arXiv subjects

Yong Zhang

Publications and source records attributed to Yong Zhang.

At least 505 records · Page 28Linked to original sources

arXiv2021

Generalizing Face Forgery Detection with High-frequency Features

Current face forgery detection methods achieve high accuracy under the within-database scenario where training and testing forgeries are synthesized by the same algorithm. However, few of them gain satisfying performance under the cross-database scenario where training and testing forgeries are synthesized by different algorithms. In this paper, we find that current CNN-based detectors tend to overfit to method-specific color textures and thus fail to generalize. Observing that image noises remove color textures and expose discrepancies between authentic and tampered regions, we propose to utilize the high-frequency noises for face forgery detection. We carefully devise three functional modules to take full advantage of the high-frequency features. The first is the multi-scale high-frequency feature extraction module that extracts high-frequency noises at multiple scales and composes a novel modality. The second is the residual-guided spatial attention module that guides the low-level RGB feature extractor to concentrate more on forgery traces from a new perspective. The last is the cross-modality attention module that leverages the correlation between the two complementary modalities to promote feature learning for each other. Comprehensive evaluations on several benchmark databases corroborate the superior generalization performance of our proposed method.

cs.CV↗

arXiv2021

Probabilistic Modeling of Semantic Ambiguity for Scene Graph Generation

To generate "accurate" scene graphs, almost all existing methods predict pairwise relationships in a deterministic manner. However, we argue that visual relationships are often semantically ambiguous. Specifically, inspired by linguistic knowledge, we classify the ambiguity into three types: Synonymy Ambiguity, Hyponymy Ambiguity, and Multi-view Ambiguity. The ambiguity naturally leads to the issue of \emph{implicit multi-label}, motivating the need for diverse predictions. In this work, we propose a novel plug-and-play Probabilistic Uncertainty Modeling (PUM) module. It models each union region as a Gaussian distribution, whose variance measures the uncertainty of the corresponding visual content. Compared to the conventional deterministic methods, such uncertainty modeling brings stochasticity of feature representation, which naturally enables diverse predictions. As a byproduct, PUM also manages to cover more fine-grained relationships and thus alleviates the issue of bias towards frequent relationships. Extensive experiments on the large-scale Visual Genome benchmark show that combining PUM with newly proposed ResCAGCN can achieve state-of-the-art performances, especially under the mean recall metric. Furthermore, we prove the universal effectiveness of PUM by plugging it into some existing models and provide insightful analysis of its ability to generate diverse yet plausible visual relationships.

cs.CV↗

arXiv2021

Three supercongruences for Apery numbers or Franel numbers

The Apéry numbers $A_n$ and the Franel numbers $f_n$ are defined by $$A_n=\sum_{k=0}^{n}{\binom{n+k}{2k}}^2{\binom{2k}{k}}^2\ \ \ \ \ {\rm and }\ \ \ \ \ \ f_n=\sum_{k=0}^{n}{\binom{n}{k}}^3(n=0, 1, \cdots,).$$ In this paper, we prove three supercongruences for Apéry numbers or Franel numbers conjectured by Z.-W. Sun. Let $p\geq 5$ be a prime and let $n\in \mathbb{Z}^{+}$. We show that \begin{align} \notag \frac{1}{n}\bigg(\sum_{k=0}^{pn-1}(2k+1)A_k-p\sum_{k=0}^{n-1}(2k+1)A_k\bigg)\equiv0\pmod{p^{4+3ν_p(n)}} \end{align} and \begin{align}\notag \frac{1}{n^3}\bigg(\sum_{k=0}^{pn-1}(2k+1)^3A_k-p^3\sum_{k=0}^{n-1}(2k+1)^3A_k\bigg)\equiv0\pmod{p^{6+3ν_p(n)}}, \end{align} where $ν_p(n)$ denotes the $p$-adic order of $n$. Also, for any prime $p$ we have \begin{align} \notag \frac{1}{n^3}\bigg(\sum_{k=0}^{pn-1}(3k+2)(-1)^kf_k-p^2\sum_{k=0}^{n-1}(3k+2)(-1)^kf_k\bigg)\equiv0\pmod{p^{3}}. \end{align}

