arXiv subjects

Yuan Wang

Publications and source records attributed to Yuan Wang.

At least 217 records · Page 12Linked to original sources

arXiv2021

Graph Attention Layer Evolves Semantic Segmentation for Road Pothole Detection: A Benchmark and Algorithms

Existing road pothole detection approaches can be classified as computer vision-based or machine learning-based. The former approaches typically employ 2-D image analysis/understanding or 3-D point cloud modeling and segmentation algorithms to detect road potholes from vision sensor data. The latter approaches generally address road pothole detection using convolutional neural networks (CNNs) in an end-to-end manner. However, road potholes are not necessarily ubiquitous and it is challenging to prepare a large well-annotated dataset for CNN training. In this regard, while computer vision-based methods were the mainstream research trend in the past decade, machine learning-based methods were merely discussed. Recently, we published the first stereo vision-based road pothole detection dataset and a novel disparity transformation algorithm, whereby the damaged and undamaged road areas can be highly distinguished. However, there are no benchmarks currently available for state-of-the-art (SoTA) CNNs trained using either disparity images or transformed disparity images. Therefore, in this paper, we first discuss the SoTA CNNs designed for semantic segmentation and evaluate their performance for road pothole detection with extensive experiments. Additionally, inspired by graph neural network (GNN), we propose a novel CNN layer, referred to as graph attention layer (GAL), which can be easily deployed in any existing CNN to optimize image feature representations for semantic segmentation. Our experiments compare GAL-DeepLabv3+, our best-performing implementation, with nine SoTA CNNs on three modalities of training data: RGB images, disparity images, and transformed disparity images. The experimental results suggest that our proposed GAL-DeepLabv3+ achieves the best overall pothole detection accuracy on all training data modalities.

cs.CV↗

arXiv2021

Profit-Maximizing Parcel Locker Location Problem under Threshold Luce Model

The growth of e-commerce has created increasing complexity in logistics services. To remain competitive, logistics and e-commerce companies are exploring new modes as supplements to traditional home delivery, one of which is the self-service parcel locker. This paper studies a parcel locker location problem where a company plans to introduce the locker service by locating locker facilities to attract customers. The objective is to maximize the profit, accounting for the revenue and the cost of facilities. To estimate the revenue, we use the threshold Luce model (TLM) to predict customers' likelihood of using the locker service. We then propose a combinatorial optimization model and develop exact solution methodologies that are practically implementable according to our extensive computational experiments. In effect, our modeling framework generalizes the traditional facility location problems based on the binomial logit model (BNL) and the multinomial logit model (MNL), both of which impose strong and strict assumptions on the customer's choice sets. That is, they assume that the choice sets will either contain only one facility or all facilities. In our numerical experiment, we demonstrate that using the BNL and the MNL in the locker location problem could lead to, respectively, pessimistic and optimistic revenue estimation. Consequently, the suggested location decisions will be either conservative or aggressive. Our proposed model, by contrast, can effectively relax these assumptions. Our results also reveal that the aggressive decision due to the use of the MNL will incur an unnecessarily high facility cost that cannot be compensated by the additional revenue, leading to profit loss that can be significant in various scenarios. Finally, we conduct sensitivity analysis on the input parameters and draw additional implications.

math.OC↗

arXiv2021

Theoretical proposals to measure resonator-induced modifications of the electronic ground-state in doped quantum wells

Recent interest in the physics of non-perturbative light-matter coupling led to the development of solid-state cavity quantum electrodynamics setups in which the interaction energies are comparable with the bare ones. In such a regime the ground state of the coupled system becomes interaction-dependent and is predicted to contain a population of virtual excitations which, notwithstanding having been object of many investigations, remain still unobserved. In this paper we investigate how virtual electronic excitations in quantum wells modify the ground-state charge distribution, and propose two methods to measure such a cavity-induced perturbation. The first approach we consider is based on spectroscopic mapping of the electronic population at a specific location in the quantum well using localised defect states. The second approach exploits instead the photonic equivalent of a Kelvin probe to measure the average change distribution across the quantum well. We find both effects observable with present-day or near-future technology. Our results thus provide a route toward a demonstration of cavity-induced modulation of ground-state electronic properties.

