arXiv subjects

Shuo Yang

Publications and source records attributed to Shuo Yang.

At least 379 records · Page 21Linked to original sources

arXiv2019

Noise-tolerant Detection of $Z_N$ Topological Orders in Quantum Many-body States

Topologically ordered states are fundamentally important in theoretical physics, which are also suggested as promising candidates to build fault-tolerant quantum devices. However, it is still elusive how topological orders can be affected or detected under noises. In this work, we find a quantity, termed as the ring degeneracy $\mathcal{D}$, which is robust under pure noise to detect both trivial and intrinsic topological orders. The ring degeneracy is defined as the degeneracy of the solutions of the self-consistent equations that encode the contraction of the corresponding tensor network(TN). For the $Z_N$ orders, we find that the ring degeneracy satisfies a simple relation $\mathcal{D} = (N + 1)/2 + d$, with $d = 0$ for odd $N$ and $d = 1/2$ for even $N$. Simulations on several non-trivial states (two-dimensional Ising model, $Z_N$ topological states, and resonating valence bond states) show that the ring degeneracy can tolerate noises up to a strength associated to the gap of the TN boundary theory.

cond-mat.stat-mech↗

arXiv2019

Region Proposal by Guided Anchoring

Region anchors are the cornerstone of modern object detection techniques. State-of-the-art detectors mostly rely on a dense anchoring scheme, where anchors are sampled uniformly over the spatial domain with a predefined set of scales and aspect ratios. In this paper, we revisit this foundational stage. Our study shows that it can be done much more effectively and efficiently. Specifically, we present an alternative scheme, named Guided Anchoring, which leverages semantic features to guide the anchoring. The proposed method jointly predicts the locations where the center of objects of interest are likely to exist as well as the scales and aspect ratios at different locations. On top of predicted anchor shapes, we mitigate the feature inconsistency with a feature adaption module. We also study the use of high-quality proposals to improve detection performance. The anchoring scheme can be seamlessly integrated into proposal methods and detectors. With Guided Anchoring, we achieve 9.1% higher recall on MS COCO with 90% fewer anchors than the RPN baseline. We also adopt Guided Anchoring in Fast R-CNN, Faster R-CNN and RetinaNet, respectively improving the detection mAP by 2.2%, 2.7% and 1.2%. Code will be available at https://github.com/open-mmlab/mmdetection.

cs.CV↗

arXiv2019

WIDER Face and Pedestrian Challenge 2018: Methods and Results

This paper presents a review of the 2018 WIDER Challenge on Face and Pedestrian. The challenge focuses on the problem of precise localization of human faces and bodies, and accurate association of identities. It comprises of three tracks: (i) WIDER Face which aims at soliciting new approaches to advance the state-of-the-art in face detection, (ii) WIDER Pedestrian which aims to find effective and efficient approaches to address the problem of pedestrian detection in unconstrained environments, and (iii) WIDER Person Search which presents an exciting challenge of searching persons across 192 movies. In total, 73 teams made valid submissions to the challenge tracks. We summarize the winning solutions for all three tracks. and present discussions on open problems and potential research directions in these topics.

cs.CV↗

arXiv2018

Fine-Grained User Profiling for Personalized Task Matching in Mobile Crowdsensing

In mobile crowdsensing, finding the best match between tasks and users is crucial to ensure both the quality and effectiveness of a crowdsensing system. Existing works usually assume a centralized task assignment by the crowdsensing platform, without addressing the need of fine-grained personalized task matching. In this paper, we argue that it is essential to match tasks to users based on a careful characterization of both the users' preference and reliability. To that end, we propose a personalized task recommender system for mobile crowdsensing, which recommends tasks to users based on a recommendation score that jointly takes each user's preference and reliability into consideration. We first present a hybrid preference metric to characterize users' preference by exploiting their implicit feedback. Then, to profile users' reliability levels, we formalize the problem as a semi-supervised learning model, and propose an efficient block coordinate descent algorithm to solve the problem. For some tasks that lack users' historical information, we further propose a matrix factorization method to infer the users' reliability levels on those tasks. We conduct extensive experiments to evaluate the performance of our system, and the evaluation results demonstrate that our system can achieve superior performance to the benchmarks in both user profiling and personalized task recommendation.

cs.IR↗

arXiv2018

Effective Learning of Probabilistic Models for Clinical Predictions from Longitudinal Data