math.NT↗

arXiv2021

Targeted Attack against Deep Neural Networks via Flipping Limited Weight Bits

To explore the vulnerability of deep neural networks (DNNs), many attack paradigms have been well studied, such as the poisoning-based backdoor attack in the training stage and the adversarial attack in the inference stage. In this paper, we study a novel attack paradigm, which modifies model parameters in the deployment stage for malicious purposes. Specifically, our goal is to misclassify a specific sample into a target class without any sample modification, while not significantly reduce the prediction accuracy of other samples to ensure the stealthiness. To this end, we formulate this problem as a binary integer programming (BIP), since the parameters are stored as binary bits ($i.e.$, 0 and 1) in the memory. By utilizing the latest technique in integer programming, we equivalently reformulate this BIP problem as a continuous optimization problem, which can be effectively and efficiently solved using the alternating direction method of multipliers (ADMM) method. Consequently, the flipped critical bits can be easily determined through optimization, rather than using a heuristic strategy. Extensive experiments demonstrate the superiority of our method in attacking DNNs.

cs.LG↗

arXiv2021

A Comprehensive Review of Computer-aided Whole-slide Image Analysis: from Datasets to Feature Extraction, Segmentation, Classification, and Detection Approaches

With the development of computer-aided diagnosis (CAD) and image scanning technology, Whole-slide Image (WSI) scanners are widely used in the field of pathological diagnosis. Therefore, WSI analysis has become the key to modern digital pathology. Since 2004, WSI has been used more and more in CAD. Since machine vision methods are usually based on semi-automatic or fully automatic computers, they are highly efficient and labor-saving. The combination of WSI and CAD technologies for segmentation, classification, and detection helps histopathologists obtain more stable and quantitative analysis results, save labor costs and improve diagnosis objectivity. This paper reviews the methods of WSI analysis based on machine learning. Firstly, the development status of WSI and CAD methods are introduced. Secondly, we discuss publicly available WSI datasets and evaluation metrics for segmentation, classification, and detection tasks. Then, the latest development of machine learning in WSI segmentation, classification, and detection are reviewed continuously. Finally, the existing methods are studied, the applicabilities of the analysis methods are analyzed, and the application prospects of the analysis methods in this field are forecasted.

cs.CV↗

arXiv2021

QoS-aware Link Scheduling Strategy for Data Transmission in SDVN

The vehicular ad-hoc network (VANET) based on dedicated short-range communication (DSRC) is a distributed communication system, in which all the nodes share the wireless channel with carrier sense multiple access/collision avoid (CSMA/CA) protocol. However, the backoff mechanism of CSMA/CA in the channel contention might cause uncertain transmission delay and impede a certain quality of service (QoS) of applications. Moreover, there still exists a possibility of parlous data-packets collision, especially for broadcast or non-acknowledgement (NACK) transmissions. The original contributions of this paper are summarized as follows: (1) Model the packets collision probability of broadcast or NACK transmission in VANET with the combination theory and investigate the potential influence of miss my packets (MMP) problem. (2) Based on the software define vehicular network (SDVN) framework and QoS requirement, a novel link-level scheduling strategy, which determines the start-sending time for each connection, is proposed to maximize packets delivery ratio (PDR). Alternatively, maximizing PDR has been converted to the overlap minimization among transmission durations. (3) Meanwhile, an innovative transmission scheduling greedy search (TSGS) algorithm is originally proposed to mitigate computational complexity. Extensive simulations have been done in a unified platform Veins combining SUMO and OMNET++. And numerous results show that the proposed algorithm can effectively improve the PDR by at least 15%, enhance the collision-avoidance performance by almost 40%, and reduce the MMP ratio by about 3% compared with the random transmitting, meanwhile meet the QoS requirement.

cs.NI↗

arXiv2021

CaEGCN: Cross-Attention Fusion based Enhanced Graph Convolutional Network for Clustering

With the powerful learning ability of deep convolutional networks, deep clustering methods can extract the most discriminative information from individual data and produce more satisfactory clustering results. However, existing deep clustering methods usually ignore the relationship between the data. Fortunately, the graph convolutional network can handle such relationship, opening up a new research direction for deep clustering. In this paper, we propose a cross-attention based deep clustering framework, named Cross-Attention Fusion based Enhanced Graph Convolutional Network (CaEGCN), which contains four main modules: the cross-attention fusion module which innovatively concatenates the Content Auto-encoder module (CAE) relating to the individual data and Graph Convolutional Auto-encoder module (GAE) relating to the relationship between the data in a layer-by-layer manner, and the self-supervised model that highlights the discriminative information for clustering tasks. While the cross-attention fusion module fuses two kinds of heterogeneous representation, the CAE module supplements the content information for the GAE module, which avoids the over-smoothing problem of GCN. In the GAE module, two novel loss functions are proposed that reconstruct the content and relationship between the data, respectively. Finally, the self-supervised module constrains the distributions of the middle layer representations of CAE and GAE to be consistent. Experimental results on different types of datasets prove the superiority and robustness of the proposed CaEGCN.

