arXiv subjects

Wei Shi

Publications and source records attributed to Wei Shi.

At least 109 records · Page 6Linked to original sources

arXiv2021

Pose-guided Feature Disentangling for Occluded Person Re-identification Based on Transformer

Occluded person re-identification is a challenging task as human body parts could be occluded by some obstacles (e.g. trees, cars, and pedestrians) in certain scenes. Some existing pose-guided methods solve this problem by aligning body parts according to graph matching, but these graph-based methods are not intuitive and complicated. Therefore, we propose a transformer-based Pose-guided Feature Disentangling (PFD) method by utilizing pose information to clearly disentangle semantic components (e.g. human body or joint parts) and selectively match non-occluded parts correspondingly. First, Vision Transformer (ViT) is used to extract the patch features with its strong capability. Second, to preliminarily disentangle the pose information from patch information, the matching and distributing mechanism is leveraged in Pose-guided Feature Aggregation (PFA) module. Third, a set of learnable semantic views are introduced in transformer decoder to implicitly enhance the disentangled body part features. However, those semantic views are not guaranteed to be related to the body without additional supervision. Therefore, Pose-View Matching (PVM) module is proposed to explicitly match visible body parts and automatically separate occlusion features. Fourth, to better prevent the interference of occlusions, we design a Pose-guided Push Loss to emphasize the features of visible body parts. Extensive experiments over five challenging datasets for two tasks (occluded and holistic Re-ID) demonstrate that our proposed PFD is superior promising, which performs favorably against state-of-the-art methods. Code is available at https://github.com/WangTaoAs/PFD_Net

cs.CV↗

arXiv2021

Semi-supervised t-SNE for Millimeter-wave Wireless Localization

We consider the mobile localization problem in future millimeter-wave wireless networks with distributed Base Stations (BSs) based on multi-antenna channel state information (CSI). For this problem, we propose a Semi-supervised tdistributed Stochastic Neighbor Embedding (St-SNE) algorithm to directly embed the high-dimensional CSI samples into the 2D geographical map. We evaluate the performance of St-SNE in a simulated urban outdoor millimeter-wave radio access network. Our results show that St-SNE achieves a mean localization error of 6.8 m with only 5% of labeled CSI samples in a 200*200 m^2 area with a ray-tracing channel model. St-SNE does not require accurate synchronization among multiple BSs, and is promising for future large-scale millimeter-wave localization.

cs.LG↗

arXiv2021

Error bounds for the asymptotic expansions of the Hermite polynomials

In this paper, we present explicit and computable error bounds for the asymptotic expansions of the Hermite polynomials with Plancherel--Rotach scale. Three cases, depending on whether the scaled variable lies in the outer or oscillatory interval, or it is the turning point, are considered separately. We introduce the "branch cut" technique to express the error terms as integrals on the contour taken as the one-sided limit of curves approaching the branch cut. This new technique enables us to derive simple error bounds in terms of elementary functions. We also provide recursive procedures for the computation of the coefficients appearing in the asymptotic expansions.

math.CA↗

arXiv2021

Understanding of Kernels in CNN Models by Suppressing Irrelevant Visual Features in Images

Deep learning models have shown their superior performance in various vision tasks. However, the lack of precisely interpreting kernels in convolutional neural networks (CNNs) is becoming one main obstacle to wide applications of deep learning models in real scenarios. Although existing interpretation methods may find certain visual patterns which are associated with the activation of a specific kernel, those visual patterns may not be specific or comprehensive enough for interpretation of a specific activation of kernel of interest. In this paper, a simple yet effective optimization method is proposed to interpret the activation of any kernel of interest in CNN models. The basic idea is to simultaneously preserve the activation of the specific kernel and suppress the activation of all other kernels at the same layer. In this way, only visual information relevant to the activation of the specific kernel is remained in the input. Consistent visual information from multiple modified inputs would help users understand what kind of features are specifically associated with specific kernel. Comprehensive evaluation shows that the proposed method can help better interpret activation of specific kernels than widely used methods, even when two kernels have very similar activation regions from the same input image.

cs.CV↗

arXiv2021

Silicon Photonics in Optical Access Networks for 5G Communications

Only radio access networks can provide connectivity across multiple antenna sites to achieve the great leap forward in capacity targeted by 5G. Optical fronthaul remains a sticking point in that connectivity, and we make the case for analog radio over fiber signals and an optical access network smartedge to achieve the potential of radio access networks. The edge of the network would house the intelligence that coordinates wireless transmissions to minimize interference and maximize throughput. As silicon photonics provides a hardware platform well adapted to support optical fronthaul, it is poised to drive smart edge adoption. We draw out the issues in adopting oursolution, propose a strategy for network densification, and cite recent demonstrations to support our approach.

