arXiv subjects

Chang Xu

Publications and source records attributed to Chang Xu.

At least 397 records · Page 22Linked to original sources

arXiv2018

Discriminative multi-view Privileged Information learning for image re-ranking

Conventional multi-view re-ranking methods usually perform asymmetrical matching between the region of interest (ROI) in the query image and the whole target image for similarity computation. Due to the inconsistency in the visual appearance, this practice tends to degrade the retrieval accuracy particularly when the image ROI, which is usually interpreted as the image objectness, accounts for a smaller region in the image. Since Privileged Information (PI), which can be viewed as the image prior, enables well characterizing the image objectness, we are aiming at leveraging PI for further improving the performance of the multi-view re-ranking accuracy in this paper. Towards this end, we propose a discriminative multi-view re-ranking approach in which both the original global image visual contents and the local auxiliary PI features are simultaneously integrated into a unified training framework for generating the latent subspaces with sufficient discriminating power. For the on-the-fly re-ranking, since the multi-view PI features are unavailable, we only project the original multi-view image representations onto the latent subspace, and thus the re-ranking can be achieved by computing and sorting the distances from the multi-view embeddings to the separating hyperplane. Extensive experimental evaluations on the two public benchmarks Oxford5k and Paris6k reveal our approach provides further performance boost for accurate image re-ranking, whilst the comparative study demonstrates the advantage of our method against other multi-view re-ranking methods.

cs.CV↗

arXiv2018

Cross-Target Stance Classification with Self-Attention Networks

In stance classification, the target on which the stance is made defines the boundary of the task, and a classifier is usually trained for prediction on the same target. In this work, we explore the potential for generalizing classifiers between different targets, and propose a neural model that can apply what has been learned from a source target to a destination target. We show that our model can find useful information shared between relevant targets which improves generalization in certain scenarios.

cs.CL↗

arXiv2018

CoMID: Context-based Multi-Invariant Detection for Monitoring Cyber-Physical Software

Cyber-physical software continually interacts with its physical environment for adaptation in order to deliver smart services. However, the interactions can be subject to various errors when the software's assumption on its environment no longer holds, thus leading to unexpected misbehavior or even failure. To address this problem, one promising way is to conduct runtime monitoring of invariants, so as to prevent cyber-physical software from entering such errors (a.k.a. abnormal states). To effectively detect abnormal states, we in this article present an approach, named Context-based Multi-Invariant Detection (CoMID), which consists of two techniques: context-based trace grouping and multi-invariant detection. The former infers contexts to distinguish different effective scopes for CoMID's derived invariants, and the latter conducts ensemble evaluation of multiple invariants to detect abnormal states. We experimentally evaluate CoMID on real-world cyber-physical software. The results show that CoMID achieves a 5.7-28.2% higher true-positive rate and a 6.8-37.6% lower false-positive rate in detecting abnormal states, as compared with state-of-the-art approaches (i.e., Daikon and ZoomIn). When deployed in field tests, CoMID's runtime monitoring improves the success rate of cyber-physical software in its task executions by 15.3-31.7%.

cs.SE↗

arXiv2018

Graph Edge Convolutional Neural Networks for Skeleton Based Action Recognition

This paper investigates body bones from skeleton data for skeleton based action recognition. Body joints, as the direct result of mature pose estimation technologies, are always the key concerns of traditional action recognition methods. However, instead of joints, we humans naturally identify how the human body moves according to shapes, lengths and places of bones, which are more obvious and stable for observation. Hence given graphs generated from skeleton data, we propose to develop convolutions over graph edges that correspond to bones in human skeleton. We describe an edge by integrating its spatial neighboring edges to explore the cooperation between different bones, as well as its temporal neighboring edges to address the consistency of movements in an action. A graph edge convolutional neural network is then designed for skeleton based action recognition. Considering the complementarity between graph node convolution and graph edge convolution, we additionally construct two hybrid neural networks to combine graph node convolutional neural network and graph edge convolutional neural network using shared intermediate layers. Experimental results on Kinetics and NTU-RGB+D datasets demonstrate that our graph edge convolution is effective to capture characteristic of actions and our graph edge convolutional neural network significantly outperforms existing state-of-art skeleton based action recognition methods. Additionally, more performance improvements can be achieved by the hybrid networks.

