understanding of some experimental results of BiFeO3 based solar cells.

cond-mat.mtrl-sci↗

arXiv2019

Dynamics in two-dimensional glassy systems of crowded Penrose kites

We investigate the translational and rotational relaxation dynamics of a crowded two-dimensional system of monodisperse Penrose kites, in which crystallization, quasi-crystallization, and nematic ordering are suppressed, from low to high area fractions along the metastable ergodic fluid branch. First, we demonstrate a decoupling between both the translational and the rotational diffusion coefficients and the relaxation time: the diffusivities are not inversely proportional to the relaxation time, neither in the low-density normal liquid regime nor in the high-density supercooled regime. Our simulations reveal that this inverse proportionality breaks in the normal liquid regime due to the Mermin-Wagner long-wavelength fluctuations and in the supercooled regime due to the dynamical heterogeneities. We then show that dynamical heterogeneities are mainly spatial for translational degrees of freedom and temporal for rotational ones, that there is no correlation between the particles with the largest translational and rotational displacements, and that different dynamical length scales characterize the translational and the rotational motion. Hence, despite the translational and the rotational glass-transition densities coincide, according to a mode-coupling fit, translations and rotations appear to decorrelate via different dynamical processes.

cond-mat.soft↗

arXiv2019

To What Extent Does Downsampling, Compression, and Data Scarcity Impact Renal Image Analysis?

The condition of the Glomeruli, or filter sacks, in renal Direct Immunofluorescence (DIF) specimens is a critical indicator for diagnosing kidney diseases. A digital pathology system which digitizes a glass histology slide into a Whole Slide Image (WSI) and then automatically detects and zooms in on the glomeruli with a higher magnification objective will be extremely helpful for pathologists. In this paper, using glomerulus detection as the study case, we provide analysis and observations on several important issues to help with the development of Computer Aided Diagnostic (CAD) systems to process WSIs. Large image resolution, large file size, and data scarcity are always challenging to deal with. To this end, we first examine image downsampling rates in terms of their effect on detection accuracy. Second, we examine the impact of image compression. Third, we examine the relationship between the size of the training set and detection accuracy. To understand the above issues, experiments are performed on the state-of-the-art detectors: Faster R-CNN, R-FCN, Mask R-CNN and SSD. Critical findings are observed: (1) The best balance between detection accuracy, detection speed and file size is achieved at 8 times downsampling captured with a $40\times$ objective; (2) compression which reduces the file size dramatically, does not necessarily have an adverse effect on overall accuracy; (3) reducing the amount of training data to some extents causes a drop in precision but has a negligible impact on the recall; (4) in most cases, Faster R-CNN achieves the best accuracy in the glomerulus detection task. We show that the image file size of $40\times$ WSI images can be reduced by a factor of over 6000 with negligible loss of glomerulus detection accuracy.

cs.CV↗

arXiv2019

Deep inspection: an electrical distribution pole parts study via deep neural networks

Electrical distribution poles are important assets in electricity supply. These poles need to be maintained in good condition to ensure they protect community safety, maintain reliability of supply, and meet legislative obligations. However, maintaining such a large volumes of assets is an expensive and challenging task. To address this, recent approaches utilise imagery data captured from helicopter and/or drone inspections. Whilst reducing the cost for manual inspection, manual analysis on each image is still required. As such, several image-based automated inspection systems have been proposed. In this paper, we target two major challenges: tiny object detection and extremely imbalanced datasets, which currently hinder the wide deployment of the automatic inspection. We propose a novel two-stage zoom-in detection method to gradually focus on the object of interest. To address the imbalanced dataset problem, we propose the resampling as well as reweighting schemes to iteratively adapt the model to the large intra-class variation of major class and balance the contributions to the loss from each class. Finally, we integrate these components together and devise a novel automatic inspection framework. Extensive experiments demonstrate that our proposed approaches are effective and can boost the performance compared to the baseline methods.

cs.CV↗

arXiv2019

Visual analytics for team-based invasion sports with significant events and Markov reward process