cs.NI↗

arXiv2021

SpinQ Gemini: a desktop quantum computer for education and research

SpinQ Gemini is a commercial desktop quantum computer designed and manufactured by SpinQ Technology. It is an integrated hardware-software system. The first generation product with two qubits was launched in January 2020. The hardware is based on NMR spectrometer, with permanent magnets providing $\sim 1$ T magnetic field. SpinQ Gemini operates under room temperature ($0$-$30^{\circ}$C), highlighting its lightweight (55 kg with a volume of $70\times 40 \times 80$ cm$^3$), cost-effective (under $50$k USD), and maintenance-free. SpinQ Gemini aims to provide real-device experience for quantum computing education for K-12 and at the college level. It also features quantum control design capabilities that benefit the researchers studying quantum control and quantum noise. Since its first launch, SpinQ Gemini has been shipped to institutions in Canada, Taiwan and Mainland China. This paper introduces the system of design of SpinQ Gemini, from hardware to software. We also demonstrate examples for performing quantum computing tasks on SpinQ Gemini, including one task for a variational quantum eigensolver of a two-qubit Heisenberg model. The next generations of SpinQ quantum computing devices will adopt models of more qubits, advanced control functions for researchers with comparable cost, as well as simplified models for much lower cost (under $5$k USD) for K-12 education. We believe that low-cost portable quantum computer products will facilitate hands-on experience for teaching quantum computing at all levels, well-prepare younger generations of students and researchers for the future of quantum technologies.

quant-ph↗

arXiv2021

Obfuscation of Images via Differential Privacy: From Facial Images to General Images

Due to the pervasiveness of image capturing devices in every-day life, images of individuals are routinely captured. Although this has enabled many benefits, it also infringes on personal privacy. A promising direction in research on obfuscation of facial images has been the work in the k-same family of methods which employ the concept of k-anonymity from database privacy. However, there are a number of deficiencies of k-anonymity that carry over to the k-same methods, detracting from their usefulness in practice. In this paper, we first outline several of these deficiencies and discuss their implications in the context of facial obfuscation. We then develop a framework through which we obtain a formal differentially private guarantee for the obfuscation of facial images in generative machine learning models. Our approach provides a provable privacy guarantee that is not susceptible to the outlined deficiencies of k-same obfuscation and produces photo-realistic obfuscated output. In addition, we demonstrate through experimental comparisons that our approach can achieve comparable utility to k-same obfuscation in terms of preservation of useful features in the images. Furthermore, we propose a method to achieve differential privacy for any image (i.e., without restriction to facial images) through the direct modification of pixel intensities. Although the addition of noise to pixel intensities does not provide the high visual quality obtained via generative machine learning models, it offers greater versatility by eliminating the need for a trained model. We demonstrate that our proposed use of the exponential mechanism in this context is able to provide superior visual quality to pixel-space obfuscation using the Laplace mechanism.

cs.CR↗

arXiv2020

Self-Refining Deep Symmetry Enhanced Network for Rain Removal

Rain removal aims to remove the rain streaks on rain images. The state-of-the-art methods are mostly based on Convolutional Neural Network~(CNN). However, as CNN is not equivariant to object rotation, these methods are unsuitable for dealing with the tilted rain streaks. To tackle this problem, we propose Deep Symmetry Enhanced Network~(DSEN) that is able to explicitly extract the rotation equivariant features from rain images. In addition, we design a self-refining mechanism to remove the accumulated rain streaks in a coarse-to-fine manner. This mechanism reuses DSEN with a novel information link which passes the gradient flow to the higher stages. Extensive experiments on both synthetic and real-world rain images show that our self-refining DSEN yields the top performance.

eess.IV↗

arXiv2020

Differential Privacy Via a Truncated and Normalized Laplace Mechanism

When querying databases containing sensitive information, the privacy of individuals stored in the database has to be guaranteed. Such guarantees are provided by differentially private mechanisms which add controlled noise to the query responses. However, most such mechanisms do not take into consideration the valid range of the query being posed. Thus, noisy responses that fall outside of this range may potentially be produced. To rectify this and therefore improve the utility of the mechanism, the commonly used Laplace distribution can be truncated to the valid range of the query and then normalized. However, such a data-dependent operation of normalization leaks additional information about the true query response thereby violating the differential privacy guarantee. Here, we propose a new method which preserves the differential privacy guarantee through a careful determination of an appropriate scaling parameter for the Laplace distribution. We also generalize the privacy guarantee in the context of the Laplace distribution to account for data-dependent normalization factors and study this guarantee for different classes of range constraint configurations. We provide derivations of the optimal scaling parameter (i.e., the minimal value that preserves differential privacy) for each class or provide an approximation thereof. As a consequence of this work, one can use the Laplace distribution to answer queries in a range-adherent and differentially private manner.

