arXiv subjects

Jing Yang

Publications and source records attributed to Jing Yang.

At least 361 records · Page 20Linked to original sources

arXiv2020

Edge-Aware Deep Image Deblurring

Image deblurring is a fundamental and challenging low-level vision problem. Previous vision research indicates that edge structure in natural scenes is one of the most important factors to estimate the abilities of human visual perception. In this paper, we resort to human visual demands of sharp edges and propose a two-phase edge-aware deep network to improve deep image deblurring. An edge detection convolutional subnet is designed in the first phase and a residual fully convolutional deblur subnet is then used for generating deblur results. The introduction of the edge-aware network enables our model with the specific capacity of enhancing images with sharp edges. We successfully apply our framework on standard benchmarks and promising results are achieved by our proposed deblur model.

cs.CV↗

arXiv2020

Tuning Conductivity Type in Monolayer WS2 and MoS2 by Sulfur Vacancies

While n-type semiconductor behavior appears to be more common in as-prepared two-dimensional (2D) transition metal dichalcogenides (TMDCs), substitutional doping with acceptor atoms is typically required to tune the conductivity to p-type in order to facilitate their potential application in different devices. Here, we report a systematic study on the equivalent electrical "doping" effect of - single sulfur vacancies (V1S) in monolayer WS2 and MoS2 by studying the interface interaction of WS2-Au and MoS2-Au contacts. Based on our first principles calculations, we found that the V1S can significantly alter the semiconductor behavior of both monolayer WS2 and MoS2 so that they can exhibit the character of electron acceptor (p-type) as well as electron donor (n-type) when they are contacted with gold. For relatively low V1S densities (approximately < 7% for MoS2 and < 3% for WS2), the monolayer TMDC serves as electron acceptor. As the V1S density increases beyond the threshold densities, the MoS2 and WS2 play the role of electron donor. The significant impact V1S can have on monolayer WS2 and MoS2 may be useful for engineering its electrical behavior and offers an alternative way to tune the semiconductor TMDCs to exhibit either n-type or p-type behavior.

cond-mat.mes-hall↗

arXiv2020

All-Optically Controlled Memristor

Memristors have emerged as key candidates for beyond-von-Neumann neuromorphic or in-memory computing owing to the feasibility of their ultrahigh-density three-dimensional integration and their ultralow energy consumption. A memristor is generally a two-terminal electronic element with conductance that varies nonlinearly with external electric stimuli and can be remembered when the electric power is turned off. As an alternative, light can be used to tune the memconductance and endow a memristor with a combination of the advantages of both photonics and electronics. Both increases and decreases in optically induced memconductance have been realized in different memristors; however, the reversible tuning of memconductance with light in the same device remains a considerable challenge that severely restricts the development of optoelectronic memristors. Here we describe an all-optically controlled (AOC) analog memristor with memconductance that is reversibly tunable over a continuous range by varying only the wavelength of the controlling light. Our memristor is based on the relatively mature semiconductor material InGaZnO (IGZO) and a memconductance tuning mechanism of light-induced electron trapping and detrapping. We demonstrate that spike-timing-dependent plasticity (STDP) learning can be realized in our device, indicating its potential applications in AOC spiking neural networks (SNNs) for highly efficient optoelectronic neuromorphic computing.

cond-mat.mtrl-sci↗

arXiv2020

Training Binary Neural Networks with Real-to-Binary Convolutions

This paper shows how to train binary networks to within a few percent points ($\sim 3-5 \%$) of the full precision counterpart. We first show how to build a strong baseline, which already achieves state-of-the-art accuracy, by combining recently proposed advances and carefully adjusting the optimization procedure. Secondly, we show that by attempting to minimize the discrepancy between the output of the binary and the corresponding real-valued convolution, additional significant accuracy gains can be obtained. We materialize this idea in two complementary ways: (1) with a loss function, during training, by matching the spatial attention maps computed at the output of the binary and real-valued convolutions, and (2) in a data-driven manner, by using the real-valued activations, available during inference prior to the binarization process, for re-scaling the activations right after the binary convolution. Finally, we show that, when putting all of our improvements together, the proposed model beats the current state of the art by more than 5% top-1 accuracy on ImageNet and reduces the gap to its real-valued counterpart to less than 3% and 5% top-1 accuracy on CIFAR-100 and ImageNet respectively when using a ResNet-18 architecture. Code available at https://github.com/brais-martinez/real2binary.

