arXiv subjects

Jian Sun

Publications and source records attributed to Jian Sun.

At least 379 records · Page 21Linked to original sources

arXiv2020

Attentive Normalization for Conditional Image Generation

Traditional convolution-based generative adversarial networks synthesize images based on hierarchical local operations, where long-range dependency relation is implicitly modeled with a Markov chain. It is still not sufficient for categories with complicated structures. In this paper, we characterize long-range dependence with attentive normalization (AN), which is an extension to traditional instance normalization. Specifically, the input feature map is softly divided into several regions based on its internal semantic similarity, which are respectively normalized. It enhances consistency between distant regions with semantic correspondence. Compared with self-attention GAN, our attentive normalization does not need to measure the correlation of all locations, and thus can be directly applied to large-size feature maps without much computational burden. Extensive experiments on class-conditional image generation and semantic inpainting verify the efficacy of our proposed module.

cs.CV↗

arXiv2020

High-Order Information Matters: Learning Relation and Topology for Occluded Person Re-Identification

Occluded person re-identification (ReID) aims to match occluded person images to holistic ones across dis-joint cameras. In this paper, we propose a novel framework by learning high-order relation and topology information for discriminative features and robust alignment. At first, we use a CNN backbone and a key-points estimation model to extract semantic local features. Even so, occluded images still suffer from occlusion and outliers. Then, we view the local features of an image as nodes of a graph and propose an adaptive direction graph convolutional (ADGC)layer to pass relation information between nodes. The proposed ADGC layer can automatically suppress the message-passing of meaningless features by dynamically learning di-rection and degree of linkage. When aligning two groups of local features from two images, we view it as a graph matching problem and propose a cross-graph embedded-alignment (CGEA) layer to jointly learn and embed topology information to local features, and straightly predict similarity score. The proposed CGEA layer not only take full use of alignment learned by graph matching but also re-place sensitive one-to-one matching with a robust soft one. Finally, extensive experiments on occluded, partial, and holistic ReID tasks show the effectiveness of our proposed method. Specifically, our framework significantly outperforms state-of-the-art by6.5%mAP scores on Occluded-Duke dataset.

cs.CV↗

arXiv2020

Learning Human-Object Interaction Detection using Interaction Points

Understanding interactions between humans and objects is one of the fundamental problems in visual classification and an essential step towards detailed scene understanding. Human-object interaction (HOI) detection strives to localize both the human and an object as well as the identification of complex interactions between them. Most existing HOI detection approaches are instance-centric where interactions between all possible human-object pairs are predicted based on appearance features and coarse spatial information. We argue that appearance features alone are insufficient to capture complex human-object interactions. In this paper, we therefore propose a novel fully-convolutional approach that directly detects the interactions between human-object pairs. Our network predicts interaction points, which directly localize and classify the inter-action. Paired with the densely predicted interaction vectors, the interactions are associated with human and object detections to obtain final predictions. To the best of our knowledge, we are the first to propose an approach where HOI detection is posed as a keypoint detection and grouping problem. Experiments are performed on two popular benchmarks: V-COCO and HICO-DET. Our approach sets a new state-of-the-art on both datasets. Code is available at https://github.com/vaesl/IP-Net.

cs.CV↗

arXiv2020

PVN3D: A Deep Point-wise 3D Keypoints Voting Network for 6DoF Pose Estimation

In this work, we present a novel data-driven method for robust 6DoF object pose estimation from a single RGBD image. Unlike previous methods that directly regressing pose parameters, we tackle this challenging task with a keypoint-based approach. Specifically, we propose a deep Hough voting network to detect 3D keypoints of objects and then estimate the 6D pose parameters within a least-squares fitting manner. Our method is a natural extension of 2D-keypoint approaches that successfully work on RGB based 6DoF estimation. It allows us to fully utilize the geometric constraint of rigid objects with the extra depth information and is easy for a network to learn and optimize. Extensive experiments were conducted to demonstrate the effectiveness of 3D-keypoint detection in the 6D pose estimation task. Experimental results also show our method outperforms the state-of-the-art methods by large margins on several benchmarks. Code and video are available at https://github.com/ethnhe/PVN3D.git.

