arXiv subjects

Ye Yuan

Publications and source records attributed to Ye Yuan.

At least 271 records · Page 15Linked to original sources

arXiv2020

Causal inference using deep neural networks

Causal inference from observation data is a core problem in many scientific fields. Here we present a general supervised deep learning framework that infers causal interactions by transforming the input vectors to an image-like representation for every pair of inputs. Given a training dataset we first construct a normalized empirical probability density distribution (NEPDF) matrix. We then train a convolutional neural network (CNN) on NEPDFs for causality predictions. We tested the method on several different simulated and real world data and compared it to prior methods for causal inference. As we show, the method is general, can efficiently handle very large datasets and improves upon prior methods.

cs.LG↗

arXiv2020

Automated data extraction of bar chart raster images

Objective: To develop software utilizing optical character recognition toward the automatic extraction of data from bar charts for meta-analysis. Methods: We utilized a multistep data extraction approach that included figure extraction, text detection, and image disassembly. PubMed Central papers that were processed in this manner included clinical trials regarding macular degeneration, a disease causing blindness with a heavy disease burden and many clinical trials. Bar chart characteristics were extracted in both an automated and manual fashion. These two approaches were then compared for accuracy. These characteristics were then compared using a Bland-Altman analysis. Results: Based on Bland-Altman analysis, 91.8% of data points were within the limits of agreement. By comparing our automated data extraction with manual data extraction, automated data extraction yielded the following accuracies: X-axis labels 79.5%, Y-tick values 88.6%, Y-axis label 88.6%, Bar value <5% error 88.0%. Discussion: Based on our analysis, we achieved an agreement between automated data extraction and manual data extraction. A major source of error was the incorrect delineation of 7s as 2s by optical character recognition library. We also would benefit from adding redundancy checks in the form of a deep neural network to boost our bar detection accuracy. Further refinements to this method are justified to extract tabulated and line graph data to facilitate automated data gathering for meta-analysis.

cs.IR↗

arXiv2020

Residual Force Control for Agile Human Behavior Imitation and Extended Motion Synthesis

Reinforcement learning has shown great promise for synthesizing realistic human behaviors by learning humanoid control policies from motion capture data. However, it is still very challenging to reproduce sophisticated human skills like ballet dance, or to stably imitate long-term human behaviors with complex transitions. The main difficulty lies in the dynamics mismatch between the humanoid model and real humans. That is, motions of real humans may not be physically possible for the humanoid model. To overcome the dynamics mismatch, we propose a novel approach, residual force control (RFC), that augments a humanoid control policy by adding external residual forces into the action space. During training, the RFC-based policy learns to apply residual forces to the humanoid to compensate for the dynamics mismatch and better imitate the reference motion. Experiments on a wide range of dynamic motions demonstrate that our approach outperforms state-of-the-art methods in terms of convergence speed and the quality of learned motions. Notably, we showcase a physics-based virtual character empowered by RFC that can perform highly agile ballet dance moves such as pirouette, arabesque and jeté. Furthermore, we propose a dual-policy control framework, where a kinematic policy and an RFC-based policy work in tandem to synthesize multi-modal infinite-horizon human motions without any task guidance or user input. Our approach is the first humanoid control method that successfully learns from a large-scale human motion dataset (Human3.6M) and generates diverse long-term motions. Code and videos are available at https://www.ye-yuan.com/rfc.

cs.RO↗

arXiv2020

PCAL: A Privacy-preserving Intelligent Credit Risk Modeling Framework Based on Adversarial Learning

Credit risk modeling has permeated our everyday life. Most banks and financial companies use this technique to model their clients' trustworthiness. While machine learning is increasingly used in this field, the resulting large-scale collection of user private information has reinvigorated the privacy debate, considering dozens of data breach incidents every year caused by unauthorized hackers, and (potentially even more) information misuse/abuse by authorized parties. To address those critical concerns, this paper proposes a framework of Privacy-preserving Credit risk modeling based on Adversarial Learning (PCAL). PCAL aims to mask the private information inside the original dataset, while maintaining the important utility information for the target prediction task performance, by (iteratively) weighing between a privacy-risk loss and a utility-oriented loss. PCAL is compared against off-the-shelf options in terms of both utility and privacy protection. Results indicate that PCAL can learn an effective, privacy-free representation from user data, providing a solid foundation towards privacy-preserving machine learning for credit risk analysis.

