Searcharxiv⌕ Search

arXiv subjects

Jian Sun

Publications and source records attributed to Jian Sun.

At least 451 records · Page 25Linked to original sources
arXiv2017

Large Kernel Matters -- Improve Semantic Segmentation by Global Convolutional Network

One of recent trends [30, 31, 14] in network architec- ture design is stacking small filters (e.g., 1x1 or 3x3) in the entire network because the stacked small filters is more ef- ficient than a large kernel, given the same computational complexity. However, in the field of semantic segmenta- tion, where we need to perform dense per-pixel prediction, we find that the large kernel (and effective receptive field) plays an important role when we have to perform the clas- sification and localization tasks simultaneously. Following our design principle, we propose a Global Convolutional Network to address both the classification and localization issues for the semantic segmentation. We also suggest a residual-based boundary refinement to further refine the ob- ject boundaries. Our approach achieves state-of-art perfor- mance on two public benchmarks and significantly outper- forms previous results, 82.2% (vs 80.2%) on PASCAL VOC 2012 dataset and 76.9% (vs 71.8%) on Cityscapes dataset.

cs.CV↗
arXiv2017

Event-Triggered Consensus for Linear Continuous-time Multi-agent Systems Based on a Predictor

In this paper, the problem of event-triggered consensus for linear continuous-time multi-agent systems is investigated. A new event-triggered consensus protocol based on a predictor is proposed to achieve consensus without continuous communication among agents. In the proposed consensus protocol, each agent only needs to monitor its states to determine its event-triggered instants. When an event is triggered, the agent will update its consensus protocol and sent its state information to its neighbors. In addition, the agent will also update its consensus protocol and the predictor when it receives the state information from its neighbors. A necessary and sufficient condition that the consensus problem can be solved is derived. Moreover, it is proved that Zeno behavior does not exist. Finally, a numerical example is given to illustrate that the protocol proposed in this paper can make the multi-agent systems achieve consensus through much fewer event-triggered times.

eess.SY↗
arXiv2017

Pressure-induced metallization and superconducting phase in ReS2

Among the family of TMDs, ReS2 takes a special position, which crystalizes in a unique distorted low-symmetry structure at ambient conditions. The interlayer interaction in ReS2 is rather weak, thus its bulk properties are similar to that of monolayer. However, how does compression change its structure and electronic properties is unknown so far. Here using ab initio crystal structure searching techniques, we explore the high-pressure phase transitions of ReS2 extensively and predict two new high-pressure phases. The ambient pressure phase transforms to a "distorted-1T" structure at very low pressure and then to a tetragonal I41/amd structure at around 90 GPa. The "distorted-1T" structure undergoes a semiconductor-metal transition (SMT) at around 70 GPa with a band overlap mechanism. Electron-phonon calculations suggest that the I41/amd structure is superconducting and has a critical superconducting temperature of about 2 K at 100 GPa. We further perform high-pressure electrical resistance measurements up to 102 GPa. Our experiments confirm the SMT and the superconducting phase transition of ReS2 under high pressure. These experimental results are in good agreement with our theoretical predictions.

cond-mat.mtrl-sci↗
arXiv2017

Deep Learning with Low Precision by Half-wave Gaussian Quantization

The problem of quantizing the activations of a deep neural network is considered. An examination of the popular binary quantization approach shows that this consists of approximating a classical non-linearity, the hyperbolic tangent, by two functions: a piecewise constant sign function, which is used in feedforward network computations, and a piecewise linear hard tanh function, used in the backpropagation step during network learning. The problem of approximating the ReLU non-linearity, widely used in the recent deep learning literature, is then considered. An half-wave Gaussian quantizer (HWGQ) is proposed for forward approximation and shown to have efficient implementation, by exploiting the statistics of of network activations and batch normalization operations commonly used in the literature. To overcome the problem of gradient mismatch, due to the use of different forward and backward approximations, several piece-wise backward approximators are then investigated. The implementation of the resulting quantized network, denoted as HWGQ-Net, is shown to achieve much closer performance to full precision networks, such as AlexNet, ResNet, GoogLeNet and VGG-Net, than previously available low-precision networks, with 1-bit binary weights and 2-bit quantized activations.