cs.CV↗

arXiv2020

Learning Dynamic Routing for Semantic Segmentation

Recently, numerous handcrafted and searched networks have been applied for semantic segmentation. However, previous works intend to handle inputs with various scales in pre-defined static architectures, such as FCN, U-Net, and DeepLab series. This paper studies a conceptually new method to alleviate the scale variance in semantic representation, named dynamic routing. The proposed framework generates data-dependent routes, adapting to the scale distribution of each image. To this end, a differentiable gating function, called soft conditional gate, is proposed to select scale transform paths on the fly. In addition, the computational cost can be further reduced in an end-to-end manner by giving budget constraints to the gating function. We further relax the network level routing space to support multi-path propagations and skip-connections in each forward, bringing substantial network capacity. To demonstrate the superiority of the dynamic property, we compare with several static architectures, which can be modeled as special cases in the routing space. Extensive experiments are conducted on Cityscapes and PASCAL VOC 2012 to illustrate the effectiveness of the dynamic framework. Code is available at https://github.com/yanwei-li/DynamicRouting.

cs.CV↗

arXiv2020

Method for Extracting Patterns of Coordinated Network Attacks on Electric Power CPS based on Temporal-Topological Correlation

In the analysis of coordinated network attacks on electric power cyber-physical system (CPS), it is difficult to restore the complete attack path, and the intent of the attack cannot be identified automatically. A method is therefore proposed for the extracting patterns of coordinated network attacks on electric power CPS based on temporal-topological correlation. First, the attack events are aggregated according to the alarm log of the cyber space, and a temporal-causal Bayesian network-based cyber attack recognition algorithm is proposed to parse out the cyber attack sequences of the same attacker. Then, according to the characteristic curves of different attack measurement data in physical space, a combination of physical attack event criteria algorithm is designed to distinguish the types of physical attack events. Finally, physical attack events and cyber attack sequences are matched via temporal-topological correlation, frequent patterns of attack sequences are extracted, and hidden multi-step attack patterns are found from scattered grid measurement data and information from alarm logs. The effectiveness and efficiency of the proposed method are verified by the testbed at Mississippi State University.

cs.CR↗

arXiv2020

A Big Data Enabled Channel Model for 5G Wireless Communication Systems

The standardization process of the fifth generation (5G) wireless communications has recently been accelerated and the first commercial 5G services would be provided as early as in 2018. The increasing of enormous smartphones, new complex scenarios, large frequency bands, massive antenna elements, and dense small cells will generate big datasets and bring 5G communications to the era of big data. This paper investigates various applications of big data analytics, especially machine learning algorithms in wireless communications and channel modeling. We propose a big data and machine learning enabled wireless channel model framework. The proposed channel model is based on artificial neural networks (ANNs), including feed-forward neural network (FNN) and radial basis function neural network (RBF-NN). The input parameters are transmitter (Tx) and receiver (Rx) coordinates, Tx-Rx distance, and carrier frequency, while the output parameters are channel statistical properties, including the received power, root mean square (RMS) delay spread (DS), and RMS angle spreads (ASs). Datasets used to train and test the ANNs are collected from both real channel measurements and a geometry based stochastic model (GBSM). Simulation results show good performance and indicate that machine learning algorithms can be powerful analytical tools for future measurement-based wireless channel modeling.

eess.SP↗

arXiv2020

Market Power in Convex Hull Pricing

The start up costs in many kinds of generators lead to complex cost structures, which in turn yield severe market loopholes in the locational marginal price (LMP) scheme. Convex hull pricing (a.k.a. extended LMP) is proposed to improve the market efficiency by providing the minimal uplift payment to the generators. In this letter, we consider a stylized model where all generators share the same generation capacity. We analyze the generators' possible strategic behaviors in such a setting, and then propose an index for market power quantification in the convex hull pricing schemes.

math.OC↗

arXiv2020

Designing transformation-induced plasticity and twinning-induced plasticity Cr-Co-Ni medium entropy alloys: theory and experiment