In team-based invasion sports such as soccer and basketball, analytics is important for teams to understand their performance and for audiences to understand matches better. The present work focuses on performing visual analytics to evaluate the value of any kind of event occurring in a sports match with a continuous parameter space. Here, the continuous parameter space involves the time, location, score, and other parameters. Because the spatiotemporal data used in such analytics is a low-level representation and has a very large size, however, traditional analytics may need to discretize the continuous parameter space (e.g., subdivide the playing area) or use a local feature to limit the analysis to specific events (e.g., only shots). These approaches make evaluation impossible for any kind of event with a continuous parameter space. To solve this problem, we consider a whole match as a Markov chain of significant events, so that event values can be estimated with a continuous parameter space by solving the Markov chain with a machine learning model. The significant events are first extracted by considering the time-varying distribution of players to represent the whole match. Then, the extracted events are redefined as different states with the continuous parameter space and built as a Markov chain so that a Markov reward process can be applied. Finally, the Markov reward process is solved by a customized fitted-value iteration algorithm so that the event values with the continuous parameter space can be predicted by a regression model. As a result, the event values can be visually inspected over the whole playing field under arbitrary given conditions. Experimental results with real soccer data show the effectiveness of the proposed system.

cs.AI↗

arXiv2019

Deep Instance-Level Hard Negative Mining Model for Histopathology Images

Histopathology image analysis can be considered as a Multiple instance learning (MIL) problem, where the whole slide histopathology image (WSI) is regarded as a bag of instances (i.e, patches) and the task is to predict a single class label to the WSI. However, in many real-life applications such as computational pathology, discovering the key instances that trigger the bag label is of great interest because it provides reasons for the decision made by the system. In this paper, we propose a deep convolutional neural network (CNN) model that addresses the primary task of a bag classification on a WSI and also learns to identify the response of each instance to provide interpretable results to the final prediction. We incorporate the attention mechanism into the proposed model to operate the transformation of instances and learn attention weights to allow us to find key patches. To perform a balanced training, we introduce adaptive weighing in each training bag to explicitly adjust the weight distribution in order to concentrate more on the contribution of hard samples. Based on the learned attention weights, we further develop a solution to boost the classification performance by generating the bags with hard negative instances. We conduct extensive experiments on colon and breast cancer histopathology data and show that our framework achieves state-of-the-art performance.

cs.CV↗

arXiv2019

CORAL8: Concurrent Object Regression for Area Localization in Medical Image Panels

This work tackles the problem of generating a medical report for multi-image panels. We apply our solution to the Renal Direct Immunofluorescence (RDIF) assay which requires a pathologist to generate a report based on observations across the eight different WSI in concert with existing clinical features. To this end, we propose a novel attention-based multi-modal generative recurrent neural network (RNN) architecture capable of dynamically sampling image data concurrently across the RDIF panel. The proposed methodology incorporates text from the clinical notes of the requesting physician to regulate the output of the network to align with the overall clinical context. In addition, we found the importance of regularizing the attention weights for word generation processes. This is because the system can ignore the attention mechanism by assigning equal weights for all members. Thus, we propose two regularizations which force the system to utilize the attention mechanism. Experiments on our novel collection of RDIF WSIs provided by a large clinical laboratory demonstrate that our framework offers significant improvements over existing methods.

cs.CV↗

arXiv2019

Long-wavelength fluctuations and anomalous dynamics in two-dimensional liquids

Long-wavelength Mermin-Wagner fluctuations prevent the existence of translational long-range order, in two-dimensional systems at finite temperature. Their dynamical signature, which is the divergence of the vibrational amplitude with the system size, also affects disordered solids and washes out the transient solid-like response generally exhibited by liquids cooled below their melting temperature. Through a combined numerical and experimental investigation, here we show that long-wavelength fluctuations are also relevant at high temperature, where the liquid dynamics does not reveal a transient solid-like response. In this regime, they induce an unusual but ubiquitous decoupling between long-time diffusion coefficient $D$ and structural relaxation time $τ$, where $D\propto τ^{-κ}$, with $κ> 1$. Long-wavelength fluctuations have a negligible influence on the relaxation dynamics only at extremely high temperatures, in molecular liquids, or extremely low densities, in colloidal systems.

cond-mat.soft↗

arXiv2019

Convex Class Model on Symmetric Positive Definite Manifolds

The effectiveness of Symmetric Positive Definite (SPD) manifold features has been proven in various computer vision tasks. However, due to the non-Euclidean geometry of these features, existing Euclidean machineries cannot be directly used. In this paper, we tackle the classification tasks with limited training data on SPD manifolds. Our proposed framework, named Manifold Convex Class Model, represents each class on SPD manifolds using a convex model, and classification can be performed by computing distances to the convex models. We provide three methods based on different metrics to address the optimization problem of the smallest distance of a point to the convex model on SPD manifold. The efficacy of our proposed framework is demonstrated both on synthetic data and several computer vision tasks including object recognition, texture classification, person re-identification and traffic scene classification.

