arXiv subjects

Quan Zhou

Publications and source records attributed to Quan Zhou.

At least 127 records · Page 7Linked to original sources

arXiv2021

FPB: Feature Pyramid Branch for Person Re-Identification

High performance person Re-Identification (Re-ID) requires the model to focus on both global silhouette and local details of pedestrian. To extract such more representative features, an effective way is to exploit deep models with multiple branches. However, most multi-branch based methods implemented by duplication of part backbone structure normally lead to severe increase of computational cost. In this paper, we propose a lightweight Feature Pyramid Branch (FPB) to extract features from different layers of networks and aggregate them in a bidirectional pyramid structure. Cooperated by attention modules and our proposed cross orthogonality regularization, FPB significantly prompts the performance of backbone network by only introducing less than 1.5M extra parameters. Extensive experimental results on standard benchmark datasets demonstrate that our proposed FPB based model outperforms state-of-the-art methods with obvious margin as well as much less model complexity. FPB borrows the idea of the Feature Pyramid Network (FPN) from prevailing object detection methods. To our best knowledge, it is the first successful application of similar structure in person Re-ID tasks, which empirically proves that pyramid network as affiliated branch could be a potential structure in related feature embedding models. The source code is publicly available at https://github.com/anocodetest1/FPB.git.

cs.CV↗

arXiv2021

Ferrofluidic Manipulator: Automatic Manipulation of Non-magnetic Microparticles at Air-Ferrofluid Interface

Manipulation of small-scale matter is a fundamental topic in micro- and nanorobotics. Numerous magnetic robotic systems have been developed for the manipulation of microparticles in an ambient environment, liquid as well as on the air-liquid interface. These systems move intrinsically magnetic or magnetically tagged objects by inducing a magnetic torque or force. However, most of the materials found in nature are non-magnetic. Here, we report a ferrofluidic manipulator for automatic two-dimensional manipulation of non-magnetic objects floating on top of a ferrofluid. The manipulation system employs eight centimeter-scale solenoids, which can move non-magnetic particles by deforming the air-ferrofluid interface. Using linear programming, we can control the motion of the non-magnetic particles with a predefined trajectory of a line, square, and circle with a precision of 25.1+/-19.5 um, 34.4+/-28.4 um and 33.4+/-26.6 um, respectively. The ferrofluidic manipulator is versatile with the materials and the shapes of the objects under manipulation. We have successfully manipulated particles made of polyethylene, polystyrene, a silicon chip, and poppy and sesame seeds. This work shows a promising venue for the manipulation of living and non-living matter at the air-liquid interface.

cs.RO↗

arXiv2021

Fiscal stimulus as an optimal control problem

During the Great Recession, Democrats in the United States argued that government spending could be utilized to "grease the wheels" of the economy in order to create wealth and to increase employment; Republicans, on the other hand, contended that government spending is wasteful and discouraged investment, thereby increasing unemployment. Today, in 2020, we find ourselves in the midst of another crisis where government spending and fiscal stimulus is again being considered as a solution. In the present paper, we address this question by formulating an optimal control problem generalizing the model of Radner & Shepp (1996). The model allows for the company to borrow continuously from the government. We prove that there exists an optimal strategy; rigorous verification proofs for its optimality are provided. We proceed to prove that government loans increase the expected net value of a company. We also examine the consequences of different profit-taking behaviors among firms who receive fiscal stimulus.

econ.GN↗

arXiv2021

The Sensitivity of Word Embeddings-based Author Detection Models to Semantic-preserving Adversarial Perturbations

Authorship analysis is an important subject in the field of natural language processing. It allows the detection of the most likely writer of articles, news, books, or messages. This technique has multiple uses in tasks related to authorship attribution, detection of plagiarism, style analysis, sources of misinformation, etc. The focus of this paper is to explore the limitations and sensitiveness of established approaches to adversarial manipulations of inputs. To this end, and using those established techniques, we first developed an experimental frame-work for author detection and input perturbations. Next, we experimentally evaluated the performance of the authorship detection model to a collection of semantic-preserving adversarial perturbations of input narratives. Finally, we compare and analyze the effects of different perturbation strategies, input and model configurations, and the effects of these on the author detection model.

cs.CL↗

arXiv2021

An Energy Sharing Mechanism Achieving the Same Flexibility as Centralized Dispatch