cs.AI↗

arXiv2021

Overlap-Minimization Scheduling Strategy for Data Transmission in VANET

The vehicular ad-hoc network (VANET) based on dedicated short-range communication (DSRC) is a distributed communication system, in which all the nodes share the wireless channel with carrier sense multiple access/collision avoid (CSMA/CA) protocol. However, the competition and backoff mechanisms of CSMA/CA often bring additional delays and data packet collisions, which may hardly meet the QoS requirements in terms of delay and packets delivery ratio (PDR). Moreover, because of the distribution nature of security information in broadcast mode, the sender cannot know whether the receivers have received the information successfully. Similarly, this problem also exists in no-acknowledge (non-ACK) transmissions of VANET. Therefore, the probability of packet collisions should be considered in broadcast or non-ACK working modes. This paper presents a connection-level scheduling algorithm overlaid on CSMA/CA to schedule the start sending time of each transmission. By converting the object of reducing collision probability to minimizing the overlap of transmission durations of connections, the probability of backoff-activation can be greatly decreased. Then the delay and the probability of packet collisions can also be decreased. Numerical simulations have been conducted in our unified platform containing SUMO, Veins and Omnet++. The result shows that the proposed algorithm can effectively improve the PDR and reduce the packets collision in VANET.

cs.NI↗

arXiv2020

Ultra-bright multiplexed energy-time entangled photon generation from lithium niobate on insulator chip

High-flux entangled photon source is the key resource for quantum optical study and application. Here it is realized in a lithium niobate on isolator (LNOI) chip, with 2.79*10^11 Hz/mW photon pair rate and 1.53*10^9 Hz/nm/mW spectral brightness. These data are boosted by over two orders of magnitude compared to existing technologies. A 130-nm broad bandwidth is engineered for 8-channel multiplexed energy-time entanglement. Harnessed by high-extinction frequency correlation and Franson interferences up to 99.17% visibility, such energy-time entanglement multiplexing further enhances high-flux data rate, and warrants broad applications in quantum information processing on a chip.

quant-ph↗

arXiv2020

Proposal of a FET-LET Hybrid 6T SRAM

There is an extremely high demand for a high speed, low power, low leakage, and low noise Static Random-Access Memory (SRAM) for high performance cache memories. The energy efficiency of SRAM is of paramount importance in both high performance and ultralow-power portable, battery operated electronic systems. In this article the factors affecting the over-all speed and total energy consumption of a conventional 6T SRAM cell/array with 6 FETs, particularly roles of access tran-sistors are analyzed to highlight the needs and directions for improvement. A hybrid 6T SRAM with two access FETs being replaced by light-effect transistors (LETs) and the electrical word lines replaced by optical waveguides (OWGs) is proposed. This hybrid SRAM is analyzed to reveal its potential in im-provement of the switching speed and thus total energy con-sumption over the conventional 6T SRAM. Numerical analyses of a prototype hybrid SRAM array of 64 KB show a factor of 7 and 34 reduction in read delay and read energy consumption, respectively; and 4 and 6 in write delay and write energy con-sumption, respectively, when the access FETs are replaced by LETs. The potential impacts on the peripheral and assist cir-cuits due to this hybrid structure and application of the LETs there are also briefly discussed.

physics.app-ph↗

arXiv2020

Automated Prostate Cancer Diagnosis Based on Gleason Grading Using Convolutional Neural Network

