arXiv subjects

Ye Tian

Publications and source records attributed to Ye Tian.

At least 235 records · Page 13Linked to original sources

arXiv2021

Imaging vibrations of locally gated, electromechanical few layer graphene resonators with a moving vacuum enclosure

Imaging the vibrations of nanomechanical resonators means measuring their flexural mode shapes from the dependence of their frequency response on in-plane position. Applied to two-dimensional resonators, this technique provides a wealth of information on the mechanical properties of atomically-thin membranes. We present a simple and robust system to image the vibrations of few layer graphene (FLG) resonators at room temperature and in vacuum with an in-plane displacement precision of $\approx0.20$ $μ$m. It consists of a sturdy vacuum enclosure mounted on a three-axis micropositioning stage and designed for free space optical measurements of vibrations. The system is equipped with ultra-flexible radio frequency waveguides to electrically actuate resonators. With it we characterize the lowest frequency mode of a FLG resonator by measuring its frequency response as a function of position on the membrane. The resonator is suspended over a nanofabricated local gate electrode acting both as a mirror and as a capacitor plate to actuate vibrations at radio frequencies. From these measurements, we estimate the ratio of thermal expansion coefficient to thermal conductivity of the membrane, and we measure the effective mass of the lowest frequency mode. We complement our study with a globally gated resonator and image its first three vibration modes. There, we find that folds in the membrane locally suppress vibrations.

cond-mat.mes-hall↗

arXiv2021

A Multilayer Correlated Topic Model

We proposed a novel multilayer correlated topic model (MCTM) to analyze how the main ideas inherit and vary between a document and its different segments, which helps understand an article's structure. The variational expectation-maximization (EM) algorithm was derived to estimate the posterior and parameters in MCTM. We introduced two potential applications of MCTM, including the paragraph-level document analysis and market basket data analysis. The effectiveness of MCTM in understanding the document structure has been verified by the great predictive performance on held-out documents and intuitive visualization. We also showed that MCTM could successfully capture customers' popular shopping patterns in the market basket analysis.

cs.IR↗

arXiv2020

AMRNet: Chips Augmentation in Aerial Images Object Detection

Object detection in aerial images is a challenging task due to the following reasons: (1) objects are small and dense relative to images; (2) the object scale varies in a wide range; (3) the number of object in different classes is imbalanced. Many current methods adopt cropping idea: splitting high resolution images into serials subregions (chips) and detecting on them. However, some problems such as scale variation, object sparsity, and class imbalance exist in the process of training network with chips. In this work, three augmentation methods are introduced to relieve these problems. Specifically, we propose a scale adaptive module, which dynamically adjusts chip size to balance object scale, narrowing scale variation in training. In addtion, we introduce mosaic to augment datasets, relieving object sparity problem. To balance catgory, we present mask resampling to paste object in chips with panoramic segmentation. Our model achieves state-of-the-art perfomance on two popular aerial image datasets of VisDrone and UAVDT. Remarkably, three methods can be independently applied to detectiors, increasing performance steady without the sacrifice of inference efficiency.

cs.CV↗

arXiv2020

DeepDyve: Dynamic Verification for Deep Neural Networks

Deep neural networks (DNNs) have become one of the enabling technologies in many safety-critical applications, e.g., autonomous driving and medical image analysis. DNN systems, however, suffer from various kinds of threats, such as adversarial example attacks and fault injection attacks. While there are many defense methods proposed against maliciously crafted inputs, solutions against faults presented in the DNN system itself (e.g., parameters and calculations) are far less explored. In this paper, we develop a novel lightweight fault-tolerant solution for DNN-based systems, namely DeepDyve, which employs pre-trained neural networks that are far simpler and smaller than the original DNN for dynamic verification. The key to enabling such lightweight checking is that the smaller neural network only needs to produce approximate results for the initial task without sacrificing fault coverage much. We develop efficient and effective architecture and task exploration techniques to achieve optimized risk/overhead trade-off in DeepDyve. Experimental results show that DeepDyve can reduce 90% of the risks at around 10% overhead.

