arXiv subjects

Yang Wang

Publications and source records attributed to Yang Wang.

At least 685 records · Page 38Linked to original sources

arXiv2020

Cross-Modal Weighting Network for RGB-D Salient Object Detection

Depth maps contain geometric clues for assisting Salient Object Detection (SOD). In this paper, we propose a novel Cross-Modal Weighting (CMW) strategy to encourage comprehensive interactions between RGB and depth channels for RGB-D SOD. Specifically, three RGB-depth interaction modules, named CMW-L, CMW-M and CMW-H, are developed to deal with respectively low-, middle- and high-level cross-modal information fusion. These modules use Depth-to-RGB Weighing (DW) and RGB-to-RGB Weighting (RW) to allow rich cross-modal and cross-scale interactions among feature layers generated by different network blocks. To effectively train the proposed Cross-Modal Weighting Network (CMWNet), we design a composite loss function that summarizes the errors between intermediate predictions and ground truth over different scales. With all these novel components working together, CMWNet effectively fuses information from RGB and depth channels, and meanwhile explores object localization and details across scales. Thorough evaluations demonstrate CMWNet consistently outperforms 15 state-of-the-art RGB-D SOD methods on seven popular benchmarks.

cs.CV↗

arXiv2020

Recurrent Relational Memory Network for Unsupervised Image Captioning

Unsupervised image captioning with no annotations is an emerging challenge in computer vision, where the existing arts usually adopt GAN (Generative Adversarial Networks) models. In this paper, we propose a novel memory-based network rather than GAN, named Recurrent Relational Memory Network ($R^2M$). Unlike complicated and sensitive adversarial learning that non-ideally performs for long sentence generation, $R^2M$ implements a concepts-to-sentence memory translator through two-stage memory mechanisms: fusion and recurrent memories, correlating the relational reasoning between common visual concepts and the generated words for long periods. $R^2M$ encodes visual context through unsupervised training on images, while enabling the memory to learn from irrelevant textual corpus via supervised fashion. Our solution enjoys less learnable parameters and higher computational efficiency than GAN-based methods, which heavily bear parameter sensitivity. We experimentally validate the superiority of $R^2M$ than state-of-the-arts on all benchmark datasets.

cs.CV↗

arXiv2020

Riemannian Newton-CG Methods for Constructing a Positive Doubly Stochastic Matrix From Spectral Data

In this paper, we consider the inverse eigenvalue problem for the positive doubly stochastic matrices, which aims to construct a positive doubly stochastic matrix from the prescribed realizable spectral data. By using the real Schur decomposition, the inverse problem is written as a nonlinear matrix equation on a matrix product manifold. We propose monotone and nonmonotone Riemannian inexact Newton-CG methods for solving the nonlinear matrix equation. The global and quadratic convergence of the proposed methods is established under some assumptions. We also provide invariant subspaces of the constructed solution to the inverse problem based on the computed real Schur decomposition. Finally, we report some numerical tests, including an application in digraph, to illustrate the effectiveness of the proposed methods.

math.NA↗

arXiv2020

Dissecting a square into congruent polygons

We study the dissection of a square into congruent convex polygons. Yuan \emph{et al.} [Dissecting the square into five congruent parts, Discrete Math. \textbf{339} (2016) 288-298] asked whether, if the number of tiles is a prime number $\geq 3$, it is true that the tile must be a rectangle. We conjecture that the same conclusion still holds even if the number of tiles is an odd number $\geq 3$. Our conjecture has been confirmed for triangles in earlier works. We prove that the conjecture holds if either the tile is a convex $q$-gon with $q\geq 6$ or it is a right-angle trapezoid.

math.CO↗

arXiv2020

Unsupervised Vehicle Re-identification with Progressive Adaptation

Vehicle re-identification (reID) aims at identifying vehicles across different non-overlapping cameras views. The existing methods heavily relied on well-labeled datasets for ideal performance, which inevitably causes fateful drop due to the severe domain bias between the training domain and the real-world scenes; worse still, these approaches required full annotations, which is labor-consuming. To tackle these challenges, we propose a novel progressive adaptation learning method for vehicle reID, named PAL, which infers from the abundant data without annotations. For PAL, a data adaptation module is employed for source domain, which generates the images with similar data distribution to unlabeled target domain as ``pseudo target samples''. These pseudo samples are combined with the unlabeled samples that are selected by a dynamic sampling strategy to make training faster. We further proposed a weighted label smoothing (WLS) loss, which considers the similarity between samples with different clusters to balance the confidence of pseudo labels. Comprehensive experimental results validate the advantages of PAL on both VehicleID and VeRi-776 dataset.