With the expeditious advancement of information technologies, health-related data presented unprecedented potentials for medical and health discoveries but at the same time significant challenges for machine learning techniques both in terms of size and complexity. Those challenges include: the structured data with various storage formats and value types caused by heterogeneous data sources; the uncertainty widely existing in every aspect of medical diagnosis and treatments; the high dimensionality of the feature space; the longitudinal medical records data with irregular intervals between adjacent observations; the richness of relations existing among objects with similar genetic factors, location or socio-demographic background. This thesis aims to develop advanced Statistical Relational Learning approaches in order to effectively exploit such health-related data and facilitate the discoveries in medical research. It presents the work on cost-sensitive statistical relational learning for mining structured imbalanced data, the first continuous-time probabilistic logic model for predicting sequential events from longitudinal structured data as well as hybrid probabilistic relational models for learning from heterogeneous structured data. It also demonstrates the outstanding performance of these proposed models as well as other state of the art machine learning models when applied to medical research problems and other real-world large-scale systems, reveals the great potential of statistical relational learning for exploring the structured health-related data to facilitate medical research.

cs.LG↗

arXiv2018

Computing the quasipotential for nongradient SDEs in 3D

Nongradient SDEs with small white noise often arise when modeling biological and ecological time-irreversible processes. If the governing SDE were gradient, the maximum likelihood transition paths, transition rates, expected exit times, and the invariant probability distribution would be given in terms of its potential function. The quasipotential plays a similar role for nongradient SDEs. Unfortunately, the quasipotential is the solution of a functional minimization problem that can be obtained analytically only in some special cases. We propose a Dijkstra-like solver for computing the quasipotential on regular rectangular meshes in 3D. This solver results from a promotion and an upgrade of the previously introduced ordered line integral method with the midpoint quadrature rule for 2D SDEs. The key innovations that have allowed us to keep the CPU times reasonable while maintaining good accuracy are $(i)$ a new hierarchical update strategy, $(ii)$ the use of Karush-Kuhn-Tucker theory for rejecting unnecessary simplex updates, and $(iii)$ pruning the number of admissible simplexes and a fast search for them. An extensive numerical study is conducted on a series of linear and nonlinear examples where the quasipotential is analytically available or can be found at transition states by other methods. In particular, the proposed solver is applied to Tao's examples where the transition states are hyperbolic periodic orbits, and to a genetic switch model by Lv et al. (2014). The C source code implementing the proposed algorithm is available at M. Cameron's web page.

math.NA↗

arXiv2018

Integrating Episodic Memory into a Reinforcement Learning Agent using Reservoir Sampling

Episodic memory is a psychology term which refers to the ability to recall specific events from the past. We suggest one advantage of this particular type of memory is the ability to easily assign credit to a specific state when remembered information is found to be useful. Inspired by this idea, and the increasing popularity of external memory mechanisms to handle long-term dependencies in deep learning systems, we propose a novel algorithm which uses a reservoir sampling procedure to maintain an external memory consisting of a fixed number of past states. The algorithm allows a deep reinforcement learning agent to learn online to preferentially remember those states which are found to be useful to recall later on. Critically this method allows for efficient online computation of gradient estimates with respect to the write process of the external memory. Thus unlike most prior mechanisms for external memory it is feasible to use in an online reinforcement learning setting.

cs.LG↗

arXiv2018

Look at Boundary: A Boundary-Aware Face Alignment Algorithm

We present a novel boundary-aware face alignment algorithm by utilising boundary lines as the geometric structure of a human face to help facial landmark localisation. Unlike the conventional heatmap based method and regression based method, our approach derives face landmarks from boundary lines which remove the ambiguities in the landmark definition. Three questions are explored and answered by this work: 1. Why using boundary? 2. How to use boundary? 3. What is the relationship between boundary estimation and landmarks localisation? Our boundary- aware face alignment algorithm achieves 3.49% mean error on 300-W Fullset, which outperforms state-of-the-art methods by a large margin. Our method can also easily integrate information from other datasets. By utilising boundary information of 300-W dataset, our method achieves 3.92% mean error with 0.39% failure rate on COFW dataset, and 1.25% mean error on AFLW-Full dataset. Moreover, we propose a new dataset WFLW to unify training and testing across different factors, including poses, expressions, illuminations, makeups, occlusions, and blurriness. Dataset and model will be publicly available at https://wywu.github.io/projects/LAB/LAB.html