cs.CV↗

arXiv2018

PPLS: A Privacy-Preserving Location-Sharing Scheme in Vehicular Social Networks

Recent advances in Socially Aware Networks (SANs) have allowed its use in many domains, out of which social Internet of vehicles (SIOV) is of prime importance. SANs can provide a promising routing and forwarding paradigm for SIOV by using interest-based communication. Though able to improve the forwarding performance, existing interest-based schemes fail to consider the important issue of protecting users' interest information. In this paper, we propose a PRivacy-preserving Interest-based Forwarding scheme (PRIF) for SIOV, which not only protects the interest information, but also improves the forwarding performance. We propose a privacy-preserving authentication protocol to recognize communities among mobile nodes. During data routing and forwarding, a node can know others' interests only if they are affiliated with the same community. Moreover, to improve forwarding performance, a new metric {\em community energy} is introduced to indicate vehicular social proximity. Community energy is generated when two nodes encounter one another and information is shared among them. PRIF considers this energy metric to select forwarders towards the destination node or the destination community. Security analysis indicates PRIF can protect nodes' interest information. In addition, extensive simulations have been conducted to demonstrate that PRIF outperforms the existing algorithms including the BEEINFO, Epidemic, and PRoPHET.

cs.CR↗

arXiv2018

PRIF: A Privacy-Preserving Interest-Based Forwarding Scheme for Social Internet of Vehicles

cs.CR↗

arXiv2018

LPTD: Achieving Lightweight and Privacy-Preserving Truth Discovery in CIoT

In recent years, cognitive Internet of Things (CIoT) has received considerable attention because it can extract valuable information from various Internet of Things (IoT) devices. In CIoT, truth discovery plays an important role in identifying truthful values from large scale data to help CIoT provide deeper insights and value from collected information. However, the privacy concerns of IoT devices pose a major challenge in designing truth discovery approaches. Although existing schemes of truth discovery can be executed with strong privacy guarantees, they are not efficient or cannot be applied in real-life CIoT applications. This article proposes a novel framework for lightweight and privacy-preserving truth discovery called LPTD-I, which is implemented by incorporating fog and cloud platforms, and adopting the homomorphic Paillier encryption and one-way hash chain techniques. This scheme not only protects devices' privacy, but also achieves high efficiency. Moreover, we introduce a fault tolerant (LPTD-II) framework which can effectively overcome malfunctioning CIoT devices. Detailed security analysis indicates the proposed schemes are secure under a comprehensively designed threat model. Experimental simulations are also carried out to demonstrate the efficiency of the proposed schemes.

cs.CR↗

arXiv2018

Attention-GAN for Object Transfiguration in Wild Images

This paper studies the object transfiguration problem in wild images. The generative network in classical GANs for object transfiguration often undertakes a dual responsibility: to detect the objects of interests and to convert the object from source domain to target domain. In contrast, we decompose the generative network into two separat networks, each of which is only dedicated to one particular sub-task. The attention network predicts spatial attention maps of images, and the transformation network focuses on translating objects. Attention maps produced by attention network are encouraged to be sparse, so that major attention can be paid to objects of interests. No matter before or after object transfiguration, attention maps should remain constant. In addition, learning attention network can receive more instructions, given the available segmentation annotations of images. Experimental results demonstrate the necessity of investigating attention in object transfiguration, and that the proposed algorithm can learn accurate attention to improve quality of generated images.