cond-mat.mes-hall↗

arXiv2021

AdaFit: Rethinking Learning-based Normal Estimation on Point Clouds

This paper presents a neural network for robust normal estimation on point clouds, named AdaFit, that can deal with point clouds with noise and density variations. Existing works use a network to learn point-wise weights for weighted least squares surface fitting to estimate the normals, which has difficulty in finding accurate normals in complex regions or containing noisy points. By analyzing the step of weighted least squares surface fitting, we find that it is hard to determine the polynomial order of the fitting surface and the fitting surface is sensitive to outliers. To address these problems, we propose a simple yet effective solution that adds an additional offset prediction to improve the quality of normal estimation. Furthermore, in order to take advantage of points from different neighborhood sizes, a novel Cascaded Scale Aggregation layer is proposed to help the network predict more accurate point-wise offsets and weights. Extensive experiments demonstrate that AdaFit achieves state-of-the-art performance on both the synthetic PCPNet dataset and the real-word SceneNN dataset.

cs.CV↗

arXiv2021

TriTransNet: RGB-D Salient Object Detection with a Triplet Transformer Embedding Network

Salient object detection is the pixel-level dense prediction task which can highlight the prominent object in the scene. Recently U-Net framework is widely used, and continuous convolution and pooling operations generate multi-level features which are complementary with each other. In view of the more contribution of high-level features for the performance, we propose a triplet transformer embedding module to enhance them by learning long-range dependencies across layers. It is the first to use three transformer encoders with shared weights to enhance multi-level features. By further designing scale adjustment module to process the input, devising three-stream decoder to process the output and attaching depth features to color features for the multi-modal fusion, the proposed triplet transformer embedding network (TriTransNet) achieves the state-of-the-art performance in RGB-D salient object detection, and pushes the performance to a new level. Experimental results demonstrate the effectiveness of the proposed modules and the competition of TriTransNet.

cs.CV↗

arXiv2021

Suppressing the endemic equilibrium in SIS epidemics: A state dependent approach

This paper considers the susceptible-infected-susceptible (SIS) epidemic model with an underlying network structure among subpopulations and focuses on the effect of social distancing to regulate the epidemic level. We demonstrate that if each subpopulation is informed of its infection rate and reduces interactions accordingly, the fraction of the subpopulation infected can remain below half for all time instants. To this end, we first modify the basic SIS model by introducing a state dependent parameter representing the frequency of interactions between subpopulations. Thereafter, we show that for this modified SIS model, the spectral radius of a suitably-defined matrix being not greater than one causes all the agents, regardless of their initial sickness levels, to converge to the healthy state; assuming non-trivial disease spread, the spectral radius being greater than one leads to the existence of a unique endemic equilibrium, which is also asymptotically stable. Finally, by leveraging the aforementioned results, we show that the fraction of (sub)populations infected never exceeds half.

eess.SY↗

arXiv2021

Integer-Only Neural Network Quantization Scheme Based on Shift-Batch-Normalization

Neural networks are very popular in many areas, but great computing complexity makes it hard to run neural networks on devices with limited resources. To address this problem, quantization methods are used to reduce model size and computation cost, making it possible to use neural networks on embedded platforms or mobile devices. In this paper, an integer-only-quantization scheme is introduced. This scheme uses one layer that combines shift-based batch normalization and uniform quantization to implement 4-bit integer-only inference. Without big integer multiplication(which is used in previous integer-only-quantization methods), this scheme can achieve good power and latency efficiency, and is especially suitable to be deployed on co-designed hardware platforms. Tests have proved that this scheme works very well for easy tasks. And for tough tasks, performance loss can be tolerated for its inference efficiency. Our work is available on github: https://github.com/hguq/IntegerNet.

cs.LG↗

arXiv2021

Multiple Symmetry-Protected Dirac Nodal Lines in A Quasi-One-Dimensional Semimetal