cs.CV↗

arXiv2018

Optimizing Video Object Detection via a Scale-Time Lattice

High-performance object detection relies on expensive convolutional networks to compute features, often leading to significant challenges in applications, e.g. those that require detecting objects from video streams in real time. The key to this problem is to trade accuracy for efficiency in an effective way, i.e. reducing the computing cost while maintaining competitive performance. To seek a good balance, previous efforts usually focus on optimizing the model architectures. This paper explores an alternative approach, that is, to reallocate the computation over a scale-time space. The basic idea is to perform expensive detection sparsely and propagate the results across both scales and time with substantially cheaper networks, by exploiting the strong correlations among them. Specifically, we present a unified framework that integrates detection, temporal propagation, and across-scale refinement on a Scale-Time Lattice. On this framework, one can explore various strategies to balance performance and cost. Taking advantage of this flexibility, we further develop an adaptive scheme with the detector invoked on demand and thus obtain improved tradeoff. On ImageNet VID dataset, the proposed method can achieve a competitive mAP 79.6% at 20 fps, or 79.0% at 62 fps as a performance/speed tradeoff.

cs.CV↗

arXiv2018

Machine Learning-based Brokers for Real-time Classification of the LSST Alert Stream

The unprecedented volume and rate of transient events that will be discovered by the Large Synoptic Survey Telescope (LSST) demands that the astronomical community update its followup paradigm. Alert-brokers -- automated software system to sift through, characterize, annotate and prioritize events for followup -- will be critical tools for managing alert streams in the LSST era. The Arizona-NOAO Temporal Analysis and Response to Events System (ANTARES) is one such broker. In this work, we develop a machine learning pipeline to characterize and classify variable and transient sources only using the available multiband optical photometry. We describe three illustrative stages of the pipeline, serving the three goals of early, intermediate and retrospective classification of alerts. The first takes the form of variable vs transient categorization, the second, a multi-class typing of the combined variable and transient dataset, and the third, a purity-driven subtyping of a transient class. While several similar algorithms have proven themselves in simulations, we validate their performance on real observations for the first time. We quantitatively evaluate our pipeline on sparse, unevenly sampled, heteroskedastic data from various existing observational campaigns, and demonstrate very competitive classification performance. We describe our progress towards adapting the pipeline developed in this work into a real-time broker working on live alert streams from time-domain surveys.

astro-ph.IM↗

arXiv2017

Faceness-Net: Face Detection through Deep Facial Part Responses

We propose a deep convolutional neural network (CNN) for face detection leveraging on facial attributes based supervision. We observe a phenomenon that part detectors emerge within CNN trained to classify attributes from uncropped face images, without any explicit part supervision. The observation motivates a new method for finding faces through scoring facial parts responses by their spatial structure and arrangement. The scoring mechanism is data-driven, and carefully formulated considering challenging cases where faces are only partially visible. This consideration allows our network to detect faces under severe occlusion and unconstrained pose variations. Our method achieves promising performance on popular benchmarks including FDDB, PASCAL Faces, AFW, and WIDER FACE.

cs.CV↗

arXiv2017

Face Detection through Scale-Friendly Deep Convolutional Networks

In this paper, we share our experience in designing a convolutional network-based face detector that could handle faces of an extremely wide range of scales. We show that faces with different scales can be modeled through a specialized set of deep convolutional networks with different structures. These detectors can be seamlessly integrated into a single unified network that can be trained end-to-end. In contrast to existing deep models that are designed for wide scale range, our network does not require an image pyramid input and the model is of modest complexity. Our network, dubbed ScaleFace, achieves promising performance on WIDER FACE and FDDB datasets with practical runtime speed. Specifically, our method achieves 76.4 average precision on the challenging WIDER FACE dataset and 96% recall rate on the FDDB dataset with 7 frames per second (fps) for 900 * 1300 input image.

cs.CV↗

arXiv2017

Algorithm-Directed Crash Consistence in Non-Volatile Memory for HPC

Fault tolerance is one of the major design goals for HPC. The emergence of non-volatile memories (NVM) provides a solution to build fault tolerant HPC. Data in NVM-based main memory are not lost when the system crashes because of the non-volatility nature of NVM. However, because of volatile caches, data must be logged and explicitly flushed from caches into NVM to ensure consistence and correctness before crashes, which can cause large runtime overhead. In this paper, we introduce an algorithm-based method to establish crash consistence in NVM for HPC applications. We slightly extend application data structures or sparsely flush cache blocks, which introduce ignorable runtime overhead. Such extension or cache flushing allows us to use algorithm knowledge to \textit{reason} data consistence or correct inconsistent data when the application crashes. We demonstrate the effectiveness of our method for three algorithms, including an iterative solver, dense matrix multiplication, and Monte-Carlo simulation. Based on comprehensive performance evaluation on a variety of test environments, we demonstrate that our approach has very small runtime overhead (at most 8.2\% and less than 3\% in most cases), much smaller than that of traditional checkpoint, while having the same or less recomputation cost.