cs.CV↗

arXiv2018

Evolutionary Generative Adversarial Networks

Generative adversarial networks (GAN) have been effective for learning generative models for real-world data. However, existing GANs (GAN and its variants) tend to suffer from training problems such as instability and mode collapse. In this paper, we propose a novel GAN framework called evolutionary generative adversarial networks (E-GAN) for stable GAN training and improved generative performance. Unlike existing GANs, which employ a pre-defined adversarial objective function alternately training a generator and a discriminator, we utilize different adversarial training objectives as mutation operations and evolve a population of generators to adapt to the environment (i.e., the discriminator). We also utilize an evaluation mechanism to measure the quality and diversity of generated samples, such that only well-performing generator(s) are preserved and used for further training. In this way, E-GAN overcomes the limitations of an individual adversarial training objective and always preserves the best offspring, contributing to progress in and the success of GANs. Experiments on several datasets demonstrate that E-GAN achieves convincing generative performance and reduces the training problems inherent in existing GANs.

cs.LG↗

arXiv2018

Quantum Zeno dynamics of a matter-wave bright soliton

The quantum measurement problem, namely how the deterministic quantum evolution leads to probabilistic measurement outcomes, remains a profound question to be answered. In the present work, we propose a spectacular demonstration and test of the subtle and peculiar character of the quantum measurement process. We show that a bright soliton supported by a Bose-Einstein condensate can be reflected as a whole by an electron beam, with neither attraction nor repulsion between the condensate's neutral atoms and the beam's electrons. This macroscopic reflection is purely due to the quantum Zeno dynamics induced by the frequent position measurement of the condensate's atoms by the electron beam. As an example of application, just as a soccer player would stop a coming ball, an electron beam moving backward with half the velocity of the bright soliton can precisely stop the soliton. This offers an entirely new and useful tool for manipulating bright solitons.

quant-ph↗

arXiv2018

Effect of different filling tendencies on the spatial quantum Zeno effect

The quantum Zeno effect is deeply related to the quantum measurement process and thus studies of it may help shed light on the hitherto mysterious measurement process in quantum mechanics. Recently, the spatial quantum Zeno effect is observed in a Bose-Einstein condensate depleted by an electron beam. We theoretically investigate how different intrinsic tendencies of filling affect the quantum Zeno effect in this system by changing the impinging point of the electron beam along the inhomogeneous condensate. Surprisingly, we find no visible effect on the critical dissipation intensity at which the quantum Zeno effect appear. Our finding shows the recent capability of combining the Bose-Einstein condensate with an electron beam offers a great opportunity for studying the spatial quantum Zeno effect, and more generally the dynamics of a quantum many-body system out of equilibrium.

quant-ph↗

arXiv2018

Investigation of the 9B nucleus and its cluster-nucleon correlations

In order to study the correlation between clusters and nucleons in light nuclei, we formulate a new superposed THSR wave function which describes both spatial large spreading and cluster-correlated dynamics of valence nucleons. By using the new THSR wave function, the binding energy of 9B is essentially improved comparing with our previous studies. We calculate the excited states of 9B and obtain the energy spectrum of 9B which is consistent with the experimental results, including prediction of the 1/2+ excited state of 9B which is not fixed yet experimentally. We study the proton dynamics in 9B and find that the cluster-proton correlation plays an essential role for the proton dynamics in the ground state of 9B. Further more, we discuss the density distribution of the valence proton with special attention to its tail structure. Finally, the resonance nature of excited states of 9B is illustrated by comparing root-mean-square radii between the ground and excited states.

nucl-th↗

arXiv2017

Convex hulls of planar random walks

For the perimeter length $L_n$ and the area $A_n$ of the convex hull of the first $n$ steps of a planar random walk, this thesis study $n \to \infty$ mean and variance asymptotics and establish distributional limits. The results apply to random walks both with drift (the mean of random walk increments) and with no drift under mild moments assumptions on the increments. Assuming increments of the random walk have finite second moment and non-zero mean, Snyder and Steele showed that $n^{-1} L_n$ converges almost surely to a deterministic limit, and proved an upper bound on the variance Var$[ L_n] = O(n)$. We show that $n^{-1}$Var$[L_n]$ converges and give a simple expression for the limit, which is non-zero for walks outside a certain degenerate class. This answers a question of Snyder and Steele. Furthermore, we prove a central limit theorem for $L_n$ in the non-degenerate case. Then we focus on the perimeter length with no drift and area with both drift and zero-drift cases. These results complement and contrast with previous work and establish non-Gaussian distributional limits. We deduce these results from weak convergence statements for the convex hulls of random walks to scaling limits defined in terms of convex hulls of certain Brownian motions. We give bounds that confirm that the limiting variances in our results are non-zero.