Nodal-line semimetals (NLSMs) contains Dirac/Weyl type band-crossing nodes extending into shapes of line, loop and chain in the reciprocal space, leading to novel band topology and transport responses. Robust NLSMs against spin-orbit coupling typically occur in three-dimensional materials with more symmetry operations to protect the line nodes of band crossing, while the possibilities in lower-dimensional materials are rarely discussed. Here we demonstrate robust NLSM phase in a quasi-one-dimensional nonmagnetic semimetal TaNiTe5. Combining angle-resolved photoemission spectroscopy measurements and first-principles calculations, we reveal how reduced dimension can interact with nonsymmorphic symmetry and result into multiple Dirac-type nodal lines with four-fold degeneracy. Our findings suggest rich physics and application in (quasi-)one-dimensional topological materials and call for further investigation on the interplay between the quantum confinement and nontrivial band topology.

cond-mat.other↗

arXiv2021

US Fatal Police Shooting Analysis and Prediction

We believe that "all men are created equal". With the rise of the police shootings reported by media, more people in the U.S. think that police use excessive force during law enforcement, especially to a specific group of people. We want to apply multidimensional statistical analysis to reveal more facts than the monotone mainstream media. Our paper has three parts. First, we proposed a new method to quantify fatal police shooting news reporting deviation of mainstream media, which includes CNN, FOX, ABC, and NBC. Second, we analyzed the most comprehensive US fatal police shooting dataset from Washington Post. We used FP-growth to reveal the frequent patterns and DBSCAN clustering to find fatal shooting hotspots. We brought multi-attributes (social economics, demographics, political tendency, education, gun ownership rate, police training hours, etc.) to reveal connections under the iceberg. We found that the police shooting rate of a state depends on many variables. The top four most relevant attributes were state joined year, state land area, gun ownership rate, and violent crime rate. Third, we proposed four regression models to predict police shooting rates at the state level. The best model Kstar could predict the fatal police shooting rate with about 88.53% correlation coefficient. We also proposed classification models, including Gradient Boosting Machine, Multi-class Classifier, Logistic Regression, and Naive Bayes Classifier, to predict the race of fatal police shooting victims. Our classification models show no significant evidence to conclude that racial discrimination happened during fatal police shootings recorded by the WP dataset.

physics.soc-ph↗

arXiv2021

Anchor & Transform: Learning Sparse Embeddings for Large Vocabularies

Learning continuous representations of discrete objects such as text, users, movies, and URLs lies at the heart of many applications including language and user modeling. When using discrete objects as input to neural networks, we often ignore the underlying structures (e.g., natural groupings and similarities) and embed the objects independently into individual vectors. As a result, existing methods do not scale to large vocabulary sizes. In this paper, we design a simple and efficient embedding algorithm that learns a small set of anchor embeddings and a sparse transformation matrix. We call our method Anchor & Transform (ANT) as the embeddings of discrete objects are a sparse linear combination of the anchors, weighted according to the transformation matrix. ANT is scalable, flexible, and end-to-end trainable. We further provide a statistical interpretation of our algorithm as a Bayesian nonparametric prior for embeddings that encourages sparsity and leverages natural groupings among objects. By deriving an approximate inference algorithm based on Small Variance Asymptotics, we obtain a natural extension that automatically learns the optimal number of anchors instead of having to tune it as a hyperparameter. On text classification, language modeling, and movie recommendation benchmarks, we show that ANT is particularly suitable for large vocabulary sizes and demonstrates stronger performance with fewer parameters (up to 40x compression) as compared to existing compression baselines.

cs.LG↗

arXiv2021

Three-Filters-to-Normal: An Accurate and Ultrafast Surface Normal Estimator

This paper proposes three-filters-to-normal (3F2N), an accurate and ultrafast surface normal estimator (SNE), which is designed for structured range sensor data, e.g., depth/disparity images. 3F2N SNE computes surface normals by simply performing three filtering operations (two image gradient filters in horizontal and vertical directions, respectively, and a mean/median filter) on an inverse depth image or a disparity image. Despite the simplicity of 3F2N SNE, no similar method already exists in the literature. To evaluate the performance of our proposed SNE, we created three large-scale synthetic datasets (easy, medium and hard) using 24 3D mesh models, each of which is used to generate 1800--2500 pairs of depth images (resolution: 480X640 pixels) and the corresponding ground-truth surface normal maps from different views. 3F2N SNE demonstrates the state-of-the-art performance, outperforming all other existing geometry-based SNEs, where the average angular errors with respect to the easy, medium and hard datasets are 1.66 degrees, 5.69 degrees and 15.31 degrees, respectively. Furthermore, our C++ and CUDA implementations achieve a processing speed of over 260 Hz and 21 kHz, respectively. Our datasets and source code are publicly available at sites.google.com/view/3f2n.