In order to efficiently explore the nearly infinite composition space in multicomponent solid solution alloys, it is important to establish predictive design strategies and use computation-aided methods. In the present work, we demonstrated the density functional theory calculations informed design routes for realizing transformation-induced plasticity (TRIP) and twinning-induced plasticity (TWIP) in Cr-Co-Ni medium entropy alloys (MEAs). We systematically studied the effects of magnetism and chemical composition on the generalized stacking fault energy surface (gamma-surface) and showed that both chemistry and the coupled magnetic state strongly affect the gamma-surface, consequently, the primary deformation modes. Based on the calculated effective energy barriers for the competing deformation modes, we constructed composition and magnetism dependent deformation maps at both room and cryogenic temperatures. Accordingly, we proposed various design routes for achieving desired primary deformation modes in the ternary Cr-Co-Ni alloys. The deformation mechanisms predicted by our theoretical models are in nice agreement with available experimental observations in literature. Furthermore, we fabricated two non-equiatomic Cr-Co-Ni MEAs possessing the designed TWIP and TRIP effects, showing excellent combinations of tensile strength and ductility.

cond-mat.mtrl-sci↗

arXiv2020

Isotropic All-electric Spin analyzer based on a quantum ring with spin-orbit coupling

Here we propose an isotropic all electrical spin analyzer in a quantum ring with spin-orbit coupling by analytically and numerically modeling how the charge transmission rates depend on the polarization of the incident spin. The formalism of spin transmission and polarization rates in an arbitrary direction is also developed by analyzing the Aharonov-Bohm and the Aharonov-Casher effects. The topological spin texture induced by the spin-orbit couplings essentially contributes to the dynamic phase and plays an important role in spin transport. The spin transport features derived analytically has been confirmed numerically. This interesting two-dimensional electron system can be designed as a spin filter, spin polarizer and general analyzer by simply tuning the spin-orbit couplings, which paves the way for realizing the tunable and integrable spintronics device.

cond-mat.mes-hall↗

arXiv2020

Dimensionalities and multiplicities determination of crystal nets

Low-dimensional materials have attracted significant attentions over the past decade. To discover new low-dimensional materials, high-throughout screening methods have been applied in different materials databases. For this purpose, the reliability of dimensionality identification is therefore highly important. In this work, we find that the existence of self-penetrating nets may lead to incorrect results by previous methods. In stead of this, we use the quotient graph to analysis the topologies of structures and compute their dimensionalities. Based on the quotient graph, we can calculate not only the dimensionality but also the multiplicity of self-penetrating structures. As a demonstration, we screened the Crystallography Open Database using our method and found hundreds of structures with different dimensionalities and high multiplicities up to eleven.

cond-mat.mtrl-sci↗

arXiv2019

DetNAS: Backbone Search for Object Detection

Object detectors are usually equipped with backbone networks designed for image classification. It might be sub-optimal because of the gap between the tasks of image classification and object detection. In this work, we present DetNAS to use Neural Architecture Search (NAS) for the design of better backbones for object detection. It is non-trivial because detection training typically needs ImageNet pre-training while NAS systems require accuracies on the target detection task as supervisory signals. Based on the technique of one-shot supernet, which contains all possible networks in the search space, we propose a framework for backbone search on object detection. We train the supernet under the typical detector training schedule: ImageNet pre-training and detection fine-tuning. Then, the architecture search is performed on the trained supernet, using the detection task as the guidance. This framework makes NAS on backbones very efficient. In experiments, we show the effectiveness of DetNAS on various detectors, for instance, one-stage RetinaNet and the two-stage FPN. We empirically find that networks searched on object detection shows consistent superiority compared to those searched on ImageNet classification. The resulting architecture achieves superior performance than hand-crafted networks on COCO with much less FLOPs complexity.

cs.CV↗

arXiv2019

Storage Control for Carbon Emission Reduction: Opportunities and Challenges

Storage is vital to power systems as it provides the urgently needed flexibility to the system. Meanwhile, it can contribute more than flexibility. In this paper, we study the possibility of utilizing storage system for carbon emission reduction. The opportunity arises due to the pending implementation of carbon tax throughout the world. Without the right incentive, most system operators have to dispatch the generators according to the merit order of the fuel costs, without any control for carbon emissions. However, we submit that storage may provide necessary flexibility in carbon emission reduction even without carbon tax. We identify the non-convex structure to conduct storage control for this task and propose an easy to implement dynamic programming algorithm to investigate the value of storage in carbon emission reduction.

eess.SY↗

arXiv2019

Two-Timescale Voltage Control in Distribution Grids Using Deep Reinforcement Learning