The Gleason grading system using histological images is the most powerful diagnostic and prognostic predictor of prostate cancer. The current standard inspection is evaluating Gleason H&E-stained histopathology images by pathologists. However, it is complicated, time-consuming, and subject to observers. Deep learning (DL) based-methods that automatically learn image features and achieve higher generalization ability have attracted significant attention. However, challenges remain especially using DL to train the whole slide image (WSI), a predominant clinical source in the current diagnostic setting, containing billions of pixels, morphological heterogeneity, and artifacts. Hence, we proposed a convolutional neural network (CNN)-based automatic classification method for accurate grading of PCa using whole slide histopathology images. In this paper, a data augmentation method named Patch-Based Image Reconstruction (PBIR) was proposed to reduce the high resolution and increase the diversity of WSIs. In addition, a distribution correction (DC) module was developed to enhance the adaption of pretrained model to the target dataset by adjusting the data distribution. Besides, a Quadratic Weighted Mean Square Error (QWMSE) function was presented to reduce the misdiagnosis caused by equal Euclidean distances. Our experiments indicated the combination of PBIR, DC, and QWMSE function was necessary for achieving superior expert-level performance, leading to the best results (0.8885 quadratic-weighted kappa coefficient).

eess.IV↗

arXiv2020

Central velocity dispersion catalog of LAMOST-DR7 galaxies

The Large Sky Area Multi-Object Fiber Spectroscopic Telescope (LAMOST) is a major facility to carry out spectroscopic surveys for cosmology and galaxy evolution studies. The seventh data release of the LAMOST ExtraGAlactic Survey (LEGAS) is currently available and including redshifts of 193\,361 galaxies. These sources are spread over $\sim 11\,500$ deg$^2$ of the sky, largely overlapping with other imaging (SDSS, HSC) and spectroscopic (BOSS) surveys. The estimated depth of the galaxy sample, $r\sim17.8$, the high signal-to-noise ratio, and the spectral resolution $R=1800$, make the LAMOST spectra suitable for galaxy velocity dispersion measurements, which are invaluable to study the structure and formation of galaxies and to determine their central dark matter (DM) content. We present the first estimates of central velocity dispersion of $\sim86\,000$ galaxies in LAMOST footprint. We have used a wrap-up procedure to perform the spectral fitting using \textsc{pPXF}, and derive velocity dispersion measurements. Statistical errors are also assessed by comparing LAMOST velocity dispersion estimates with the ones of SDSS and BOSS over a common sample of $\sim51\,000$ galaxies. The two datasets show a good agreement, within the statistical errors, in particular when velocity dispersion values are corrected to 1 effective radius aperture. We also present a preliminary Mass-$σ$ relation and find consistency with previous analyses based on local galaxy samples. These first results suggest that LAMOST spectra are suitable for galaxy velocity dispersion measurements to complement the available catalogs of galaxy internal kinematics in the northern hemisphere. We plan to expand this analysis to next LAMOST data releases.

astro-ph.GA↗

arXiv2020

Dual ResGCN for Balanced Scene GraphGeneration

Visual scene graph generation is a challenging task. Previous works have achieved great progress, but most of them do not explicitly consider the class imbalance issue in scene graph generation. Models learned without considering the class imbalance tend to predict the majority classes, which leads to a good performance on trivial frequent predicates, but poor performance on informative infrequent predicates. However, predicates of minority classes often carry more semantic and precise information~(\textit{e.g.}, \emph{`on'} v.s \emph{`parked on'}). % which leads to a good score of recall, but a poor score of mean recall. To alleviate the influence of the class imbalance, we propose a novel model, dubbed \textit{dual ResGCN}, which consists of an object residual graph convolutional network and a relation residual graph convolutional network. The two networks are complementary to each other. The former captures object-level context information, \textit{i.e.,} the connections among objects. We propose a novel ResGCN that enhances object features in a cross attention manner. Besides, we stack multiple contextual coefficients to alleviate the imbalance issue and enrich the prediction diversity. The latter is carefully designed to explicitly capture relation-level context information \textit{i.e.,} the connections among relations. We propose to incorporate the prior about the co-occurrence of relation pairs into the graph to further help alleviate the class imbalance issue. Extensive evaluations of three tasks are performed on the large-scale database VG to demonstrate the superiority of the proposed method.

