arXiv subjects

Xin Luo

Publications and source records attributed to Xin Luo.

At least 109 records · Page 6Linked to original sources

arXiv2022

Online Enhanced Semantic Hashing: Towards Effective and Efficient Retrieval for Streaming Multi-Modal Data

With the vigorous development of multimedia equipment and applications, efficient retrieval of large-scale multi-modal data has become a trendy research topic. Thereinto, hashing has become a prevalent choice due to its retrieval efficiency and low storage cost. Although multi-modal hashing has drawn lots of attention in recent years, there still remain some problems. The first point is that existing methods are mainly designed in batch mode and not able to efficiently handle streaming multi-modal data. The second point is that all existing online multi-modal hashing methods fail to effectively handle unseen new classes which come continuously with streaming data chunks. In this paper, we propose a new model, termed Online enhAnced SemantIc haShing (OASIS). We design novel semantic-enhanced representation for data, which could help handle the new coming classes, and thereby construct the enhanced semantic objective function. An efficient and effective discrete online optimization algorithm is further proposed for OASIS. Extensive experiments show that our method can exceed the state-of-the-art models. For good reproducibility and benefiting the community, our code and data are already available in supplementary material and will be made publicly available.

cs.MM↗

arXiv2022

ViT-FOD: A Vision Transformer based Fine-grained Object Discriminator

Recently, several Vision Transformer (ViT) based methods have been proposed for Fine-Grained Visual Classification (FGVC).These methods significantly surpass existing CNN-based ones, demonstrating the effectiveness of ViT in FGVC tasks.However, there are some limitations when applying ViT directly to FGVC.First, ViT needs to split images into patches and calculate the attention of every pair, which may result in heavy redundant calculation and unsatisfying performance when handling fine-grained images with complex background and small objects.Second, a standard ViT only utilizes the class token in the final layer for classification, which is not enough to extract comprehensive fine-grained information. To address these issues, we propose a novel ViT based fine-grained object discriminator for FGVC tasks, ViT-FOD for short. Specifically, besides a ViT backbone, it further introduces three novel components, i.e, Attention Patch Combination (APC), Critical Regions Filter (CRF), and Complementary Tokens Integration (CTI). Thereinto, APC pieces informative patches from two images to generate a new image so that the redundant calculation can be reduced. CRF emphasizes tokens corresponding to discriminative regions to generate a new class token for subtle feature learning. To extract comprehensive information, CTI integrates complementary information captured by class tokens in different ViT layers. We conduct comprehensive experiments on widely used datasets and the results demonstrate that ViT-FOD is able to achieve state-of-the-art performance.

cs.CV↗

arXiv2022

High-order Order Proximity-Incorporated, Symmetry and Graph-Regularized Nonnegative Matrix Factorization for Community Detection

Community describes the functional mechanism of a network, making community detection serve as a fundamental graph tool for various real applications like discovery of social circle. To date, a Symmetric and Non-negative Matrix Factorization (SNMF) model has been frequently adopted to address this issue owing to its high interpretability and scalability. However, most existing SNMF-based community detection methods neglect the high-order connection patterns in a network. Motivated by this discovery, in this paper, we propose a High-Order Proximity (HOP)-incorporated, Symmetry and Graph-regularized NMF (HSGN) model that adopts the following three-fold ideas: a) adopting a weighted pointwise mutual information (PMI)-based approach to measure the HOP indices among nodes in a network; b) leveraging an iterative reconstruction scheme to encode the captured HOP into the network; and c) introducing a symmetry and graph-regularized NMF algorithm to detect communities accurately. Extensive empirical studies on eight real-world networks demonstrate that an HSGN-based community detector significantly outperforms both benchmark and state-of-the-art community detectors in providing highly-accurate community detection results.

cs.SI↗

arXiv2022

Second-order Symmetric Non-negative Latent Factor Analysis

Precise representation of large-scale undirected network is the basis for understanding relations within a massive entity set. The undirected network representation task can be efficiently addressed by a symmetry non-negative latent factor (SNLF) model, whose objective is clearly non-convex. However, existing SNLF models commonly adopt a first-order optimizer that cannot well handle the non-convex objective, thereby resulting in inaccurate representation results. On the other hand, higher-order learning algorithms are expected to make a breakthrough, but their computation efficiency are greatly limited due to the direct manipulation of the Hessian matrix, which can be huge in undirected network representation tasks. Aiming at addressing this issue, this study proposes to incorporate an efficient second-order method into SNLF, thereby establishing a second-order symmetric non-negative latent factor analysis model for undirected network with two-fold ideas: a) incorporating a mapping strategy into SNLF model to form an unconstrained model, and b) training the unconstrained model with a specially designed second order method to acquire a proper second-order step efficiently. Empirical studies indicate that proposed model outperforms state-of-the-art models in representation accuracy with affordable computational burden.