cs.CV↗
arXiv2017

Topological Dirac line nodes and superconductivity coexist in SnSe at high pressure

Due to fundamental interest and potential applications in quantum computation, tremendous efforts have been invested to study topological superconductivity. However, bulk topological superconductivity seems to be difficult to realize and its mechanism is still elusive. Several possible routes to induce topological superconductivity have been proposed, including proximity efforts, doping or pressurizing a topological insulator or semimetal. Among them, the pressurizing is considered to be a clean way to tune the electronic structures. Here we report the discovery of a pressure-induced topological and superconducting phase of SnSe, a material which is highly focused recently due to its superior thermoelectric properties. In situ high-pressure electrical transport and synchrotron X-ray diffraction measurements show that the superconductivity emerges along with the formation of a CsCl-type structural symmetry of SnSe above around 27 GPa, with a maximum critical temperature of 3.2 K at 39 GPa. Based on ab initio calculations, this CsCl-type SnSe is predicted to be a Dirac line nodes (DLN) semimetal in the absence of spin-orbit coupling, whose DLN states are protected by the coexistence of time-reversal and inversion symmetries. These results make CsCl-type SnSe an interesting model platform with simple crystal symmetry to study the interplay of topological physics and superconductivity.

cond-mat.mtrl-sci↗
arXiv2016

Superconductivity Induced by High Pressure in Weyl Semimetal TaP

Weyl semimetal defines a material with three dimensional Dirac cones which appear in pair due to the breaking of spatial inversion or time reversal symmetry. Superconductivity is the state of quantum condensation of paired electrons. Turning a Weyl semimetal into superconducting state is very important in having some unprecedented discoveries. In this work, by doing resistive measurements on a recently recognized Weyl semimetal TaP under pressure up to about 100 GPa, we observe superconductivity at about 70 GPa. The superconductivity retains when the pressure is released. The systematic evolutions of resistivity and magnetoresistance with pressure are well interpreted by the relative shift between the chemical potential and paired Weyl points. Calculations based on the density functional theory also illustrate the structure transition at about 70GPa, the phase at higher pressure may host superconductivity. Our discovery of superconductivity in TaP by pressure will stimulate further study on superconductivity in Weyl semimetals.

cond-mat.supr-con↗
arXiv2016

Ground state structure of polymeric carbon monoxide with high energy density

Crystal structure prediction methods and first-principles calculations have been used to explore low-energy structures of carbon monoxide (CO). Contrary to the standard wisdom, the most stable structure of CO at ambient pressure was found to be a polymeric structure of Pna21 symmetry rather than a molecular solid. This phase is formed from six-membered (4 Carbon + 2 Oxygen) rings connected by C=C double bonds with two double-bonded oxygen atoms attached to each ring. Interestingly, the polymeric Pna21 phase of CO has a much higher energy density than trinitrotoluene (TNT). On compression to about 7 GPa, Pna21 is found to transform into another chain-like phase of Cc symmetry which has similar ring units to Pna21. On compression to 100 GPa it is energetically favorable for CO to polymerize to form a single-bonded Cmcm phase from another structure of Cmca symmetry composed of units similar to those found in the single-bonded I212121 structure. Thermodynamic stability of these structures was verified using calculations with different density functionals, including hybrid and van der Waals corrected functionals.

cond-mat.mtrl-sci↗
arXiv2016

Object Detection Networks on Convolutional Feature Maps

Most object detectors contain two important components: a feature extractor and an object classifier. The feature extractor has rapidly evolved with significant research efforts leading to better deep convolutional architectures. The object classifier, however, has not received much attention and many recent systems (like SPPnet and Fast/Faster R-CNN) use simple multi-layer perceptrons. This paper demonstrates that carefully designing deep networks for object classification is just as important. We experiment with region-wise classifier networks that use shared, region-independent convolutional features. We call them "Networks on Convolutional feature maps" (NoCs). We discover that aside from deep feature maps, a deep and convolutional per-region classifier is of particular importance for object detection, whereas latest superior image classification models (such as ResNets and GoogLeNets) do not directly lead to good detection accuracy without using such a per-region classifier. We show by experiments that despite the effective ResNets and Faster R-CNN systems, the design of NoCs is an essential element for the 1st-place winning entries in ImageNet and MS COCO challenges 2015.