Deploying distributed renewable energy at the demand side is an important measure to implement a sustainable society. However, the massive small solar and wind generation units are beyond the control of a central operator. To encourage users to participate in energy management and reduce the dependence on dispatchable resources, a peer-to-peer energy sharing scheme is proposed which releases the flexibility at the demand side. Every user makes decision individually considering only local constraints; the microgrid operator announces the sharing prices subjective to the coupling constraints without knowing users' local constraints. This can help protect privacy. We prove that the proposed mechanism can achieve the same disutility and flexibility as centralized dispatch, and develop an effective modified best response based algorithm for reaching the market equilibrium. The concept of absorbable region is presented to measure the operating flexibility under the proposed energy sharing mechanism. A linear programming based polyhedral projection algorithm is developed to compute that region. Case studies validate the theoretical results and show that the proposed method is scalable.

math.OC↗

arXiv2021

Motion and trapping of micro- and millimeter-sized particles on the air-paramagnetic-liquid interface

Understanding the motion of particles on an air-liquid interface can impact a wide range of scientific fields and applications. Diamagnetic particles floating on an air-paramagnetic-liquid interface are previously known to have a repulsive motion from a magnet. Here, we show a motion mechanism where the diamagnetic particles floating on the air-paramagnetic-liquid interface are attracted and eventually trapped at an off-center distance from the magnet. The behavior of magnetic particles has been also studied and the motion mechanisms are theorized in a unified framework, revealing that the motion of particles on an air-paramagnetic-liquid interface is governed not only by magnetic energy, but as an interplay of the curvature of the interface deformation created by the nonuniform magnetic field, the gravitational potential, and the magnetic energy from the particle and the liquid. The attractive motion mechanism has been applied in directed self-assembly and robotic particle guiding.

physics.app-ph↗

arXiv2021

Tighter Bound Estimation of Sensitivity Analysis for Incremental and Decremental Data Modification

In large-scale classification problems, the data set always be faced with frequent updates when a part of the data is added to or removed from the original data set. In this case, conventional incremental learning, which updates an existing classifier by explicitly modeling the data modification, is more efficient than retraining a new classifier from scratch. However, sometimes, we are more interested in determining whether we should update the classifier or performing some sensitivity analysis tasks. To deal with these such tasks, we propose an algorithm to make rational inferences about the updated linear classifier without exactly updating the classifier. Specifically, the proposed algorithm can be used to estimate the upper and lower bounds of the updated classifier's coefficient matrix with a low computational complexity related to the size of the updated dataset. Both theoretical analysis and experiment results show that the proposed approach is superior to existing methods in terms of tightness of coefficients' bounds and computational complexity.

cs.LG↗

arXiv2021

Fairness in Forecasting and Learning Linear Dynamical Systems

In machine learning, training data often capture the behaviour of multiple subgroups of some underlying human population. When the amounts of training data for the subgroups are not controlled carefully, under-representation bias arises. We introduce two natural notions of subgroup fairness and instantaneous fairness to address such under-representation bias in time-series forecasting problems. In particular, we consider the subgroup-fair and instant-fair learning of a linear dynamical system (LDS) from multiple trajectories of varying lengths, and the associated forecasting problems. We provide globally convergent methods for the learning problems using hierarchies of convexifications of non-commutative polynomial optimisation problems. Our empirical results on a biased data set motivated by insurance applications and the well-known COMPAS data set demonstrate both the beneficial impact of fairness considerations on statistical performance and encouraging effects of exploiting sparsity on run time.

cs.LG↗

arXiv2020

Multi-level Chaotic Maps for 3D Textured Model Encryption

With rapid progress of Virtual Reality and Augmented Reality technologies, 3D contents are the next widespread media in many applications. Thus, the protection of 3D models is primarily important. Encryption of 3D models is essential to maintain confidentiality. Previous work on encryption of 3D surface model often consider the point clouds, the meshes and the textures individually. In this work, a multi-level chaotic maps models for 3D textured encryption was presented by observing the different contributions for recognizing cipher 3D models between vertices (point cloud), polygons and textures. For vertices which make main contribution for recognizing, we use high level 3D Lu chaotic map to encrypt them. For polygons and textures which make relatively smaller contributions for recognizing, we use 2D Arnold's cat map and 1D Logistic map to encrypt them, respectively. The experimental results show that our method can get similar performance with the other method use the same high level chaotic map for point cloud, polygons and textures, while we use less time. Besides, our method can resist more method of attacks such as statistic attack, brute-force attack, correlation attack.