cs.CV↗

arXiv2020

Knowledge distillation via adaptive instance normalization

This paper addresses the problem of model compression via knowledge distillation. To this end, we propose a new knowledge distillation method based on transferring feature statistics, specifically the channel-wise mean and variance, from the teacher to the student. Our method goes beyond the standard way of enforcing the mean and variance of the student to be similar to those of the teacher through an $L_2$ loss, which we found it to be of limited effectiveness. Specifically, we propose a new loss based on adaptive instance normalization to effectively transfer the feature statistics. The main idea is to transfer the learned statistics back to the teacher via adaptive instance normalization (conditioned on the student) and let the teacher network "evaluate" via a loss whether the statistics learned by the student are reliably transferred. We show that our distillation method outperforms other state-of-the-art distillation methods over a large set of experimental settings including different (a) network architectures, (b) teacher-student capacities, (c) datasets, and (d) domains.

cs.CV↗

arXiv2020

Stochastic Linear Contextual Bandits with Diverse Contexts

In this paper, we investigate the impact of context diversity on stochastic linear contextual bandits. As opposed to the previous view that contexts lead to more difficult bandit learning, we show that when the contexts are sufficiently diverse, the learner is able to utilize the information obtained during exploitation to shorten the exploration process, thus achieving reduced regret. We design the LinUCB-d algorithm, and propose a novel approach to analyze its regret performance. The main theoretical result is that under the diverse context assumption, the cumulative expected regret of LinUCB-d is bounded by a constant. As a by-product, our results improve the previous understanding of LinUCB and strengthen its performance guarantee.

cs.LG↗

arXiv2020

MODMA dataset: a Multi-modal Open Dataset for Mental-disorder Analysis

According to the World Health Organization, the number of mental disorder patients, especially depression patients, has grown rapidly and become a leading contributor to the global burden of disease. However, the present common practice of depression diagnosis is based on interviews and clinical scales carried out by doctors, which is not only labor-consuming but also time-consuming. One important reason is due to the lack of physiological indicators for mental disorders. With the rising of tools such as data mining and artificial intelligence, using physiological data to explore new possible physiological indicators of mental disorder and creating new applications for mental disorder diagnosis has become a new research hot topic. However, good quality physiological data for mental disorder patients are hard to acquire. We present a multi-modal open dataset for mental-disorder analysis. The dataset includes EEG and audio data from clinically depressed patients and matching normal controls. All our patients were carefully diagnosed and selected by professional psychiatrists in hospitals. The EEG dataset includes not only data collected using traditional 128-electrodes mounted elastic cap, but also a novel wearable 3-electrode EEG collector for pervasive applications. The 128-electrodes EEG signals of 53 subjects were recorded as both in resting state and under stimulation; the 3-electrode EEG signals of 55 subjects were recorded in resting state; the audio data of 52 subjects were recorded during interviewing, reading, and picture description. We encourage other researchers in the field to use it for testing their methods of mental-disorder analysis.

cs.DL↗

arXiv2020

Timely Synchronization with Sporadic Status Changes

In this paper, we consider a status updating system where the transmitter sends status updates of the signal it monitors to the destination through a rate-limited link. We consider the scenario where the status of the monitored signal only changes at discrete time points. The objective is to let the destination be synchronized with the source in a timely manner once a status change happens. What complicates the problem is that the transmission takes multiple time slots due to the link-rate constraint. Thus, the transmitter has to decide to switch or to skip a new update when the status of the monitored signal changes and it has not completed the transmission of the previous one yet. We adopt a metric called "Age of Synchronization" (AoS) to measure the "dissatisfaction" of the destination when it is desynchronized with the source. Then, the objective of this paper is to minimize the time-average AoS by designing optimal transmission policies for the transmitter. We formulate the problem as a Markov decision process (MDP) and prove the multi-threshold structure of the optimal policy. Based on that, we propose a low computational-complexity algorithm for the MDP value iteration. We then evaluate the performance of the multi-threshold policy through simulations and compare it with two baseline policies and the AoI-optimal policy.