cs.LG↗

arXiv2021

Asymmetric Modality Translation For Face Presentation Attack Detection

Face presentation attack detection (PAD) is an essential measure to protect face recognition systems from being spoofed by malicious users and has attracted great attention from both academia and industry. Although most of the existing methods can achieve desired performance to some extent, the generalization issue of face presentation attack detection under cross-domain settings (e.g., the setting of unseen attacks and varying illumination) remains to be solved. In this paper, we propose a novel framework based on asymmetric modality translation for face presentation attack detection in bi-modality scenarios. Under the framework, we establish connections between two modality images of genuine faces. Specifically, a novel modality fusion scheme is presented that the image of one modality is translated to the other one through an asymmetric modality translator, then fused with its corresponding paired image. The fusion result is fed as the input to a discriminator for inference. The training of the translator is supervised by an asymmetric modality translation loss. Besides, an illumination normalization module based on Pattern of Local Gravitational Force (PLGF) representation is used to reduce the impact of illumination variation. We conduct extensive experiments on three public datasets, which validate that our method is effective in detecting various types of attacks and achieves state-of-the-art performance under different evaluation protocols.

cs.CV↗

arXiv2021

Weakly-Supervised Online Hashing

With the rapid development of social websites, recent years have witnessed an explosive growth of social images with user-provided tags which continuously arrive in a streaming fashion. Due to the fast query speed and low storage cost, hashing-based methods for image search have attracted increasing attention. However, existing hashing methods for social image retrieval are based on batch mode which violates the nature of social images, i.e., social images are usually generated periodically or collected in a stream fashion. Although there exist many online image hashing methods, they either adopt unsupervised learning which ignore the relevant tags, or are designed in the supervised manner which needs high-quality labels. In this paper, to overcome the above limitations, we propose a new method named Weakly-supervised Online Hashing (WOH). In order to learn high-quality hash codes, WOH exploits the weak supervision by considering the semantics of tags and removing the noise. Besides, We develop a discrete online optimization algorithm for WOH, which is efficient and scalable. Extensive experiments conducted on two real-world datasets demonstrate the superiority of WOH compared with several state-of-the-art hashing baselines.

cs.CV↗

arXiv2021

Exploiting Negative Learning for Implicit Pseudo Label Rectification in Source-Free Domain Adaptive Semantic Segmentation

It is desirable to transfer the knowledge stored in a well-trained source model onto non-annotated target domain in the absence of source data. However, state-of-the-art methods for source free domain adaptation (SFDA) are subject to strict limits: 1) access to internal specifications of source models is a must; and 2) pseudo labels should be clean during self-training, making critical tasks relying on semantic segmentation unreliable. Aiming at these pitfalls, this study develops a domain adaptive solution to semantic segmentation with pseudo label rectification (namely \textit{PR-SFDA}), which operates in two phases: 1) \textit{Confidence-regularized unsupervised learning}: Maximum squares loss applies to regularize the target model to ensure the confidence in prediction; and 2) \textit{Noise-aware pseudo label learning}: Negative learning enables tolerance to noisy pseudo labels in training, meanwhile positive learning achieves fast convergence. Extensive experiments have been performed on domain adaptive semantic segmentation benchmark, \textit{GTA5 $\to$ Cityscapes}. Overall, \textit{PR-SFDA} achieves a performance of 49.0 mIoU, which is very close to that of the state-of-the-art counterparts. Note that the latter demand accesses to the source model's internal specifications, whereas the \textit{PR-SFDA} solution needs none as a sharp contrast.

cs.CV↗

arXiv2021

Interactions between Hlawka Type-1 and Type-2 Quantities

The classical Hlawka inequality possesses deep connections with zonotopes and zonoids in convex geometry, and has been related to Minkowski space. We introduce Hlawka Type-1 and Type-2 quantities, and establish a Hlawka-type relation between them, which connects a vast number of strikingly different variants of the Hlawka inequalities, such as Serre's reverse Hlawka inequality in the future cone of the Minkowski space, the Hlawka inequality for subadditive function on abelian group by Ressel, and the integral analogs by Takahasi et al. Besides, we announce several enhanced results, such as the Hlawka inequality for the power of measure function. Particularly, we give a complete study of the Hlawka inequality for quadratic form which relates to a work of Serre.

math.FA↗

arXiv2021

Far-Field Super-Resolution Imaging By Nonlinear Excited Evanescent Waves

Abbe's resolution limit, one of the best-known physical limitations, poses a great challenge for any wave systems in imaging, wave transport, and dynamics. Originally formulated in linear optics, this Abbe's limit can be broken using nonlinear optical interactions. Here we extend the Abbe theory into a nonlinear regime and experimentally demonstrate a far-field, label-free, and scan-free super-resolution imaging technique based on nonlinear four-wave mixing to retrieve near-field scattered evanescent waves, achieving sub-wavelength resolution of $λ/15.6$. This method paves the way for application in biomedical imaging, semiconductor metrology, and photolithography.