cs.CR↗

arXiv2020

Precise phase control of large-scale inorganic perovskites via vapor-phase anion-exchange strategy

Anion exchange offers great flexibility and high precision in phase control, compositional engineering and optoelectronic property tuning. Different from previous successful anion exchange process in liquid solution, herein, we develop a vapor-phase anion-exchange strategy to realize the precise phase and bandgap control of large-scale inorganic perovskites by using gas injection cycle, produing some perovskites such as CsPbCl3 which has never been reported in thin film morphology. Ab-initio calculations also provide the insightful mechanism to understand the impact of anion exchange on tuning the electronic properties and optimizing the structural stability. Furthermore, because of precise control of specific atomic concentrations, intriguing tunable photoluminsecence is observed and photodetectors with tunable photoresponse edge from green to ultraviolet light can be realized accurately with an ultrahigh spectral resolution of 1 nm. Therefore, we offer a new, universal vapor-phase anion exchange method for inorganic perovskite with fine-tunable optoelectronic properties.

physics.app-ph↗

arXiv2020

Critical behavior of the insulator-to-metal transition in Te-hyperdoped Si

Hyperdoping Si with chalcogens is a topic of great interest due to the strong sub-bandgap absorption exhibited by the resulting material, which can be exploited to develop broadband room-temperature infrared photodetectors using fully Si-compatible technology. Here, we report on the critical behavior of the impurity-driven insulator-to-metal transition in Te-hyperdoped Si layers fabricated via ion implantation followed by nanosecond pulsed-laser melting. Electrical transport measurements reveal an insulator-to-metal transition, which is also confirmed and understood by density functional theory calculations. We demonstrate that the metallic phase is governed by a power law dependence of the conductivity at temperatures below 25 K, whereas the conductivity in the insulating phase is well described by a variable-range hopping mechanism with a Coulomb gap at temperatures in the range of 2-50 K. These results show that the electron wave-function in the vicinity of the transition is strongly affected by the disorder and the electron-electron interaction.

cond-mat.mtrl-sci↗

arXiv2020

End-to-End 3D Multi-Object Tracking and Trajectory Forecasting

3D multi-object tracking (MOT) and trajectory forecasting are two critical components in modern 3D perception systems. We hypothesize that it is beneficial to unify both tasks under one framework to learn a shared feature representation of agent interaction. To evaluate this hypothesis, we propose a unified solution for 3D MOT and trajectory forecasting which also incorporates two additional novel computational units. First, we employ a feature interaction technique by introducing Graph Neural Networks (GNNs) to capture the way in which multiple agents interact with one another. The GNN is able to model complex hierarchical interactions, improve the discriminative feature learning for MOT association, and provide socially-aware context for trajectory forecasting. Second, we use a diversity sampling function to improve the quality and diversity of our forecasted trajectories. The learned sampling function is trained to efficiently extract a variety of outcomes from a generative trajectory distribution and helps avoid the problem of generating many duplicate trajectory samples. We show that our method achieves state-of-the-art performance on the KITTI dataset. Our project website is at http://www.xinshuoweng.com/projects/GNNTrkForecast.