cs.CV↗

arXiv2020

Polariton Topological Transition Effects on Radiative Heat Transfer

Twisted two-dimensional bilayer materials exhibit many exotic physical phenomena. Manipulating the twist angle between the two layers enables fine control of the physical structure, resulting in development of many novel physics, such as the magic-angle flat-band superconductivity, the formation of moire exciton and interlayer magnetism. Here, combined with analogous principles, we study theoretically the near-field radiative heat transfer (NFRHT) between two twisted hyperbolic systems. This two twisted hyperbolic systems are mirror images of each other. Each twisted hyperbolic system is composed of two graphene gratings, where there is an angle ϕ between this two graphene gratings. By analyzing the photonic transmission coefficient as well as the plasmon dispersion relation of twisted hyperbolic system, we prove that the topological transitions of the surface state at a special angle (from open (hyperbolic) to closed (elliptical) contours) can modulate efficiently the radiative heat transfer. Meanwhile the role of the thickness of dielectric spacer and vacuum gap on the manipulating the topological transitions of the surface state and the NFRHT are also discussed. We predict the hysteresis effect of topological transitions at a larger vacuum gap, and demonstrate that as thickness of dielectric spacer increase, the transition from the enhancement effect of heat transfer caused by the twisted hyperbolic system to a suppression. This technology could novel mechanism and control method for NFRHT, and may open a promising pathway for highly efficient thermal management, energy harvesting, and subwavelength thermal imaging.

physics.optics↗

arXiv2020

The Discovery of Tunable Universality Class in Superconducting $β$-W Thin Films

The interplay between quenched disorder and critical behavior in quantum phase transitions is conceptually fascinating and of fundamental importance for understanding phase transitions. However, it is still unclear whether or not the quenched disorder influences the universality class of quantum phase transitions. More crucially, the absence of superconducting-metal transitions under in-plane magnetic fields in 2D superconductors imposes constraints on the universality of quantum criticality. Here, we discover the tunable universality class of superconductor-metal transition by changing the disorder strength in $β$-W films with varying thickness. The finite-size scaling uncovers the switch of universality class: quantum Griffiths singularity to multiple quantum criticality at a critical thickness of $t_{c \perp 1}\sim 8 nm$ and then from multiple quantum criticality to single criticality at $t_{c\perp 2}\sim 16 nm$. Moreover, the superconducting-metal transition is observed for the first time under in-plane magnetic fields and the universality class is changed at $t_{c \parallel }\sim 8 nm$. The discovery of tunable universality class under both out-of-plane and in-plane magnetic fields provides broad information for the disorder effect on superconducting-metal transitions and quantum criticality.

cond-mat.supr-con↗

arXiv2020

The existence and decay of solitary waves for the Fornberg-Whitham equation

In this paper, we consider the Fornberg-Whitham equation and a family of solitary wave solutions is found by using minimization principle, where a related penalization function and the concentration-compactness lemma play a key role in our proof. Besides, we also prove that the family of solitary solutions is orbital stable and decay exponentially when speed wave c is bigger than 1.

math.AP↗

arXiv2020

A Relaxed Matching Procedure for Unsupervised BLI

Recently unsupervised Bilingual Lexicon Induction (BLI) without any parallel corpus has attracted much research interest. One of the crucial parts in methods for the BLI task is the matching procedure. Previous works impose a too strong constraint on the matching and lead to many counterintuitive translation pairings. Thus, We propose a relaxed matching procedure to find a more precise matching between two languages. We also find that aligning source and target language embedding space bidirectionally will bring significant improvement. We follow the previous iterative framework to conduct experiments. Results on standard benchmark demonstrate the effectiveness of our proposed method, which substantially outperforms previous unsupervised methods.

cs.CL↗

arXiv2020

Semi-Supervised Bilingual Lexicon Induction with Two-way Interaction

Semi-supervision is a promising paradigm for Bilingual Lexicon Induction (BLI) with limited annotations. However, previous semisupervised methods do not fully utilize the knowledge hidden in annotated and nonannotated data, which hinders further improvement of their performance. In this paper, we propose a new semi-supervised BLI framework to encourage the interaction between the supervised signal and unsupervised alignment. We design two message-passing mechanisms to transfer knowledge between annotated and non-annotated data, named prior optimal transport and bi-directional lexicon update respectively. Then, we perform semi-supervised learning based on a cyclic or a parallel parameter feeding routine to update our models. Our framework is a general framework that can incorporate any supervised and unsupervised BLI methods based on optimal transport. Experimental results on MUSE and VecMap datasets show significant improvement of our models. Ablation study also proves that the two-way interaction between the supervised signal and unsupervised alignment accounts for the gain of the overall performance. Results on distant language pairs further illustrate the advantage and robustness of our proposed method.

cs.CL↗