cs.CV↗
arXiv2016

Bed-Load Transport Rate Based on the Entrainment Probabilities of Sediment Grains by Rolling and Lifting

A function for the bed-load sediment transport rate is derived. This is achieved from the first principle by using the entrainment probabilities of the sediment grains by rolling and lifting, and by introducing two travel lengths, respectively, for the first time. The predictions from the new bed-load function agree well with the experimental results over the entire experimental range and show significant improvement over the commonly used formula for bed-load transport rate. The new function shows that, in terms of contributing to the bed-load transport rate, the total entrainment probability of the sediment grains is a weighted summation of those by the lifted and rolling grains, rather than a simple addition of the two. The function has also been used to predict the total entrainment probability, saltation length and the bed layer thickness at high bed-load transport rate. These predictions all agree well with the experimental results. It is found that, on average, the travel length for the rolling sand grains is about one order of magnitude less than that for the lifted ones.

physics.geo-ph↗
arXiv2016

Identity Mappings in Deep Residual Networks

Deep residual networks have emerged as a family of extremely deep architectures showing compelling accuracy and nice convergence behaviors. In this paper, we analyze the propagation formulations behind the residual building blocks, which suggest that the forward and backward signals can be directly propagated from one block to any other block, when using identity mappings as the skip connections and after-addition activation. A series of ablation experiments support the importance of these identity mappings. This motivates us to propose a new residual unit, which makes training easier and improves generalization. We report improved results using a 1001-layer ResNet on CIFAR-10 (4.62% error) and CIFAR-100, and a 200-layer ResNet on ImageNet. Code is available at: https://github.com/KaimingHe/resnet-1k-layers

cs.CV↗
arXiv2016

Supervised Transformer Network for Efficient Face Detection

Large pose variations remain to be a challenge that confronts real-word face detection. We propose a new cascaded Convolutional Neural Network, dubbed the name Supervised Transformer Network, to address this challenge. The first stage is a multi-task Region Proposal Network (RPN), which simultaneously predicts candidate face regions along with associated facial landmarks. The candidate regions are then warped by mapping the detected facial landmarks to their canonical positions to better normalize the face patterns. The second stage, which is a RCNN, then verifies if the warped candidate regions are valid faces or not. We conduct end-to-end learning of the cascaded network, including optimizing the canonical positions of the facial landmarks. This supervised learning of the transformations automatically selects the best scale to differentiate face/non-face patterns. By combining feature maps from both stages of the network, we achieve state-of-the-art detection accuracies on several public benchmarks. For real-time performance, we run the cascaded network only on regions of interests produced from a boosting cascade face detector. Our detector runs at 30 FPS on a single CPU core for a VGA-resolution image.

cs.CV↗
arXiv2016

Total Variation Regularized Tensor RPCA for Background Subtraction from Compressive Measurements

Background subtraction has been a fundamental and widely studied task in video analysis, with a wide range of applications in video surveillance, teleconferencing and 3D modeling. Recently, motivated by compressive imaging, background subtraction from compressive measurements (BSCM) is becoming an active research task in video surveillance. In this paper, we propose a novel tensor-based robust PCA (TenRPCA) approach for BSCM by decomposing video frames into backgrounds with spatial-temporal correlations and foregrounds with spatio-temporal continuity in a tensor framework. In this approach, we use 3D total variation (TV) to enhance the spatio-temporal continuity of foregrounds, and Tucker decomposition to model the spatio-temporal correlations of video background. Based on this idea, we design a basic tensor RPCA model over the video frames, dubbed as the holistic TenRPCA model (H-TenRPCA). To characterize the correlations among the groups of similar 3D patches of video background, we further design a patch-group-based tensor RPCA model (PG-TenRPCA) by joint tensor Tucker decompositions of 3D patch groups for modeling the video background. Efficient algorithms using alternating direction method of multipliers (ADMM) are developed to solve the proposed models. Extensive experiments on simulated and real-world videos demonstrate the superiority of the proposed approaches over the existing state-of-the-art approaches.