cs.CV↗

arXiv2020

AutoPose: Searching Multi-Scale Branch Aggregation for Pose Estimation

We present AutoPose, a novel neural architecture search(NAS) framework that is capable of automatically discovering multiple parallel branches of cross-scale connections towards accurate and high-resolution 2D human pose estimation. Recently, high-performance hand-crafted convolutional networks for pose estimation show growing demands on multi-scale fusion and high-resolution representations. However, current NAS works exhibit limited flexibility on scale searching, they dominantly adopt simplified search spaces of single-branch architectures. Such simplification limits the fusion of information at different scales and fails to maintain high-resolution representations. The presentedAutoPose framework is able to search for multi-branch scales and network depth, in addition to the cell-level microstructure. Motivated by the search space, a novel bi-level optimization method is presented, where the network-level architecture is searched via reinforcement learning, and the cell-level search is conducted by the gradient-based method. Within 2.5 GPU days, AutoPose is able to find very competitive architectures on the MS COCO dataset, that are also transferable to the MPII dataset. Our code is available at https://github.com/VITA-Group/AutoPose.

cs.CV↗

arXiv2020

Efficient Non-Line-of-Sight Imaging from Transient Sinograms

Non-line-of-sight (NLOS) imaging techniques use light that diffusely reflects off of visible surfaces (e.g., walls) to see around corners. One approach involves using pulsed lasers and ultrafast sensors to measure the travel time of multiply scattered light. Unlike existing NLOS techniques that generally require densely raster scanning points across the entirety of a relay wall, we explore a more efficient form of NLOS scanning that reduces both acquisition times and computational requirements. We propose a circular and confocal non-line-of-sight (C2NLOS) scan that involves illuminating and imaging a common point, and scanning this point in a circular path along a wall. We observe that (1) these C2NLOS measurements consist of a superposition of sinusoids, which we refer to as a transient sinogram, (2) there exists computationally efficient reconstruction procedures that transform these sinusoidal measurements into 3D positions of hidden scatterers or NLOS images of hidden objects, and (3) despite operating on an order of magnitude fewer measurements than previous approaches, these C2NLOS scans provide sufficient information about the hidden scene to solve these different NLOS imaging tasks. We show results from both simulated and real C2NLOS scans.

cs.CV↗

arXiv2020

On Deep Unsupervised Active Learning

Unsupervised active learning has attracted increasing attention in recent years, where its goal is to select representative samples in an unsupervised setting for human annotating. Most existing works are based on shallow linear models by assuming that each sample can be well approximated by the span (i.e., the set of all linear combinations) of certain selected samples, and then take these selected samples as representative ones to label. However, in practice, the data do not necessarily conform to linear models, and how to model nonlinearity of data often becomes the key point to success. In this paper, we present a novel Deep neural network framework for Unsupervised Active Learning, called DUAL. DUAL can explicitly learn a nonlinear embedding to map each input into a latent space through an encoder-decoder architecture, and introduce a selection block to select representative samples in the the learnt latent space. In the selection block, DUAL considers to simultaneously preserve the whole input patterns as well as the cluster structure of data. Extensive experiments are performed on six publicly available datasets, and experimental results clearly demonstrate the efficacy of our method, compared with state-of-the-arts.

cs.LG↗

arXiv2020

DLow: Diversifying Latent Flows for Diverse Human Motion Prediction

Deep generative models are often used for human motion prediction as they are able to model multi-modal data distributions and characterize diverse human behavior. While much care has been taken into designing and learning deep generative models, how to efficiently produce diverse samples from a deep generative model after it has been trained is still an under-explored problem. To obtain samples from a pretrained generative model, most existing generative human motion prediction methods draw a set of independent Gaussian latent codes and convert them to motion samples. Clearly, this random sampling strategy is not guaranteed to produce diverse samples for two reasons: (1) The independent sampling cannot force the samples to be diverse; (2) The sampling is based solely on likelihood which may only produce samples that correspond to the major modes of the data distribution. To address these problems, we propose a novel sampling method, Diversifying Latent Flows (DLow), to produce a diverse set of samples from a pretrained deep generative model. Unlike random (independent) sampling, the proposed DLow sampling method samples a single random variable and then maps it with a set of learnable mapping functions to a set of correlated latent codes. The correlated latent codes are then decoded into a set of correlated samples. During training, DLow uses a diversity-promoting prior over samples as an objective to optimize the latent mappings to improve sample diversity. The design of the prior is highly flexible and can be customized to generate diverse motions with common features (e.g., similar leg motion but diverse upper-body motion). Our experiments demonstrate that DLow outperforms state-of-the-art baseline methods in terms of sample diversity and accuracy. Our code is released on the project page: https://www.ye-yuan.com/dlow.