cs.CV↗

arXiv2020

Recovering Accurate Labeling Information from Partially Valid Data for Effective Multi-Label Learning

Partial Multi-label Learning (PML) aims to induce the multi-label predictor from datasets with noisy supervision, where each training instance is associated with several candidate labels but only partially valid. To address the noisy issue, the existing PML methods basically recover the ground-truth labels by leveraging the ground-truth confidence of the candidate label, \ie the likelihood of a candidate label being a ground-truth one. However, they neglect the information from non-candidate labels, which potentially contributes to the ground-truth label recovery. In this paper, we propose to recover the ground-truth labels, \ie estimating the ground-truth confidences, from the label enrichment, composed of the relevance degrees of candidate labels and irrelevance degrees of non-candidate labels. Upon this observation, we further develop a novel two-stage PML method, namely \emph{\underline{P}artial \underline{M}ulti-\underline{L}abel \underline{L}earning with \underline{L}abel \underline{E}nrichment-\underline{R}ecovery} (\baby), where in the first stage, it estimates the label enrichment with unconstrained label propagation, then jointly learns the ground-truth confidence and multi-label predictor given the label enrichment. Experimental results validate that \baby outperforms the state-of-the-art PML methods.

cs.LG↗

arXiv2020

Few-Shot Scene Adaptive Crowd Counting Using Meta-Learning

We consider the problem of few-shot scene adaptive crowd counting. Given a target camera scene, our goal is to adapt a model to this specific scene with only a few labeled images of that scene. The solution to this problem has potential applications in numerous real-world scenarios, where we ideally like to deploy a crowd counting model specially adapted to a target camera. We accomplish this challenge by taking inspiration from the recently introduced learning-to-learn paradigm in the context of few-shot regime. In training, our method learns the model parameters in a way that facilitates the fast adaptation to the target scene. At test time, given a target scene with a small number of labeled data, our method quickly adapts to that scene with a few gradient updates to the learned parameters. Our extensive experimental results show that the proposed approach outperforms other alternatives in few-shot scene adaptive crowd counting. Code is available at https://github.com/maheshkkumar/fscc.

cs.CV↗

arXiv2020

Automated Radiological Report Generation For Chest X-Rays With Weakly-Supervised End-to-End Deep Learning

The chest X-Ray (CXR) is the one of the most common clinical exam used to diagnose thoracic diseases and abnormalities. The volume of CXR scans generated daily in hospitals is huge. Therefore, an automated diagnosis system able to save the effort of doctors is of great value. At present, the applications of artificial intelligence in CXR diagnosis usually use pattern recognition to classify the scans. However, such methods rely on labeled databases, which are costly and usually have large error rates. In this work, we built a database containing more than 12,000 CXR scans and radiological reports, and developed a model based on deep convolutional neural network and recurrent network with attention mechanism. The model learns features from the CXR scans and the associated raw radiological reports directly; no additional labeling of the scans are needed. The model provides automated recognition of given scans and generation of reports. The quality of the generated reports was evaluated with both the CIDEr scores and by radiologists as well. The CIDEr scores are found to be around 5.8 on average for the testing dataset. Further blind evaluation suggested a comparable performance against human radiologist.