cs.DB↗

arXiv2020

The Unusual Eruption of the Extragalactic Classical Nova M31N 2017-09a

M31N 2017-09a is a classical nova and was observed for some 160 days following its initial eruption, during which time it underwent a number of bright secondary outbursts. The light-curve is characterized by continual variation with excursions of at least 0.5 magnitudes on a daily time-scale. The lower envelope of the eruption suggests that a single power-law can describe the decline rate. The eruption is relatively long with $t_2 = 111$, and $t_3 = 153$ days.

astro-ph.SR↗

arXiv2020

SNEAP: A Fast and Efficient Toolchain for Mapping Large-Scale Spiking Neural Network onto NoC-based Neuromorphic Platform

Spiking neural network (SNN), as the third generation of artificial neural networks, has been widely adopted in vision and audio tasks. Nowadays, many neuromorphic platforms support SNN simulation and adopt Network-on-Chips (NoC) architecture for multi-cores interconnection. However, interconnection brings huge area overhead to the platform. Moreover, run-time communication on the interconnection has a significant effect on the total power consumption and performance of the platform. In this paper, we propose a toolchain called SNEAP for mapping SNNs to neuromorphic platforms with multi-cores, which aims to reduce the energy and latency brought by spike communication on the interconnection. SNEAP includes two key steps: partitioning the SNN to reduce the spikes communicated between partitions, and mapping the partitions of SNN to the NoC to reduce average hop of spikes under the constraint of hardware resources. SNEAP can reduce more spikes communicated on the interconnection of NoC and spend less time than other toolchains in the partitioning phase. Moreover, the average hop of spikes is reduced more by SNEAP within a time period, which effectively reduces the energy and latency on the NoC-based neuromorphic platform. The experimental results show that SNEAP can achieve 418x reduction in end-to-end execution time, and reduce energy consumption and spike latency, on average, by 23% and 51% respectively, compared with SpiNeMap.

cs.DC↗

arXiv2020

Accelerating Incremental Gradient Optimization with Curvature Information

This paper studies an acceleration technique for incremental aggregated gradient ({\sf IAG}) method through the use of \emph{curvature} information for solving strongly convex finite sum optimization problems. These optimization problems of interest arise in large-scale learning applications. Our technique utilizes a curvature-aided gradient tracking step to produce accurate gradient estimates incrementally using Hessian information. We propose and analyze two methods utilizing the new technique, the curvature-aided IAG ({\sf CIAG}) method and the accelerated CIAG ({\sf A-CIAG}) method, which are analogous to gradient method and Nesterov's accelerated gradient method, respectively. Setting $κ$ to be the condition number of the objective function, we prove the $R$ linear convergence rates of $1 - \frac{4c_0 κ}{(κ+1)^2}$ for the {\sf CIAG} method, and $1 - \sqrt{\frac{c_1}{2κ}}$ for the {\sf A-CIAG} method, where $c_0,c_1 \leq 1$ are constants inversely proportional to the distance between the initial point and the optimal solution. When the initial iterate is close to the optimal solution, the $R$ linear convergence rates match with the gradient and accelerated gradient method, albeit {\sf CIAG} and {\sf A-CIAG} operate in an incremental setting with strictly lower computation complexity. Numerical experiments confirm our findings. The source codes used for this paper can be found on \url{http://github.com/hoitowai/ciag/}.

math.OC↗

arXiv2020

Joint Embedding in Named Entity Linking on Sentence Level

Named entity linking is to map an ambiguous mention in documents to an entity in a knowledge base. The named entity linking is challenging, given the fact that there are multiple candidate entities for a mention in a document. It is difficult to link a mention when it appears multiple times in a document, since there are conflicts by the contexts around the appearances of the mention. In addition, it is difficult since the given training dataset is small due to the reason that it is done manually to link a mention to its mapping entity. In the literature, there are many reported studies among which the recent embedding methods learn vectors of entities from the training dataset at document level. To address these issues, we focus on how to link entity for mentions at a sentence level, which reduces the noises introduced by different appearances of the same mention in a document at the expense of insufficient information to be used. We propose a new unified embedding method by maximizing the relationships learned from knowledge graphs. We confirm the effectiveness of our method in our experimental studies.