cs.CV↗

arXiv2019

Disorder induced multifractal superconductivity in monolayer niobium dichalcogenides

The interplay between disorder and superconductivity is a subtle and fascinating phenomenon in quantum many body physics. The conventional superconductors are insensitive to dilute nonmagnetic impurities, known as the Anderson's theorem. Destruction of superconductivity and even superconductor-insulator transitions occur in the regime of strong disorder. Hence disorder-enhanced superconductivity is rare and has only been observed in some alloys or granular states. Because of the entanglement of various effects, the mechanism of enhancement is still under debate. Here we report well-controlled disorder effect in the recently discovered monolayer NbSe$_2$ superconductor. The superconducting transition temperatures of NbSe$_2$ monolayers are substantially increased by disorder. Realistic theoretical modeling shows that the unusual enhancement possibly arises from the multifractality of electron wave functions. This work provides the first experimental evidence of the multifractal superconducting state.

cond-mat.supr-con↗

arXiv2019

AliGraph: A Comprehensive Graph Neural Network Platform

An increasing number of machine learning tasks require dealing with large graph datasets, which capture rich and complex relationship among potentially billions of elements. Graph Neural Network (GNN) becomes an effective way to address the graph learning problem by converting the graph data into a low dimensional space while keeping both the structural and property information to the maximum extent and constructing a neural network for training and referencing. However, it is challenging to provide an efficient graph storage and computation capabilities to facilitate GNN training and enable development of new GNN algorithms. In this paper, we present a comprehensive graph neural network system, namely AliGraph, which consists of distributed graph storage, optimized sampling operators and runtime to efficiently support not only existing popular GNNs but also a series of in-house developed ones for different scenarios. The system is currently deployed at Alibaba to support a variety of business scenarios, including product recommendation and personalized search at Alibaba's E-Commerce platform. By conducting extensive experiments on a real-world dataset with 492.90 million vertices, 6.82 billion edges and rich attributes, AliGraph performs an order of magnitude faster in terms of graph building (5 minutes vs hours reported from the state-of-the-art PowerGraph platform). At training, AliGraph runs 40%-50% faster with the novel caching strategy and demonstrates around 12 times speed up with the improved runtime. In addition, our in-house developed GNN models all showcase their statistically significant superiorities in terms of both effectiveness and efficiency (e.g., 4.12%-17.19% lift by F1 scores).

cs.DC↗

arXiv2018

SlideNet: Fast and Accurate Slide Quality Assessment Based on Deep Neural Networks

This work tackles the automatic fine-grained slide quality assessment problem for digitized direct smears test using the Gram staining protocol. Automatic quality assessment can provide useful information for the pathologists and the whole digital pathology workflow. For instance, if the system found a slide to have a low staining quality, it could send a request to the automatic slide preparation system to remake the slide. If the system detects severe damage in the slides, it could notify the experts that manual microscope reading may be required. In order to address the quality assessment problem, we propose a deep neural network based framework to automatically assess the slide quality in a semantic way. Specifically, the first step of our framework is to perform dense fine-grained region classification on the whole slide and calculate the region distribution histogram. Next, our framework will generate assessments of the slide quality from various perspectives: staining quality, information density, damage level and which regions are more valuable for subsequent high-magnification analysis. To make the information more accessible, we present our results in the form of a heat map and text summaries. Additionally, in order to stimulate research in this direction, we propose a novel dataset for slide quality assessment. Experiments show that the proposed framework outperforms recent related works.

cs.CV↗

arXiv2017

Lung Nodule Classification by the Combination of Fusion Classifier and Cascaded Convolutional Neural Networks

Lung nodule classification is a class imbalanced problem, as nodules are found with much lower frequency than non-nodules. In the class imbalanced problem, conventional classifiers tend to be overwhelmed by the majority class and ignore the minority class. We showed that cascaded convolutional neural networks can classify the nodule candidates precisely for a class imbalanced nodule candidate data set in our previous study. In this paper, we propose Fusion classifier in conjunction with the cascaded convolutional neural network models. To fuse the models, nodule probabilities are calculated by using the convolutional neural network models at first. Then, Fusion classifier is trained and tested by the nodule probabilities. The proposed method achieved the sensitivity of 94.4% and 95.9% at 4 and 8 false positives per scan in Free Receiver Operating Characteristics (FROC) curve analysis, respectively.

cs.CV↗