cs.DC↗

arXiv2017

Residual Attention Network for Image Classification

In this work, we propose "Residual Attention Network", a convolutional neural network using attention mechanism which can incorporate with state-of-art feed forward network architecture in an end-to-end training fashion. Our Residual Attention Network is built by stacking Attention Modules which generate attention-aware features. The attention-aware features from different modules change adaptively as layers going deeper. Inside each Attention Module, bottom-up top-down feedforward structure is used to unfold the feedforward and feedback attention process into a single feedforward process. Importantly, we propose attention residual learning to train very deep Residual Attention Networks which can be easily scaled up to hundreds of layers. Extensive analyses are conducted on CIFAR-10 and CIFAR-100 datasets to verify the effectiveness of every module mentioned above. Our Residual Attention Network achieves state-of-the-art object recognition performance on three benchmark datasets including CIFAR-10 (3.90% error), CIFAR-100 (20.45% error) and ImageNet (4.8% single model and single crop, top-5 error). Note that, our method achieves 0.6% top-1 accuracy improvement with 46% trunk depth and 69% forward FLOPs comparing to ResNet-200. The experiment also demonstrates that our network is robust against noisy labels.

cs.CV↗

arXiv2017

Synthesis of Borophene Nanoribbons on Ag(110) Surface

We present the successful synthesis of single-atom-thick borophene nanoribbons (BNRs) by self-assembly of boron on Ag(110) surface. The scanning tunneling microscopy (STM) studies reveal high quality BNRs: all the ribbons are along the [-110] direction of Ag(110), and can run across the steps on the surface. The width of ribbons is distributed in a narrow range around 10.3 nm. High resolution STM images revealed four ordered surface structures in BNRs. Combined with DFT calculations, we found that all the four structures of boron nanoribbons consist of the boron chains with different width, separated by hexagonal hole arrays. The successful synthesis of BNRs enriches the low dimensional allotrope of boron and may promote further applications of borophene

cond-mat.mtrl-sci↗

arXiv2017

$h\toμτ$ and muon g-2 in the alignment limit of two-Higgs-doublet model

We examine the $h\to μτ$ and muon g-2 in the exact alignment limit of two-Higgs-doublet model. In this case, the couplings of the SM-like Higgs to the SM particles are the same as the Higgs couplings in the SM at the tree level, and the tree-level lepton-flavor-violating coupling $hμτ$ is absent. We assume the lepton-flavor-violating $μτ$ excess observed by CMS to be respectively from the other neutral Higgses, $H$ and $A$, which almost degenerates with the SM-like Higgs at the 125 GeV. After imposing the relevant theoretical constraints and experimental constraints from the precision electroweak data, $B$-meson decays, $τ$ decays and Higgs searches, we find that the muon g-2 anomaly and $μτ$ excess favor the small lepton Yukawa coupling and top Yukawa coupling of the non-SM-like Higgs around 125 GeV, and the lepton-flavor-violating coupling is sensitive to another heavy neutral Higgs mass. In addition, if the $μτ$ excess is from $H$ around 125 GeV, the experimental data of the heavy Higgs decaying into $μτ$ favor $m_A>230$ GeV for a relatively large $H\bar{t}t$ coupling.

hep-ph↗

arXiv2017

Hand3D: Hand Pose Estimation using 3D Neural Network

We propose a novel 3D neural network architecture for 3D hand pose estimation from a single depth image. Different from previous works that mostly run on 2D depth image domain and require intermediate or post process to bring in the supervision from 3D space, we convert the depth map to a 3D volumetric representation, and feed it into a 3D convolutional neural network(CNN) to directly produce the pose in 3D requiring no further process. Our system does not require the ground truth reference point for initialization, and our network architecture naturally integrates both local feature and global context in 3D space. To increase the coverage of the hand pose space of the training data, we render synthetic depth image by transferring hand pose from existing real image datasets. We evaluation our algorithm on two public benchmarks and achieve the state-of-the-art performance. The synthetic hand pose dataset will be available.

cs.CV↗

arXiv2017

Loop optimization for tensor network renormalization

We introduce a tensor renormalization group scheme for coarse-graining a two-dimensional tensor network that can be successfully applied to both classical and quantum systems on and off criticality. The key innovation in our scheme is to deform a 2D tensor network into small loops and then optimize the tensors on each loop. In this way, we remove short-range entanglement at each iteration step and significantly improve the accuracy and stability of the renormalization flow. We demonstrate our algorithm in the classical Ising model and a frustrated 2D quantum model.

cond-mat.str-el↗