physics.optics↗

arXiv2020

Khintchine inequality on normed spaces and the application to Banach-Mazur distance

We establish variant Khintchine inequalities on normed spaces of Hanner type and cotype, in which the Rademacher distribution corresponding to classical Khintchine inequality is replaced by general symmetric distributions. The proof involves the $p$-barycenter and Birkhoff's ergodic theorem. More importantly, by employing these Khintchine inequalities, we get some lower bounds for Banach-Mazur distance between $l^p$-ball and a general centrally symmetric convex body.

math.FA↗

arXiv2020

Transition Metal-Tetracyanoquinodimethane Monolayers as Single-Atom Catalysts for Electrocatalytic Nitrogen Reduction Reaction

Converting earth-abundant dinitrogen into value-added chemical ammonia is a significant yet challenging topic. Electrocatalytic nitrogen reduction reaction (NRR), compared with conventional Haber-Bosch process, is an energy-saving and environmentally friendly approach. The major task of electrocatalytic NRR is to find electrocatalysts which can activate dinitrogen effectively and exhibit high selectivity and stability. Single atom catalysts can act as a good solution. In this work, by means of first-principles density functional theory, molecular dynamics calculations, and a two-step screening process, we confirm that single Sc and Ti atom supported on tetracyanoquinodimethane monolayers (Sc,Ti-TCNQ) are excellent candidates for NRR electrocatalysts. N2 adsorption and activation are effective due to the acceptance-donation mechanism and outstanding electronic structure of TM-TCNQ, and Gibbs free energy diagram shows that Sc-TCNQ and Ti-TCNQ exhibit low NRR overpotential of 0.33 and 0.22 V through enzymatic-consecutive mixed pathway, respectively. In addition, selectivity over HER and stability of Sc/Ti-TCNQ monolayers are also validated. This work opens a new avenue for designing novel single atom catalysts for NRR as well as other catalytic applications.

physics.chem-ph↗

arXiv2020

Spectrum of signless 1-Laplacian on simplicial complexes

We introduce the signless 1-Laplacians and the dual Cheeger constants on simplicial complexes. The connection of its spectrum to the combinatorial properties like independence number, chromatic number and dual Cheeger constant is investigated. Our estimates can be comparable to Hoffman's bounds in virtue of Laplacian on simplicial complexes. An interesting inequality relating multiplicity of the largest eigenvalue, independence number and chromatic number are provided, which could be regarded as a variant version of Lovasz sandwich theorem. Also, the behavior of the operator under the topological operations of wedge and duplication of motifs is studied. The Courant nodal domain theorem in spectral theory is extended to the case of signless 1-Laplacian on complexes.

math.SP↗

arXiv2020

Dual Graph Representation Learning

Graph representation learning embeds nodes in large graphs as low-dimensional vectors and is of great benefit to many downstream applications. Most embedding frameworks, however, are inherently transductive and unable to generalize to unseen nodes or learn representations across different graphs. Although inductive approaches can generalize to unseen nodes, they neglect different contexts of nodes and cannot learn node embeddings dually. In this paper, we present a context-aware unsupervised dual encoding framework, \textbf{CADE}, to generate representations of nodes by combining real-time neighborhoods with neighbor-attentioned representation, and preserving extra memory of known nodes. We exhibit that our approach is effective by comparing to state-of-the-art methods.

cs.LG↗

arXiv2020

Theoretical investigation of two-dimensional phosphorus carbides as promising anode materials for lithium-ion batteries

Employing two-dimensional (2D) materials as anodes for lithium-ion batteries (LIBs) is believed to be an effective approach to meet the growing demands of high-capacity next-generation LIBs. In this work, the first-principles density functional theory (DFT) calculations are employed to evaluate the potential application of two-dimensional phosphorus carbide (2D PCx, x=2, 5, and 6) monolayers as anode materials for lithium-ion batteries. The 2D PCx systems are predicted to show outstanding structural stability and electronic properties. From the nudge elastic band calculations, the Li atoms show extreme high diffusivities on the PCx monolayer with low energy barriers of 0.18 eV for PC2, 0.47 eV for PC5, and 0.44 eV for PC6. We further demonstrate that the theoretical specific capacity of monolayer PC5 and PC6 can reach up to 1251.7 and 1235.9 mAh g-1, respectively, several times that of graphite anode used in commercial LIBs. These results suggest that both PC5 and PC6 monolayer are promising anode materials for LIBs. Our work opens a new avenue to explore novel 2D materials in energy applications, where phosphorus carbides could be used as high-performance anode in LIBs.