cs.IT↗

arXiv2020

Decentralized Multi-player Multi-armed Bandits with No Collision Information

The decentralized stochastic multi-player multi-armed bandit (MP-MAB) problem, where the collision information is not available to the players, is studied in this paper. Building on the seminal work of Boursier and Perchet (2019), we propose error correction synchronization involving communication (EC-SIC), whose regret is shown to approach that of the centralized stochastic MP-MAB with collision information. By recognizing that the communication phase without collision information corresponds to the Z-channel model in information theory, the proposed EC-SIC algorithm applies optimal error correction coding for the communication of reward statistics. A fixed message length, as opposed to the logarithmically growing one in Boursier and Perchet (2019), also plays a crucial role in controlling the communication loss. Experiments with practical Z-channel codes, such as repetition code, flip code and modified Hamming code, demonstrate the superiority of EC-SIC in both synthetic and real-world datasets.

cs.LG↗

arXiv2020

A Real-Time Deep Network for Crowd Counting

Automatic analysis of highly crowded people has attracted extensive attention from computer vision research. Previous approaches for crowd counting have already achieved promising performance across various benchmarks. However, to deal with the real situation, we hope the model run as fast as possible while keeping accuracy. In this paper, we propose a compact convolutional neural network for crowd counting which learns a more efficient model with a small number of parameters. With three parallel filters executing the convolutional operation on the input image simultaneously at the front of the network, our model could achieve nearly real-time speed and save more computing resources. Experiments on two benchmarks show that our proposed method not only takes a balance between performance and efficiency which is more suitable for actual scenes but also is superior to existing light-weight models in speed.

cs.CV↗

arXiv2020

Information Freshness for Timely Detection of Status Changes

In this paper, we aim to establish the connection between Age of Information (AoI) in network theory, information uncertainty in information theory, and detection delay in time series analysis. We consider a dynamic system whose state changes at discrete time points, and a state change won't be detected until an update generated after the change point is delivered to the destination for the first time. We introduce an information theoretic metric to measure the information freshness at the destination, and name it as generalized Age of Information (GAoI). We show that under any state-independent online updating policy, if the underlying state of the system evolves according to a stationary Markov chain, the GAoI is proportional to the AoI. Besides, the accumulative GAoI and AoI are proportional to the expected accumulative detection delay of all changes points over a period of time. Thus, any (G)AoI-optimal state-independent updating policy equivalently minimizes the corresponding expected change point detection delay, which validates the fundamental role of (G)AoI in real-time status monitoring. Besides, we also investigate a Bayesian change point detection scenario where the underlying state evolution is not stationary. Although AoI is no longer related to detection delay explicitly, we show that the accumulative GAoI is still an affine function of the expected detection delay, which indicates the versatility of GAoI in capturing information freshness in dynamic systems.

cs.IT↗

arXiv2020

Fast Video Crowd Counting with a Temporal Aware Network

Crowd counting aims to count the number of instantaneous people in a crowded space, and many promising solutions have been proposed for single image crowd counting. With the ubiquitous video capture devices in public safety field, how to effectively apply the crowd counting technique to video content has become an urgent problem. In this paper, we introduce a novel framework based on temporal aware modeling of the relationship between video frames. The proposed network contains a few dilated residual blocks, and each of them consists of the layers that compute the temporal convolutions of features from the adjacent frames to improve the prediction. To alleviate the expensive computation and satisfy the demand of fast video crowd counting, we also introduce a lightweight network to balance the computational cost with representation ability. We conduct experiments on the crowd counting benchmarks and demonstrate its superiority in terms of effectiveness and efficiency over previous video-based approaches.

cs.CV↗

arXiv2020

On mu-Symmetric Polynomials

In this paper, we study functions of the roots of a univariate polynomial in which the roots have a given multiplicity structure $μ$. Traditionally, root functions are studied via the theory of symmetric polynomials; we extend this theory to $μ$-symmetric polynomials. We were motivated by a conjecture from Becker et al.~(ISSAC 2016) about the $μ$-symmetry of a particular root function $D^+(μ)$, called D-plus. To investigate this conjecture, it was desirable to have fast algorithms for checking if a given root function is $μ$-symmetric. We designed three such algorithms: one based on Gröbner bases, another based on preprocessing and reduction, and the third based on solving linear equations. We implemented them in Maple and experiments show that the latter two algorithms are significantly faster than the first.