cs.CV↗
arXiv2016

Convergence of the Point Integral method for Poisson equation on point cloud

The Laplace-Beltrami operator (LBO) is a fundamental object associated to Riemannian manifolds, which encodes all intrinsic geometry of the manifolds and has many desirable properties. Recently, we proposed a novel numerical method, Point Integral method (PIM), to discretize the Laplace-Beltrami operator on point clouds \cite{LSS}. In this paper, we analyze the convergence of Point Integral method (PIM) for Poisson equation with Neumann boundary condition on submanifolds isometrically embedded in Euclidean spaces.

math.NA↗
arXiv2016

ScribbleSup: Scribble-Supervised Convolutional Networks for Semantic Segmentation

Large-scale data is of crucial importance for learning semantic segmentation models, but annotating per-pixel masks is a tedious and inefficient procedure. We note that for the topic of interactive image segmentation, scribbles are very widely used in academic research and commercial software, and are recognized as one of the most user-friendly ways of interacting. In this paper, we propose to use scribbles to annotate images, and develop an algorithm to train convolutional networks for semantic segmentation supervised by scribbles. Our algorithm is based on a graphical model that jointly propagates information from scribbles to unmarked pixels and learns network parameters. We present competitive object semantic segmentation results on the PASCAL VOC dataset by using scribbles as annotations. Scribbles are also favored for annotating stuff (e.g., water, sky, grass) that has no well-defined shape, and our method shows excellent results on the PASCAL-CONTEXT dataset thanks to extra inexpensive scribble annotations. Our scribble annotations on PASCAL VOC are available at http://research.microsoft.com/en-us/um/people/jifdai/downloads/scribble_sup

cs.CV↗
arXiv2016

Origin of the superconductivity of WTe2 under pressure

Tungsten ditelluride (WTe2) has attracted significant attention due to its interesting electronic properties, such as the unsaturated magnetoresistance and superconductivity. Recently, it has been proposed to be a new type of Weyl semimetal, which is distinguished from other transition metal dichalcogenides (TMDs) from a topological prospective. Here, we study the structure of WTe2 under pressure with a crystal structure prediction and ab initio calculations combined with high pressure synchrotron X-ray diffraction and Raman spectroscopy measurements. We find that the ambient orthorhombic structure (Td) transforms into a monoclinic structure (1T') at around 4-5 GPa. As the transition pressure is very close to the critical point in recent high-pressure electrical transport measurements, the emergence of superconductivity in WTe2 under pressure is attributed to the Td-1T' structure phase transition, which associates with a sliding mechanism of the TMD layers and results in a shorter Te-Te interlayer distance compared to the intralayer ones. These results highlight the critical role of the interlayer stacking and chalcogen interactions on the electronic and superconducting properties of multilayered TMDs under hydrostatic strain environments.

cond-mat.mtrl-sci↗
arXiv2016

Functional Brain Imaging: A Comprehensive Survey

Functional brain imaging allows measuring dynamic functionality in all brain regions. It is broadly used in clinical cognitive neuroscience as, well as in research. It will allow the observation of neural activities in the brain simultaneously. From the beginning when functional brain imaging was initiated by the mapping of brain functions proposed by phrenologists, many scientists were asking why we need to image brain functionality since we have already structural information. Simply, their important question was including a great answer. Functional information of the human brain would definitely complement structural information, helping to have a better understanding of what is happening in the brain. This paper, which could be useful to those who have an interest in functional brain imaging, such as engineers, will present a quick review of modalities used in functional brain imaging. We will concentrate on the most used techniques in functional imaging which are functional magnetic resonance imaging (fMRI) and functional optical imaging, which is one of novelties in this area of study.

physics.med-ph↗
arXiv2016

Rich Image Captioning in the Wild

We present an image caption system that addresses new challenges of automatically describing images in the wild. The challenges include high quality caption quality with respect to human judgments, out-of-domain data handling, and low latency required in many applications. Built on top of a state-of-the-art framework, we developed a deep vision model that detects a broad range of visual concepts, an entity recognition model that identifies celebrities and landmarks, and a confidence model for the caption output. Experimental results show that our caption engine outperforms previous state-of-the-art systems significantly on both in-domain dataset (i.e. MS COCO) and out of-domain datasets.

cs.CV↗