cs.LG↗

arXiv2020

Temporal Self-Ensembling Teacher for Semi-Supervised Object Detection

This paper focuses on Semi-Supervised Object Detection (SSOD). Knowledge Distillation (KD) has been widely used for semi-supervised image classification. However, adapting these methods for SSOD has the following obstacles. (1) The teacher model serves a dual role as a teacher and a student, such that the teacher predictions on unlabeled images may be very close to those of student, which limits the upper-bound of the student. (2) The class imbalance issue in SSOD hinders an efficient knowledge transfer from teacher to student. To address these problems, we propose a novel method Temporal Self-Ensembling Teacher (TSE-T) for SSOD. Differently from previous KD based methods, we devise a temporally evolved teacher model. First, our teacher model ensembles its temporal predictions for unlabeled images under stochastic perturbations. Second, our teacher model ensembles its temporal model weights with the student model weights by an exponential moving average (EMA) which allows the teacher gradually learn from the student. These self-ensembling strategies increase data and model diversity, thus improving teacher predictions on unlabeled images. Finally, we use focal loss to formulate consistency regularization term to handle the data imbalance problem, which is a more efficient manner to utilize the useful information from unlabeled images than a simple hard-thresholding method which solely preserves confident predictions. Evaluated on the widely used VOC and COCO benchmarks, the mAP of our method has achieved 80.73% and 40.52% on the VOC2007 test set and the COCO2014 minval5k set respectively, which outperforms a strong fully-supervised detector by 2.37% and 1.49%. Furthermore, our method sets the new state-of-the-art in SSOD on VOC2007 test set which outperforms the baseline SSOD method by 1.44%. The source code of this work is publicly available at http://github.com/syangdong/tse-t.

cs.CV↗

arXiv2020

CG-SENSE revisited: Results from the first ISMRM reproducibility challenge

Purpose: The aim of this work is to shed light on the issue of reproducibility in MR image reconstruction in the context of a challenge. Participants had to recreate the results of "Advances in sensitivity encoding with arbitrary k-space trajectories" by Pruessmann et al. Methods: The task of the challenge was to reconstruct radially acquired multi-coil k-space data (brain/heart) following the method in the original paper, reproducing its key figures. Results were compared to consolidated reference implementations created after the challenge, accounting for the two most common programming languages used in the submissions (Matlab/Python). Results: Visually, differences between submissions were small. Pixel-wise differences originated from image orientation, assumed field-of-view or resolution. The reference implementations were in good agreement, both visually and in terms of image similarity metrics. Discussion and Conclusion: While the description level of the published algorithm enabled participants to reproduce CG-SENSE in general, details of the implementation varied, e.g., density compensation or Tikhonov regularization. Implicit assumptions about the data lead to further differences, emphasizing the importance of sufficient meta-data accompanying open data sets. Defining reproducibility quantitatively turned out to be non-trivial for this image reconstruction challenge, in the absence of ground-truth results. Typical similarity measures like NMSE of SSIM were misled by image intensity scaling and outlier pixels. Thus, to facilitate reproducibility, researchers are encouraged to publish code and data alongside the original paper. Future methodological papers on MR image reconstruction might benefit from the consolidated reference implementations of CG-SENSE presented here, as a benchmark for methods comparison.

eess.IV↗

arXiv2020

Resisting Large Data Variations via Introspective Transformation Network

Training deep networks that generalize to a wide range of variations in test data is essential to building accurate and robust image classifiers. One standard strategy is to apply data augmentation to synthetically enlarge the training set. However, data augmentation is essentially a brute-force method which generates uniform samples from some pre-defined set of transformations. In this paper, we propose a principled approach to train networks with significantly improved resistance to large variations between training and testing data. This is achieved by embedding a learnable transformation module into the introspective network, which is a convolutional neural network (CNN) classifier empowered with generative capabilities. Our approach alternates between synthesizing pseudo-negative samples and transformed positive examples based on the current model, and optimizing model predictions on these synthesized samples. Experimental results verify that our approach significantly improves the ability of deep networks to resist large variations between training and testing data and achieves classification accuracy improvements on several benchmark datasets, including MNIST, affNIST, SVHN, CIFAR-10 and miniImageNet.

cs.CV↗

arXiv2020

Learning a Multi-Domain Curriculum for Neural Machine Translation

Most data selection research in machine translation focuses on improving a single domain. We perform data selection for multiple domains at once. This is achieved by carefully introducing instance-level domain-relevance features and automatically constructing a training curriculum to gradually concentrate on multi-domain relevant and noise-reduced data batches. Both the choice of features and the use of curriculum are crucial for balancing and improving all domains, including out-of-domain. In large-scale experiments, the multi-domain curriculum simultaneously reaches or outperforms the individual performance and brings solid gains over no-curriculum training.

cs.CL↗

arXiv2020

Downstream Model Design of Pre-trained Language Model for Relation Extraction Task

Supervised relation extraction methods based on deep neural network play an important role in the recent information extraction field. However, at present, their performance still fails to reach a good level due to the existence of complicated relations. On the other hand, recently proposed pre-trained language models (PLMs) have achieved great success in multiple tasks of natural language processing through fine-tuning when combined with the model of downstream tasks. However, original standard tasks of PLM do not include the relation extraction task yet. We believe that PLMs can also be used to solve the relation extraction problem, but it is necessary to establish a specially designed downstream task model or even loss function for dealing with complicated relations. In this paper, a new network architecture with a special loss function is designed to serve as a downstream model of PLMs for supervised relation extraction. Experiments have shown that our method significantly exceeded the current optimal baseline models across multiple public datasets of relation extraction.