cs.SC↗

arXiv2020

Gravitational Waves from first-order phase transition and domain wall

In many particle physics models, domain wall can form during the phase transition process after discrete symmetry breaking. We study the scenario within a complex singlet extended Standard Model framework, where a strongly first order phase transition can occur depending on the hidden scalar mass and the mixing between the extra heavy Higgs and the SM Higgs mass. The gravitational wave spectrum is of a typical two-peak shape, the amplitude and the peak from the strongly first order phase transition is able to be probed by the future space-based interferometers, and the one locates around the peak from the domain wall decay is far beyond the capability of the current PTA, and future SKA.

hep-ph↗

arXiv2019

Cascaded Detail-Preserving Networks for Super-Resolution of Document Images

The accuracy of OCR is usually affected by the quality of the input document image and different kinds of marred document images hamper the OCR results. Among these scenarios, the low-resolution image is a common and challenging case. In this paper, we propose the cascaded networks for document image super-resolution. Our model is composed by the Detail-Preserving Networks with small magnification. The loss function with perceptual terms is designed to simultaneously preserve the original patterns and enhance the edge of the characters. These networks are trained with the same architecture and different parameters and then assembled into a pipeline model with a larger magnification. The low-resolution images can upscale gradually by passing through each Detail-Preserving Network until the final high-resolution images. Through extensive experiments on two scanning document image datasets, we demonstrate that the proposed approach outperforms recent state-of-the-art image super-resolution methods, and combining it with standard OCR system lead to signification improvements on the recognition results.

cs.CV↗

arXiv2019

The Second Discriminant of a Univariate Polynomial

We define the second discriminant $D_2$ of a univariate polynomial $f$ of degree greater than $2$ as the product of the linear forms $2\,r_k-r_i-r_j$ for all triples of roots $r_i, r_k, r_j$ of $f$ with $i<j$ and $j\neq k, k\neq i$. $D_2$ vanishes if and only if $f$ has at least one root which is equal to the average of two other roots. We show that $D_2$ can be expressed as the resultant of $f$ and a determinant formed with the derivatives of $f$, establishing a new relation between the roots and the coefficients of $f$. We prove several notable properties and present an application of $D_2$.

math.AC↗

arXiv2019

Meta-neural-network for Realtime and Passive Deep-learning-based Object Recognition

Deep-learning recently show great success across disciplines yet conventionally require time-consuming computer processing or bulky-sized diffractive elements. Here we theoretically propose and experimentally demonstrate a purely-passive "meta-neural-network" with compactness and high-resolution for real-time recognizing complicated objects by analyzing acoustic scattering. We prove our meta-neural-network mimics standard neural network despite its small footprint, thanks to unique capability of its metamaterial unit cells, dubbed "meta-neurons", to produce deep-subwavelength-distribution of discrete phase shift as learnable parameters during training. The resulting device exhibits the "intelligence" to perform desired tasks with potential to address the current trade-off between reducing device's size, cost and energy consumption and increasing recognition speed and accuracy, showcased by an example of handwritten digit recognition. Our mechanism opens the route to new metamaterial-based deep-learning paradigms and enable conceptual devices such as smart transducers automatically analyzing signals, with far-reaching implications for acoustics, optics and related fields.

cs.NE↗

arXiv2019

Optimal measurements for quantum multiparameter estimation with general states

We generalize the approach by Braunstein and Caves [Phys. Rev. Lett. 72, 3439 (1994)] to quantum multi-parameter estimation with general states. We derive a matrix bound of the classical Fisher information matrix due to each measurement operator. The saturation of all these bounds results in the saturation of the matrix Helstrom Cramér-Rao bound. Remarkably, the saturation of the matrix bound is equivalent to the saturation of the scalar bound with respect to any given positive definite weight matrix. Necessary and sufficient conditions are obtained for the optimal measurements that give rise to the Helstrom Cramér-Rao bound associated with a general quantum state. To saturate the Helstrom bound with separable measurements or collective measurement entangling only a small number of identical states, we find it is necessary for the symmetric logarithmic derivatives to commute on the support of the state. As an important application of our results, we construct several local optimal measurements for the problem of estimating the three-dimensional separation of two incoherent optical point sources.

quant-ph↗