cs.CV↗

arXiv2021

A Differential Testing Approach for Evaluating Abstract Syntax Tree Mapping Algorithms

Abstract syntax tree (AST) mapping algorithms are widely used to analyze changes in source code. Despite the foundational role of AST mapping algorithms, little effort has been made to evaluate the accuracy of AST mapping algorithms, i.e., the extent to which an algorihtm captures the evolution of code. We observe that a program element often has only one best-mapped program element. Based on this observation, we propose a hierarchical approach to automatically compare the similarity of mapped statements and tokens by different algorithms. By performing the comparison, we determine if each of the compared algorithms generates inaccurate mappings for a statement or its tokens. We invite 12 external experts to determine if three commonly used AST mapping algorithms generate accurate mappings for a statement and its tokens for 200 statements. Based on the experts' feedback,we observe that our approach achieves a precision of 0.98--1.00 and a recall of 0.65--0.75. Furthermore, we conduct a large-scale study with a dataset of ten Java projects, containing a total of 263,165 file revisions. Our approach determines that GumTree, MTDiff and IJM generate inaccurate mappings for 20%--29%, 25%--36% and 21%--30% of the file revisions, respectively. Our experimental results show that state-of-art AST mapping agorithms still need improvements.

cs.SE↗

arXiv2021

Improving Reinforcement Learning with Human Assistance: An Argument for Human Subject Studies with HIPPO Gym

Reinforcement learning (RL) is a popular machine learning paradigm for game playing, robotics control, and other sequential decision tasks. However, RL agents often have long learning times with high data requirements because they begin by acting randomly. In order to better learn in complex tasks, this article argues that an external teacher can often significantly help the RL agent learn. OpenAI Gym is a common framework for RL research, including a large number of standard environments and agents, making RL research significantly more accessible. This article introduces our new open-source RL framework, the Human Input Parsing Platform for Openai Gym (HIPPO Gym), and the design decisions that went into its creation. The goal of this platform is to facilitate human-RL research, again lowering the bar so that more researchers can quickly investigate different ways that human teachers could assist RL agents, including learning from demonstrations, learning from feedback, or curriculum learning.

cs.LG↗

arXiv2020

Rethinking Road Surface 3D Reconstruction and Pothole Detection: From Perspective Transformation to Disparity Map Segmentation

Potholes are one of the most common forms of road damage, which can severely affect driving comfort, road safety and vehicle condition. Pothole detection is typically performed by either structural engineers or certified inspectors. This task is, however, not only hazardous for the personnel but also extremely time-consuming. This paper presents an efficient pothole detection algorithm based on road disparity map estimation and segmentation. We first generalize the perspective transformation by incorporating the stereo rig roll angle. The road disparities are then estimated using semi-global matching. A disparity map transformation algorithm is then performed to better distinguish the damaged road areas. Finally, we utilize simple linear iterative clustering to group the transformed disparities into a collection of superpixels. The potholes are then detected by finding the superpixels, whose values are lower than an adaptively determined threshold. The proposed algorithm is implemented on an NVIDIA RTX 2080 Ti GPU in CUDA. The experiments demonstrate the accuracy and efficiency of our proposed road pothole detection algorithm, where an accuracy of 99.6% and an F-score of 89.4% are achieved.