cs.CV↗

arXiv2020

Keeping Designers in the Loop: Communicating Inherent Algorithmic Trade-offs Across Multiple Objectives

Artificial intelligence algorithms have been used to enhance a wide variety of products and services, including assisting human decision making in high-stakes contexts. However, these algorithms are complex and have trade-offs, notably between prediction accuracy and fairness to population subgroups. This makes it hard for designers to understand algorithms and design products or services in a way that respects users' goals, values, and needs. We proposed a method to help designers and users explore algorithms, visualize their trade-offs, and select algorithms with trade-offs consistent with their goals and needs. We evaluated our method on the problem of predicting criminal defendants' likelihood to re-offend through (i) a large-scale Amazon Mechanical Turk experiment, and (ii) in-depth interviews with domain experts. Our evaluations show that our method can help designers and users of these systems better understand and navigate algorithmic trade-offs. This paper contributes a new way of providing designers the ability to understand and control the outcomes of algorithmic systems they are creating.

cs.HC↗

arXiv2020

Self-PU: Self Boosted and Calibrated Positive-Unlabeled Training

Many real-world applications have to tackle the Positive-Unlabeled (PU) learning problem, i.e., learning binary classifiers from a large amount of unlabeled data and a few labeled positive examples. While current state-of-the-art methods employ importance reweighting to design various risk estimators, they ignored the learning capability of the model itself, which could have provided reliable supervision. This motivates us to propose a novel Self-PU learning framework, which seamlessly integrates PU learning and self-training. Self-PU highlights three "self"-oriented building blocks: a self-paced training algorithm that adaptively discovers and augments confident positive/negative examples as the training proceeds; a self-calibrated instance-aware loss; and a self-distillation scheme that introduces teacher-students learning as an effective regularization for PU learning. We demonstrate the state-of-the-art performance of Self-PU on common PU learning benchmarks (MNIST and CIFAR-10), which compare favorably against the latest competitors. Moreover, we study a real-world application of PU learning, i.e., classifying brain images of Alzheimer's Disease. Self-PU obtains significantly improved results on the renowned Alzheimer's Disease Neuroimaging Initiative (ADNI) database over existing methods. The code is publicly available at: https://github.com/TAMU-VITA/Self-PU.

cs.LG↗

arXiv2020

Exact Single-Source SimRank Computation on Large Graphs

SimRank is a popular measurement for evaluating the node-to-node similarities based on the graph topology. In recent years, single-source and top-$k$ SimRank queries have received increasing attention due to their applications in web mining, social network analysis, and spam detection. However, a fundamental obstacle in studying SimRank has been the lack of ground truths. The only exact algorithm, Power Method, is computationally infeasible on graphs with more than $10^6$ nodes. Consequently, no existing work has evaluated the actual trade-offs between query time and accuracy on large real-world graphs. In this paper, we present ExactSim, the first algorithm that computes the exact single-source and top-$k$ SimRank results on large graphs. With high probability, this algorithm produces ground truths with a rigorous theoretical guarantee. We conduct extensive experiments on real-world datasets to demonstrate the efficiency of ExactSim. The results show that ExactSim provides the ground truth for any single-source SimRank query with a precision up to 7 decimal places within a reasonable query time.