math.PR↗

arXiv2017

Towards Evolutional Compression

Compressing convolutional neural networks (CNNs) is essential for transferring the success of CNNs to a wide variety of applications to mobile devices. In contrast to directly recognizing subtle weights or filters as redundant in a given CNN, this paper presents an evolutionary method to automatically eliminate redundant convolution filters. We represent each compressed network as a binary individual of specific fitness. Then, the population is upgraded at each evolutionary iteration using genetic operations. As a result, an extremely compact CNN is generated using the fittest individual. In this approach, either large or small convolution filters can be redundant, and filters in the compressed network are more distinct. In addition, since the number of filters in each convolutional layer is reduced, the number of filter channels and the size of feature maps are also decreased, naturally improving both the compression and speed-up ratios. Experiments on benchmark deep CNN models suggest the superiority of the proposed algorithm over the state-of-the-art compression methods.

stat.ML↗

arXiv2017

On the expected diameter of planar Brownian motion

Known results show that the diameter $d_1$ of the trace of planar Brownian motion run for unit time satisfies $1.595 \leq \mathbb{E} d_1 \leq 2.507$. This note improves these bounds to $1.601 \leq \mathbb{E} d_1 \leq 2.355$. Simulations suggest that $\mathbb{E} d_1 \approx 1.99$.

math.PR↗

arXiv2017

New cluster approach on properties of 8-11Be isotopes with isospin-dependent spin-orbit potential

The nonlocalized clustering approach is generalized to 8-11Be isotopes with isospin dependent spin-orbit potential. A new form of the Tohsaki-Horiuchi-Schuck-Röpke (THSR) wave function is introduced to provide a correct description for the σ-binding neutron in 11Be. Systematic calculations for 8-11Be isotopes are performed and results fit well with experimental values. The low energy spectrum of 11Be is also obtained, especially the correct spin-parity 1/2+ is reproduced for the intruder ground state. The exotic neutron halo structure of 11Be is studied by calculations of root-mean-square radii and density distribution. We obtain a large spatial distribution for the last valence neutron of 11Be, which fits the phenomenological extracted value from experimental data. The spectroscopic factor is also calculated and discussed for the 1/2+ ground state of 11Be.

nucl-th↗

arXiv2017

Alpha Cluster Formation and Decay in Quartetting Wave Function Approach

We present a microscopic calculation of alpha-cluster formation in heavy nuclei by using the quartetting wave function approach. The interaction of the quartet with the core nucleus is taken in local density approximation. The alpha-cluster formation is found to be particularly sensitive to the interplay of the mean field felt by the alpha-cluster and the Pauli blocking as a consequence of antisymmetrization. The striking feature of alpha-cluster formation probability across the major shell closures of 82 protons and 126 neutrons is reproduced. The shell (or subshell) effects on the alpha-cluster formation in superheavy nuclei are also analyzed.

nucl-th↗

arXiv2017

Reinforcement Learning for Learning Rate Control

Stochastic gradient descent (SGD), which updates the model parameters by adding a local gradient times a learning rate at each step, is widely used in model training of machine learning algorithms such as neural networks. It is observed that the models trained by SGD are sensitive to learning rates and good learning rates are problem specific. We propose an algorithm to automatically learn learning rates using neural network based actor-critic methods from deep reinforcement learning (RL).In particular, we train a policy network called actor to decide the learning rate at each step during training, and a value network called critic to give feedback about quality of the decision (e.g., the goodness of the learning rate outputted by the actor) that the actor made. The introduction of auxiliary actor and critic networks helps the main network achieve better performance. Experiments on different datasets and network architectures show that our approach leads to better convergence of SGD than human-designed competitors.

cs.LG↗