physics.app-ph↗

arXiv2020

Origin and Electronic Behavior of Improper Ferroelectricity in AB2 (A=Cr, Mo, W; B=S, Se, Te) Transition Metal Dichalcogenides

Persistent electrical polarized states are fundamentally important to the electric industry as they can be used in the non-volatile memory, the artificial neuromorphic network, and negative capacitors, making ultralow energy consumption electronic devises possible. With the recent development in low dimensional ferroelectric materials, emerging 2D out-of-plane ferroelectric materials like MoTe2 have great potential for future development. Despite previous phenomenological studies, the underlying microscopic origin of ferroelectricity is still missing. Here, using density functional theory and Wannier function methods, we reveal that the origin of ferroelectricity of these transition metal dichalcogenides comes from the Jahn taller effect and followed by a covalent bonding between transition metal atoms. Moreover, the atypical electronic behavior of these monolayer AB2 (A=Cr, Mo, W; B=S, Se, Te) TMDs compare to traditional improper ferroelectrics hints a strong electronic origin of the polarization, suitable for future industrial applications.

cond-mat.mes-hall↗

arXiv2018

Global sensitivity analysis based on DIRECT-KG-HDMR and thermal optimization of pin-fin heat sink for the platform inertial navigation system

In this study, in order to reduce the local high temperature of the platform in inertial navigation system (PINS), a pin-fin heat sink with staggered arrangement is designed. To reduce the dimension of the inputs and improve the efficiency of optimization, a feasible global sensitivity analysis (GSA) based on Kriging-High Dimensional Model Representation with DIviding RECTangles sampling strategy (DIRECT-KG-HDMR) is proposed. Compared with other GSA methods, the proposed method can indicate the effects of the structural and the material parameters on the maximum temperature at the bottom of the heat sink by using both sensitivity and coupling coefficients. From the results of GSA, it can be found that the structural parameters have greater effects on thermal performance than the material ones. Moreover, the coupling intensities between the structural and material parameters are weak. Therefore, the structural parameters are selected to optimize the thermal performance of the heat sink, and several popular optimization algorithms such as GA, DE, TLBO, PSO and EGO are used for the optimization. Moreover, steady thermal response of the PINS with the optimized heat sink is also studied, and its result shows that the maximum temperature of high temperature region of the platform is reduced by 1.09 degree Celsius compared with the PINS without the heat sink.

cs.CE↗

arXiv2018

ConvPath: A Software Tool for Lung Adenocarcinoma Digital Pathological Image Analysis Aided by Convolutional Neural Network

The spatial distributions of different types of cells could reveal a cancer cell growth pattern, its relationships with the tumor microenvironment and the immune response of the body, all of which represent key hallmarks of cancer. However, manually recognizing and localizing all the cells in pathology slides are almost impossible. In this study, we developed an automated cell type classification pipeline, ConvPath, which includes nuclei segmentation, convolutional neural network-based tumor, stromal and lymphocytes classification, and extraction of tumor microenvironment related features for lung cancer pathology images. The overall classification accuracy is 92.9% and 90.1% in training and independent testing datasets, respectively. By identifying cells and classifying cell types, this pipeline can convert a pathology image into a spatial map of tumor, stromal and lymphocyte cells. From this spatial map, we can extracted features that characterize the tumor micro-environment. Based on these features, we developed an image feature-based prognostic model and validated the model in two independent cohorts. The predicted risk group serves as an independent prognostic factor, after adjusting for clinical variables that include age, gender, smoking status, and stage.

cs.CV↗

arXiv2018

A Bayesian model for lithology/fluid class prediction using a Markov mesh prior fitted from a training image

We consider a Bayesian model for inversion of observed amplitude variation with offset (AVO) data into lithology/fluid classes, and study in particular how the choice of prior distribution for the lithology/fluid classes influences the inversion results. Two distinct prior distributions are considered, a simple manually specified Markov random field prior with a first order neighborhood and a Markov mesh model with a much larger neighborhood estimated from a training image. They are chosen to model both horisontal connectivity and vertical thickness distribution of the lithology/fluid classes, and are compared on an offshore clastic oil reservoir in the North Sea. We combine both priors with the same linearised Gaussian likelihood function based on a convolved linearised Zoeppritz relation and estimate properties of the resulting two posterior distributions by simulating from these distributions with the Metropolis-Hastings algorithm. The influence of the prior on the marginal posterior probabilities for the lithology/fluid classes is clearly observable, but modest. The importance of the prior on the connectivity properties in the posterior realisations, however, is much stronger. The larger neighborhood of the Markov mesh prior enables it to identify and model connectivity and curvature much better than what can be done by the first order neighborhood Markov random field prior. As a result, we conclude that the posterior realisations based on the Markov mesh prior appear with much higher lateral connectivity, which is geologically plausible.

stat.AP↗