Modern distribution grids are currently being challenged by frequent and sizable voltage fluctuations, due mainly to the increasing deployment of electric vehicles and renewable generators. Existing approaches to maintaining bus voltage magnitudes within the desired region can cope with either traditional utility-owned devices (e.g., shunt capacitors), or contemporary smart inverters that come with distributed generation units (e.g., photovoltaic plants). The discrete on-off commitment of capacitor units is often configured on an hourly or daily basis, yet smart inverters can be controlled within milliseconds, thus challenging joint control of these two types of assets. In this context, a novel two-timescale voltage regulation scheme is developed for distribution grids by judiciously coupling data-driven with physicsbased optimization. On a faster timescale, say every second, the optimal setpoints of smart inverters are obtained by minimizing instantaneous bus voltage deviations from their nominal values, based on either the exact alternating current power flow model or a linear approximant of it; whereas, on the slower timescale (e.g., every hour), shunt capacitors are configured to minimize the longterm discounted voltage deviations using a deep reinforcement learning algorithm. Extensive numerical tests on a real-world 47- bus distribution network as well as the IEEE 123-bus test feeder using real data corroborate the effectiveness of the novel scheme.

eess.SY↗

arXiv2019

Conductor Galloping Prediction on Imbalanced Datasets: SVM with Smart Sampling

Conductor galloping is the high-amplitude, low-frequency oscillation of overhead power lines due to wind. Such movements may lead to severe damages to transmission lines, and hence pose significant risks to the power system operation. In this paper, we target to design a prediction framework for conductor galloping. The difficulty comes from imbalanced dataset as galloping happens rarely. By examining the impacts of data balance and data volume on the prediction performance, we propose to employ proper sample adjustment methods to achieve better performance. Numerical study suggests that using only three features, together with over sampling, the SVM based prediction framework achieves an F_1-score of 98.9%.

eess.SP↗

arXiv2019

Correlations in the chain melting of host-guest Calcium

In this paper, we study chain melting state in the commensurate host-guest structure of calcium. We trained a NN (neural network) force field with DeepMD-kit, and by implementing classical simulations, we found that the convergence of z-proejcted MSD of guest atoms needs at least 8192-atom supercell. We ascribe the origination of chain melting to the phase transition at 600 K, in which the arrangement of guest chains transform from a checkerboard pattern to a stripe pattern, and the energy barrier of sliding chains against each other is obviously reduced. We also found that the chain melting state of calcium could be separated into two 2D (two-dimensional) and 3D (three-dimensional) disorder, with distinct chain dynamics.

cond-mat.mtrl-sci↗

arXiv2019

A Statistical Learning Approach to Reactive Power Control in Distribution Systems

Pronounced variability due to the growth of renewable energy sources, flexible loads, and distributed generation is challenging residential distribution systems. This context, motivates well fast, efficient, and robust reactive power control. Real-time optimal reactive power control is possible in theory by solving a non-convex optimization problem based on the exact model of distribution flow. However, lack of high-precision instrumentation and reliable communications, as well as the heavy computational burden of non-convex optimization solvers render computing and implementing the optimal control challenging in practice. Taking a statistical learning viewpoint, the input-output relationship between each grid state and the corresponding optimal reactive power control is parameterized in the present work by a deep neural network, whose unknown weights are learned offline by minimizing the power loss over a number of historical and simulated training pairs. In the inference phase, one just feeds the real-time state vector into the learned neural network to obtain the `optimal' reactive power control with only several matrix-vector multiplications. The merits of this novel statistical learning approach are computational efficiency as well as robustness to random input perturbations. Numerical tests on a 47-bus distribution network using real data corroborate these practical merits.

eess.SY↗

arXiv2019

Induction Networks for Few-Shot Text Classification

Text classification tends to struggle when data is deficient or when it needs to adapt to unseen classes. In such challenging scenarios, recent studies have used meta-learning to simulate the few-shot task, in which new queries are compared to a small support set at the sample-wise level. However, this sample-wise comparison may be severely disturbed by the various expressions in the same class. Therefore, we should be able to learn a general representation of each class in the support set and then compare it to new queries. In this paper, we propose a novel Induction Network to learn such a generalized class-wise representation, by innovatively leveraging the dynamic routing algorithm in meta-learning. In this way, we find the model is able to induce and generalize better. We evaluate the proposed model on a well-studied sentiment classification dataset (English) and a real-world dialogue intent classification dataset (Chinese). Experiment results show that on both datasets, the proposed model significantly outperforms the existing state-of-the-art approaches, proving the effectiveness of class-wise generalization in few-shot text classification.

cs.CL↗