cs.CL↗

arXiv2020

Polar state of 0.67BiFeO3-0.33BaTiO3 near the morphotropic phase boundary

The symmetric studies on the structure-property relationship of the unpoled and poled states of 0.67BiFeO3-0.33BaTiO3 (0.67BF-0.33BT) were conducted to understand the origin of the morphotropic phase boundary (MPB) in BF-BT. A typical relaxor-type dielectric anomaly was observed (Tf, ~627 K). The remnant polarization (Pr) and maximum value of electro-strain (Sm) increase clearly during heating (Pr, ~40 uC/cm2; Sm, 0.191 % under 40 kV/cm at 453 K). The first-cycle electro-strain loops indicate the difference in the polar state between 0.67BF-0.33BT and 0.94BiNaTiO3-0.06BaTiO3. Both the unpoled and poled samples have the similar frequency dispersion behaviors. Even in the poled samples, the transition between the ergodic relaxor state and ferroelectric-like state does not involve a clear dielectric anomaly. Analyses based on the Rietveld refinement of XRD patterns, bright-field images and selected-area electron diffractions (SAED) demonstrated that the formation of the long-range ferroelectric domains was difficult under the poling field.

cond-mat.mtrl-sci↗

arXiv2020

Distributed Algorithms for Composite Optimization: Unified Framework and Convergence Analysis

We study distributed composite optimization over networks: agents minimize a sum of smooth (strongly) convex functions, the agents' sum-utility, plus a nonsmooth (extended-valued) convex one. We propose a general unified algorithmic framework for such a class of problems and provide a unified convergence analysis leveraging the theory of operator splitting. Distinguishing features of our scheme are: (i) When the agents' functions are strongly convex, the algorithm converges at a linear rate, whose dependence on the agents' functions and network topology is decoupled, matching the typical rates of centralized optimization; the rate expression improves on existing results; (ii) When the objective function is convex (but not strongly convex), similar separation as in (i) is established for the coefficient of the proved sublinear rate; (iii) The algorithm can adjust the ratio between the number of communications and computations to achieve a rate (in terms of computations) independent on the network connectivity; and (iv) A by-product of our analysis is a tuning recommendation for several existing (non accelerated) distributed algorithms yielding the fastest provably (worst-case) convergence rate. This is the first time that a general distributed algorithmic framework applicable to composite optimization enjoys all such properties.

math.OC↗

arXiv2020

Accelerated Primal-Dual Algorithms for Distributed Smooth Convex Optimization over Networks

This paper proposes a novel family of primal-dual-based distributed algorithms for smooth, convex, multi-agent optimization over networks that uses only gradient information and gossip communications. The algorithms can also employ acceleration on the computation and communications. We provide a unified analysis of their convergence rate, measured in terms of the Bregman distance associated to the saddle point reformation of the distributed optimization problem. When acceleration is employed, the rate is shown to be optimal, in the sense that it matches (under the proposed metric) existing complexity lower bounds of distributed algorithms applicable to such a class of problem and using only gradient information and gossip communications. Preliminary numerical results on distributed least-square regression problems show that the proposed algorithm compares favorably on existing distributed schemes.

math.OC↗

arXiv2020

A Tamm Plasmon-Porous GaN Distributed Bragg Reflector Cavity

This paper reports on design, measurement and optimisation of a Tamm plasmon metal-DBR cavity for use in the green part of the visible spectrum. It uses an optimised silver layer thickness and a porous DBR created using a novel electro-chemical etching technique. This device has applications in low cost lasers, photodetectors and photoconductive switches for the visible wavelength range.

physics.optics↗

arXiv2020

Asynchronous Decentralized Successive Convex Approximation

We study decentralized asynchronous multiagent optimization over networks, modeled as static (possibly directed) graphs. The optimization problem consists of minimizing a (possibly nonconvex) smooth function--the sum of the agents' local costs--plus a convex (possibly nonsmooth) regularizer, subject to convex constraints. Agents can perform their local computations as well as communicate with their immediate neighbors at any time, without any form of coordination or centralized scheduling; furthermore, when solving their local subproblems, they can use outdated information from their neighbors. We propose the first distributed asynchronous algorithm, termed ASY-DSCA, that converges at an R-linear rate to the optimal solution of convex problems whose objective function satisfies a general error bound condition; this condition is weaker than the more frequently used strong convexity, and it is satisfied by several empirical risk functions that are not strongly convex; examples include LASSO and logistic regression problems. When the objective function is nonconvex, ASY-DSCA converges to a stationary solution of the problem at a sublinear rate.