cs.CV↗

arXiv2020

Where am I? SLAM for Mobile Machines on A Smart Working Site

The current optimization approaches of construction machinery are mainly based on internal sensors. However, the decision of a reasonable strategy is not only determined by its intrinsic signals, but also very strongly by environmental information, especially the terrain. Due to the dynamically changing of the construction site and the consequent absence of a high definition map, the Simultaneous Localization and Mapping (SLAM) offering the terrain information for construction machines is still challenging. Current SLAM technologies proposed for mobile machines are strongly dependent on costly or computationally expensive sensors, such as RTK GPS and cameras, so that commercial use is rare. In this study, we proposed an affordable SLAM method to create a multi-layer gird map for the construction site so that the machine can have the environmental information and be optimized accordingly. Concretely, after the machine passes by, we can get the local information and record it. Combining with positioning technology, we then create a map of the interesting places of the construction site. As a result of our research gathered from Gazebo, we showed that a suitable layout is the combination of 1 IMU and 2 differential GPS antennas using the unscented Kalman filter, which keeps the average distance error lower than 2m and the mapping error lower than 1.3% in the harsh environment. As an outlook, our SLAM technology provides the cornerstone to activate many efficiency improvement approaches.

cs.RO↗

arXiv2020

Reconfiguration of District Heating Network for Operational Flexibility Enhancement in Power System Unit Commitment

Massive adoptions of combined heat and power (CHP) units necessitate the coordinated operation of power system and district heating system (DHS). Exploiting the reconfigurable property of district heating networks (DHNs) provides a cost-effective solution to enhance the flexibility of the power system by redistributing heat loads in DHS. In this paper, a unit commitment considering combined electricity and reconfigurable heating network (UC-CERHN) is proposed to coordinate the day-ahead scheduling of power system and DHS. The DHS is formulated as a nonlinear and mixed-integer model with considering the reconfigurable DHN. Also, an auxiliary energy flow variable is introduced in the formed DHS model to make the commitment problem tractable, where the computational burdens are significantly reduced. Extensive case studies are presented to validate the effectiveness of the approximated model and illustrate the potential benefits of the proposed method with respect to congestion management and wind power accommodation. (Corresponding author:Hongbin Sun)

eess.SY↗

arXiv2020

Bridge the Domain Gap Between Ultra-wide-field and Traditional Fundus Images via Adversarial Domain Adaptation

For decades, advances in retinal imaging technology have enabled effective diagnosis and management of retinal disease using fundus cameras. Recently, ultra-wide-field (UWF) fundus imaging by Optos camera is gradually put into use because of its broader insights on fundus for some lesions that are not typically seen in traditional fundus images. Research on traditional fundus images is an active topic but studies on UWF fundus images are few. One of the most important reasons is that UWF fundus images are hard to obtain. In this paper, for the first time, we explore domain adaptation from the traditional fundus to UWF fundus images. We propose a flexible framework to bridge the domain gap between two domains and co-train a UWF fundus diagnosis model by pseudo-labelling and adversarial learning. We design a regularisation technique to regulate the domain adaptation. Also, we apply MixUp to overcome the over-fitting issue from incorrect generated pseudo-labels. Our experimental results on either single or both domains demonstrate that the proposed method can well adapt and transfer the knowledge from traditional fundus images to UWF fundus images and improve the performance of retinal disease recognition.

eess.IV↗

arXiv2020

BiCANet: Bi-directional Contextual Aggregating Network for Image Semantic Segmentation

Exploring contextual information in convolution neural networks (CNNs) has gained substantial attention in recent years for semantic segmentation. This paper introduces a Bi-directional Contextual Aggregating Network, called BiCANet, for semantic segmentation. Unlike previous approaches that encode context in feature space, BiCANet aggregates contextual cues from a categorical perspective, which is mainly consist of three parts: contextual condensed projection block (CCPB), bi-directional context interaction block (BCIB), and muti-scale contextual fusion block (MCFB). More specifically, CCPB learns a category-based mapping through a split-transform-merge architecture, which condenses contextual cues with different receptive fields from intermediate layer. BCIB, on the other hand, employs dense skipped-connections to enhance the class-level context exchanging. Finally, MCFB integrates multi-scale contextual cues by investigating short- and long-ranged spatial dependencies. To evaluate BiCANet, we have conducted extensive experiments on three semantic segmentation datasets: PASCAL VOC 2012, Cityscapes, and ADE20K. The experimental results demonstrate that BiCANet outperforms recent state-of-the-art networks without any postprocess techniques. Particularly, BiCANet achieves the mIoU score of 86.7%, 82.4% and 38.66% on PASCAL VOC 2012, Cityscapes and ADE20K testset, respectively.