cs.CV↗

arXiv2020

Observation of spin-momentum-layer locking in centrosymmetric BiOI

Spin polarization effects in nonmagnetic materials are generally believed as an outcome of spin-orbit coupling provided that the global inversion symmetry is lacking, also known as 'spin-momentum locking'. The recently discovered hidden spin polarization indicates that specific atomic site asymmetry could also induce measurable spin polarization, leading to a paradigm shift to centrosymmetric crystals for potential spintronic applications. Here, combining spin- and angle-resolved photoemission spectroscopy and theoretical calculations, we report distinct spin-layer locking phenomena surrounding different high-symmetry momenta in a centrosymmetric, layered material BiOI. The measured spin is highly polarized along the Brillouin zone boundary, while is almost vanishing around the zone center due to its nonsymmorphic crystal structure. Our work not only demonstrates the existence of hidden spin polarization, but also uncovers the microscopic mechanism of the way spin, momentum and layer locking to each other, shedding lights on the design metrics for future spintronic devices.

cond-mat.mtrl-sci↗

arXiv2020

Resilient Self/Event-Triggered Consensus Based on Ternary Control

The paper considers the problem of multi-agent consensus in the presence of adversarial agents which may try to prevent and introduce undesired influence on the coordination among the regular agents. To our setting, we extend the so-called mean subsequence reduced algorithms with the aim to reduce the amount of communication via two measures: The agents exchange information in the form of ternary data at each transmission and moreover keep the frequency of data exchange low by employing self- and event-triggered communication. We will observe that in hostile environments with adversaries, the self-triggered approach can bring certain advantages over the event-triggered counterpart.

eess.SY↗

arXiv2020

Revisiting the distance, environment and supernova properties of SNR G57.2+0.8 that hosts SGR 1935+2154

We have performed a multi-wavelength study of supernova remnant (SNR) G57.2+0.8 and its environment. The SNR hosts the magnetar SGR 1935+2154, which emitted an extremely bright ms-duration radio burst on 2020 Apr 28 (The Chime/Frb Collaboration et al. 2020; Bochenek et al. 2020). We used the 12CO and 13CO J=1-0 data from the Milky Way Image Scroll Painting (MWISP) CO line survey to search for molecular gas associated with G57.2+0.8, in order to constrain the physical parameters (e.g., the distance) of the SNR and its magnetar. We report that SNR G57.2+0.8 is likely impacting the molecular clouds (MCs) at the local standard of rest (LSR) velocity V_{LSR} ~ 30 km/s and excites a weak 1720 MHz OH maser with a peak flux density of 47 mJy/beam. The chance coincidence of a random OH spot falling in the SNR is <12%, and the OH-CO correspondence chance is 7% at the maser spot. This combines to give < 1% false probability of the OH maser, suggesting a real maser detection. The LSR velocity of the MCs places the SNR and magnetar at a kinematic distance of d=6.6 +/- 0.7 kpc. The nondetection of thermal X-ray emission from the SNR and the relatively dense environment suggests G57.2+0.8 be an evolved SNR with an age $t>1.6 \times 10^4$ (d/6.6 kpc) yr. The explosion energy of G57.2+0.8 is lower than $2 \times 10^{51}(n_0/10 cm^{-3})^{1.16} (d/~6.6 kpc)^{3.16}$ erg, which is not very energetic even assuming a high ambient density $n_0$ = 10 cm$^{-3}$. This reinforces the opinion that magnetars do not necessarily result from very energetic supernova explosions.

astro-ph.HE↗

arXiv2020

Leveraging an Efficient and Semantic Location Embedding to Seek New Ports of Bike Share Services

For short distance traveling in crowded urban areas, bike share services are becoming popular owing to the flexibility and convenience. To expand the service coverage, one of the key tasks is to seek new service ports, which requires to well understand the underlying features of the existing service ports. In this paper, we propose a new model, named for Efficient and Semantic Location Embedding (ESLE), which carries both geospatial and semantic information of the geo-locations. To generate ESLE, we first train a multi-label model with a deep Convolutional Neural Network (CNN) by feeding the static map-tile images and then extract location embedding vectors from the model. Compared to most recent relevant literature, ESLE is not only much cheaper in computation, but also easier to interpret via a systematic semantic analysis. Finally, we apply ESLE to seek new service ports for NTT DOCOMO's bike share services operated in Japan. The initial results demonstrate the effectiveness of ESLE, and provide a few insights that might be difficult to discover by using the conventional approaches.

cs.LG↗