math.OC↗

arXiv2019

Horizontal non-vanishing of Heegner points and toric periods

Let $F/\mathbb{Q}$ be a totally real field and $A$ a modular $\GL_2$-type abelian variety over $F$. Let $K/F$ be a CM quadratic extension. Let $χ$ be a class group character over $K$ such that the Rankin-Selberg convolution $L(s,A,χ)$ is self-dual with root number $-1$. We show that the number of class group characters $χ$ with bounded ramification such that $L'(1, A, χ) \neq 0$ increases with the absolute value of the discriminant of $K$. We also consider a rather general rank zero situation. Let $π$ be a cuspidal cohomological automorphic representation over $\GL_{2}(\BA_{F})$. Let $χ$ be a Hecke character over $K$ such that the Rankin-Selberg convolution $L(s,π,χ)$ is self-dual with root number $1$. We show that the number of Hecke characters $χ$ with fixed $\infty$-type and bounded ramification such that $L(1/2, π, χ) \neq 0$ increases with the absolute value of the discriminant of $K$. The Gross-Zagier formula and the Waldspurger formula relate the question to horizontal non-vanishing of Heegner points and toric periods, respectively. For both situations, the strategy is geometric relying on the Zariski density of CM points on self-products of a quaternionic Shimura variety. The recent result \cite{Ts, YZ, AGHP} on the André-Oort conjecture is accordingly fundamental to the approach.

math.NT↗

arXiv2019

A Unified Contraction Analysis of a Class of Distributed Algorithms for Composite Optimization

We study distributed composite optimization over networks: agents minimize the sum of a smooth (strongly) convex function, the agents' sum-utility, plus a non-smooth (extended-valued) convex one. We propose a general algorithmic framework for such a class of problems and provide a unified convergence analysis leveraging the theory of operator splitting. Our results unify several approaches proposed in the literature of distributed optimization for special instances of our formulation. Distinguishing features of our scheme are: (i) when the agents' functions are strongly convex, the algorithm converges at a linear rate, whose dependencies on the agents' functions and the network topology are decoupled, matching the typical rates of centralized optimization; (ii) the step-size does not depend on the network parameters but only on the optimization ones; and (iii) the algorithm can adjust the ratio between the number of communications and computations to achieve the same rate of the centralized proximal gradient scheme (in terms of computations). This is the first time that a distributed algorithm applicable to composite optimization enjoys such properties.

math.OC↗

arXiv2019

Achieving Linear Convergence in Distributed Asynchronous Multi-agent Optimization

This papers studies multi-agent (convex and \emph{nonconvex}) optimization over static digraphs. We propose a general distributed \emph{asynchronous} algorithmic framework whereby i) agents can update their local variables as well as communicate with their neighbors at any time, without any form of coordination; and ii) they can perform their local computations using (possibly) delayed, out-of-sync information from the other agents. Delays need not be known to the agent or obey any specific profile, and can also be time-varying (but bounded). The algorithm builds on a tracking mechanism that is robust against asynchrony (in the above sense), whose goal is to estimate locally the average of agents' gradients. When applied to strongly convex functions, we prove that it converges at an R-linear (geometric) rate as long as the step-size is {sufficiently small}. A sublinear convergence rate is proved, when nonconvex problems and/or diminishing, {\it uncoordinated} step-sizes are considered. To the best of our knowledge, this is the first distributed algorithm with provable geometric convergence rate in such a general asynchronous setting. Preliminary numerical results demonstrate the efficacy of the proposed algorithm and validate our theoretical findings.

math.OC↗

arXiv2019

Computer-aided Detection of Squamous Carcinoma of the Cervix in Whole Slide Images

Goal: Squamous cell carcinoma of cervix is one of the most prevalent cancer worldwide in females. Traditionally, the most indispensable diagnosis of cervix squamous carcinoma is histopathological assessment which is achieved under microscope by pathologist. However, human evaluation of pathology slide is highly depending on the experience of pathologist, thus big inter- and intra-observer variability exists. Digital pathology, in combination with deep learning provides an opportunity to improve the objectivity and efficiency of histopathologic slide analysis. Methods: In this study, we obtained 800 haematoxylin and eosin stained slides from 300 patients suffered from cervix squamous carcinoma. Based on information from morphological heterogeneity in the tumor and its adjacent area, we established deep learning models using popular convolution neural network architectures (inception-v3, InceptionResnet-v2 and Resnet50). Then random forest was introduced to feature extractions and slide-based classification. Results: The overall performance of our proposed models on slide-based tumor discrimination were outstanding with an AUC scores > 0.94. While, location identifications of lesions in whole slide images were mediocre (FROC scores > 0.52) duo to the extreme complexity of tumor tissues. Conclusion: For the first time, our analysis workflow highlighted a quantitative visual-based slide analysis of cervix squamous carcinoma. Significance: This study demonstrates a pathway to assist pathologist and accelerate the diagnosis of patients by utilizing new computational approaches.

cs.CV↗