cs.CV↗

arXiv2020

Entropy Minimization vs. Diversity Maximization for Domain Adaptation

Entropy minimization has been widely used in unsupervised domain adaptation (UDA). However, existing works reveal that entropy minimization only may result into collapsed trivial solutions. In this paper, we propose to avoid trivial solutions by further introducing diversity maximization. In order to achieve the possible minimum target risk for UDA, we show that diversity maximization should be elaborately balanced with entropy minimization, the degree of which can be finely controlled with the use of deep embedded validation in an unsupervised manner. The proposed minimal-entropy diversity maximization (MEDM) can be directly implemented by stochastic gradient descent without use of adversarial learning. Empirical evidence demonstrates that MEDM outperforms the state-of-the-art methods on four popular domain adaptation datasets.

cs.LG↗

arXiv2019

FDDWNet: A Lightweight Convolutional Neural Network for Real-time Sementic Segmentation

This paper introduces a lightweight convolutional neural network, called FDDWNet, for real-time accurate semantic segmentation. In contrast to recent advances of lightweight networks that prefer to utilize shallow structure, FDDWNet makes an effort to design more deeper network architecture, while maintains faster inference speed and higher segmentation accuracy. Our network uses factorized dilated depth-wise separable convolutions (FDDWC) to learn feature representations from different scale receptive fields with fewer model parameters. Additionally, FDDWNet has multiple branches of skipped connections to gather context cues from intermediate convolution layers. The experiments show that FDDWNet only has 0.8M model size, while achieves 60 FPS running speed on a single RTX 2080Ti GPU with a 1024x512 input image. The comprehensive experiments demonstrate that our model achieves state-of-the-art results in terms of available speed and accuracy trade-off on CityScapes and CamVid datasets.

cs.CV↗

arXiv2019

A hypothesis-testing perspective on the G-normal distribution theory

The G-normal distribution was introduced by Peng [2007] as the limiting distribution in the central limit theorem for sublinear expectation spaces. Equivalently, it can be interpreted as the solution to a stochastic control problem where we have a sequence of random variables, whose variances can be chosen based on all past information. In this note we study the tail behavior of the G-normal distribution through analyzing a nonlinear heat equation. Asymptotic results are provided so that the tail "probabilities" can be easily evaluated with high accuracy. This study also has a significant impact on the hypothesis testing theory for heteroscedastic data; we show that even if the data are generated under the null hypothesis, it is possible to cheat and attain statistical significance by sequentially manipulating the error variances of the observations.

math.ST↗

arXiv2019

ESNet: An Efficient Symmetric Network for Real-time Semantic Segmentation

The recent years have witnessed great advances for semantic segmentation using deep convolutional neural networks (DCNNs). However, a large number of convolutional layers and feature channels lead to semantic segmentation as a computationally heavy task, which is disadvantage to the scenario with limited resources. In this paper, we design an efficient symmetric network, called (ESNet), to address this problem. The whole network has nearly symmetric architecture, which is mainly composed of a series of factorized convolution unit (FCU) and its parallel counterparts (PFCU). On one hand, the FCU adopts a widely-used 1D factorized convolution in residual layers. On the other hand, the parallel version employs a transform-split-transform-merge strategy in the designment of residual module, where the split branch adopts dilated convolutions with different rate to enlarge receptive field. Our model has nearly 1.6M parameters, and is able to be performed over 62 FPS on a single GTX 1080Ti GPU. The experiments demonstrate that our approach achieves state-of-the-art results in terms of speed and accuracy trade-off for real-time semantic segmentation on CityScapes dataset.

cs.CV↗

arXiv2019

LEDNet: A Lightweight Encoder-Decoder Network for Real-Time Semantic Segmentation

The extensive computational burden limits the usage of CNNs in mobile devices for dense estimation tasks. In this paper, we present a lightweight network to address this problem,namely LEDNet, which employs an asymmetric encoder-decoder architecture for the task of real-time semantic segmentation.More specifically, the encoder adopts a ResNet as backbone network, where two new operations, channel split and shuffle, are utilized in each residual block to greatly reduce computation cost while maintaining higher segmentation accuracy. On the other hand, an attention pyramid network (APN) is employed in the decoder to further lighten the entire network complexity. Our model has less than 1M parameters,and is able to run at over 71 FPS in a single GTX 1080Ti GPU. The comprehensive experiments demonstrate that our approach achieves state-of-the-art results in terms of speed and accuracy trade-off on CityScapes dataset.

cs.CV↗