cs.DS↗

arXiv2020

Self-assembled nematic colloidal motors powered by light

Biological motors are marvels of nature that inspire creation of their synthetic counterparts with comparable nanoscale dimensions, high efficiency and diverse functions. Molecular motors have been synthesized, but obtaining nanomotors through self-assembly remains challenging. Here we describe a self-assembled colloidal motor with a repetitive light-driven rotation of transparent micro-particles immersed in a liquid crystal and powered by a continuous exposure to unstructured ~1 nW light. A monolayer of azobenzene molecules defines how the liquid crystal's optical axis mechanically couples to the particle's surface, as well as how they jointly rotate as the light's polarization changes. The rotating particle twists the liquid crystal, which changes polarization of traversing light. The resulting feedback mechanism yields a continuous opto-mechanical cycle and drives the unidirectional particle spinning, with handedness and frequency robustly controlled by polarization and intensity of light. Our findings may lead to opto-mechanical devices and colloidal machines compatible with liquid crystal display technology.

cond-mat.soft↗

arXiv2020

Generative Hybrid Representations for Activity Forecasting with No-Regret Learning

Automatically reasoning about future human behaviors is a difficult problem but has significant practical applications to assistive systems. Part of this difficulty stems from learning systems' inability to represent all kinds of behaviors. Some behaviors, such as motion, are best described with continuous representations, whereas others, such as picking up a cup, are best described with discrete representations. Furthermore, human behavior is generally not fixed: people can change their habits and routines. This suggests these systems must be able to learn and adapt continuously. In this work, we develop an efficient deep generative model to jointly forecast a person's future discrete actions and continuous motions. On a large-scale egocentric dataset, EPIC-KITCHENS, we observe our method generates high-quality and diverse samples while exhibiting better generalization than related generative models. Finally, we propose a variant to continually learn our model from streaming data, observe its practical effectiveness, and theoretically justify its learning efficiency.

cs.CV↗

arXiv2020

SiamFC++: Towards Robust and Accurate Visual Tracking with Target Estimation Guidelines

Visual tracking problem demands to efficiently perform robust classification and accurate target state estimation over a given target at the same time. Former methods have proposed various ways of target state estimation, yet few of them took the particularity of the visual tracking problem itself into consideration. After a careful analysis, we propose a set of practical guidelines of target state estimation for high-performance generic object tracker design. Following these guidelines, we design our Fully Convolutional Siamese tracker++ (SiamFC++) by introducing both classification and target state estimation branch(G1), classification score without ambiguity(G2), tracking without prior knowledge(G3), and estimation quality score(G4). Extensive analysis and ablation studies demonstrate the effectiveness of our proposed guidelines. Without bells and whistles, our SiamFC++ tracker achieves state-of-the-art performance on five challenging benchmarks(OTB2015, VOT2018, LaSOT, GOT-10k, TrackingNet), which proves both the tracking and generalization ability of the tracker. Particularly, on the large-scale TrackingNet dataset, SiamFC++ achieves a previously unseen AUC score of 75.4 while running at over 90 FPS, which is far above the real-time requirement. Code and models are available at: https://github.com/MegviiDetection/video_analyst .

cs.CV↗

arXiv2020

Semi-Supervised Cervical Dysplasia Classification With Learnable Graph Convolutional Network

Cervical cancer is the second most prevalent cancer affecting women today. As the early detection of cervical carcinoma relies heavily upon screening and pre-clinical testing, digital cervicography has great potential as a primary or auxiliary screening tool, especially in low-resource regions due to its low cost and easy access. Although an automated cervical dysplasia detection system has been desirable, traditional fully-supervised training of such systems requires large amounts of annotated data which are often labor-intensive to collect. To alleviate the need for much manual annotation, we propose a novel graph convolutional network (GCN) based semi-supervised classification model that can be trained with fewer annotations. In existing GCNs, graphs are constructed with fixed features and can not be updated during the learning process. This limits their ability to exploit new features learned during graph convolution. In this paper, we propose a novel and more flexible GCN model with a feature encoder that adaptively updates the adjacency matrix during learning and demonstrate that this model design leads to improved performance. Our experimental results on a cervical dysplasia classification dataset show that the proposed framework outperforms previous methods under a semi-supervised setting, especially when the labeled samples are scarce.

cs.CV↗