cs.CL↗

arXiv2020

Push-Pull Gradient Methods for Distributed Optimization in Networks

In this paper, we focus on solving a distributed convex optimization problem in a network, where each agent has its own convex cost function and the goal is to minimize the sum of the agents' cost functions while obeying the network connectivity structure. In order to minimize the sum of the cost functions, we consider new distributed gradient-based methods where each node maintains two estimates, namely, an estimate of the optimal decision variable and an estimate of the gradient for the average of the agents' objective functions. From the viewpoint of an agent, the information about the gradients is pushed to the neighbors, while the information about the decision variable is pulled from the neighbors hence giving the name "push-pull gradient methods". The methods utilize two different graphs for the information exchange among agents, and as such, unify the algorithms with different types of distributed architecture, including decentralized (peer-to-peer), centralized (master-slave), and semi-centralized (leader-follower) architecture. We show that the proposed algorithms and their many variants converge linearly for strongly convex and smooth objective functions over a network (possibly with unidirectional data links) in both synchronous and asynchronous random-gossip settings. In particular, under the random-gossip setting, "push-pull" is the first class of algorithms for distributed optimization over directed graphs. Moreover, we numerically evaluate our proposed algorithms in both scenarios, and show that they outperform other existing linearly convergent schemes, especially for ill-conditioned problems and networks that are not well balanced.

math.OC↗

arXiv2020

Chip-scale Full-Stokes Spectropolarimeter in Silicon Photonic Circuits

Wavelength-dependent polarization state of light carries crucial information about light-matter interactions. However, its measurement is limited to bulky, energy-consuming devices, which prohibits many modern, portable applications. Here, we propose and demonstrate a chip-scale spectropolarimeter implemented using a CMOS-compatible silicon photonics technology. Four compact Vernier microresonator spectrometers are monolithically integrated with a broadband polarimeter consisting of a 2D nanophotonic antenna and a polarimetric circuit to achieve full-Stokes spectropolarimetric analysis. The proposed device offers a solid-state spectropolarimetry solution with a small footprint of 1*0.6 mm2 and low power consumption of 360 mW}. Full-Stokes spectral detection across a broad spectral range of 50 nm with a resolution of 1~nm is demonstrated in characterizing a material possessing structural chirality. The proposed device may enable a broader application of spectropolarimetry in the fields ranging from biomedical diagnostics and chemical analysis to observational astronomy.

physics.optics↗

arXiv2019

A Push-Pull Gradient Method for Distributed Optimization in Networks

In this paper, we focus on solving a distributed convex optimization problem in a network, where each agent has its own convex cost function and the goal is to minimize the sum of the agents' cost functions while obeying the network connectivity structure. In order to minimize the sum of the cost functions, we consider a new distributed gradient-based method where each node maintains two estimates, namely, an estimate of the optimal decision variable and an estimate of the gradient for the average of the agents' objective functions. From the viewpoint of an agent, the information about the decision variable is pushed to the neighbors, while the information about the gradients is pulled from the neighbors (hence giving the name "push-pull gradient method"). The method unifies the algorithms with different types of distributed architecture, including decentralized (peer-to-peer), centralized (master-slave), and semi-centralized (leader-follower) architecture. We show that the algorithm converges linearly for strongly convex and smooth objective functions over a directed static network. In our numerical test, the algorithm performs well even for time-varying directed networks.

math.OC↗

arXiv2019

Bayesian Nonparametric Nonhomogeneous Poisson Process with Applications to USGS Earthquake Data

Intensity estimation is a common problem in statistical analysis of spatial point pattern data. This paper proposes a nonparametric Bayesian method for estimating the spatial point process intensity based on mixture of finite mixture (MFM) model. MFM approach leads to a consistent estimate of the intensity of spatial point patterns in different areas while considering heterogeneity. An efficient Markov chain Monte Carlo (MCMC) algorithm is proposed for our method. Extensive simulation studies are carried out to examine empirical performance of the proposed method. The usage of our proposed method is further illustrated with the analysis of the Earthquake Hazards Program of United States Geological Survey (USGS) earthquake data.

stat.ME↗

arXiv2019

X-ray differential phase contrast imaging on asymmetric dual-phase grating interferometer with source grating: theory and experiment

Recently, the dual-phase grating based X-ray differential phase contrast imaging technique has shown better radiation dose efficiency performance than the Talbot-Lau system. In this paper, we provide a theoretical analyses framework derived from wave optics to ease the design of such interferometer systems, including the inter-grating distances, the diffraction fringe period, the phase grating periods, and especially the source grating period if a medical grade X-ray tube with large focal spot is utilized. In addition, a geometrical explanation of the dual-phase grating system similar to the standard thin lens imaging theory is derived with an optical symmetry assumption for the first time. Finally, both numerical and experimental studies have been performed to validate the theory.

physics.optics↗