cs.CV↗

arXiv2020

Survey on Deep Multi-modal Data Analytics: Collaboration, Rivalry and Fusion

With the development of web technology, multi-modal or multi-view data has surged as a major stream for big data, where each modal/view encodes individual property of data objects. Often, different modalities are complementary to each other. Such fact motivated a lot of research attention on fusing the multi-modal feature spaces to comprehensively characterize the data objects. Most of the existing state-of-the-art focused on how to fuse the energy or information from multi-modal spaces to deliver a superior performance over their counterparts with single modal. Recently, deep neural networks have exhibited as a powerful architecture to well capture the nonlinear distribution of high-dimensional multimedia data, so naturally does for multi-modal data. Substantial empirical studies are carried out to demonstrate its advantages that are benefited from deep multi-modal methods, which can essentially deepen the fusion from multi-modal deep feature spaces. In this paper, we provide a substantial overview of the existing state-of-the-arts on the filed of multi-modal data analytics from shallow to deep spaces. Throughout this survey, we further indicate that the critical components for this field go to collaboration, adversarial competition and fusion over multi-modal spaces. Finally, we share our viewpoints regarding some future directions on this field.

cs.CV↗

arXiv2020

Utilizing machine learning to prevent water main breaks by understanding pipeline failure drivers

Data61 and Western Water worked collaboratively to apply engineering expertise and Machine Learning tools to find a cost-effective solution to the pipe failure problem in the region west of Melbourne, where on average 400 water main failures occur per year. To achieve this objective, we constructed a detailed picture and understanding of the behaviour of the water pipe network by 1) discovering the underlying drivers of water main breaks, and 2) developing a Machine Learning system to assess and predict the failure likelihood of water main breaking using historical failure records, descriptors of pipes, and other environmental factors. The ensuing results open up an avenue for Western Water to identify the priority of pipe renewals

cs.CY↗

arXiv2020

Ontology-based systematic classification and analysis of coronaviruses, hosts, and host-coronavirus interactions towards deep understanding of COVID-19

Given the existing COVID-19 pandemic worldwide, it is critical to systematically study the interactions between hosts and coronaviruses including SARS-Cov, MERS-Cov, and SARS-CoV-2 (cause of COVID-19). We first created four host-pathogen interaction (HPI)-Outcome postulates, and generated a HPI-Outcome model as the basis for understanding host-coronavirus interactions (HCI) and their relations with the disease outcomes. We hypothesized that ontology can be used as an integrative platform to classify and analyze HCI and disease outcomes. Accordingly, we annotated and categorized different coronaviruses, hosts, and phenotypes using ontologies and identified their relations. Various COVID-19 phenotypes are hypothesized to be caused by the backend HCI mechanisms. To further identify the causal HCI-outcome relations, we collected 35 experimentally-verified HCI protein-protein interactions (PPIs), and applied literature mining to identify additional host PPIs in response to coronavirus infections. The results were formulated in a logical ontology representation for integrative HCI-outcome understanding. Using known PPIs as baits, we also developed and applied a domain-inferred prediction method to predict new PPIs and identified their pathological targets on multiple organs. Overall, our proposed ontology-based integrative framework combined with computational predictions can be used to support fundamental understanding of the intricate interactions between human patients and coronaviruses (including SARS-CoV-2) and their association with various disease outcomes.

q-bio.OT↗

arXiv2020

Try This Instead: Personalized and Interpretable Substitute Recommendation

As a fundamental yet significant process in personalized recommendation, candidate generation and suggestion effectively help users spot the most suitable items for them. Consequently, identifying substitutable items that are interchangeable opens up new opportunities to refine the quality of generated candidates. When a user is browsing a specific type of product (e.g., a laptop) to buy, the accurate recommendation of substitutes (e.g., better equipped laptops) can offer the user more suitable options to choose from, thus substantially increasing the chance of a successful purchase. However, existing methods merely treat this problem as mining pairwise item relationships without the consideration of users' personal preferences. Moreover, the substitutable relationships are implicitly identified through the learned latent representations of items, leading to uninterpretable recommendation results. In this paper, we propose attribute-aware collaborative filtering (A2CF) to perform substitute recommendation by addressing issues from both personalization and interpretability perspectives. Instead of directly modelling user-item interactions, we extract explicit and polarized item attributes from user reviews with sentiment analysis, whereafter the representations of attributes, users, and items are simultaneously learned. Then, by treating attributes as the bridge between users and items, we can thoroughly model the user-item preferences (i.e., personalization) and item-item relationships (i.e., substitution) for recommendation. In addition, A2CF is capable of generating intuitive interpretations by analyzing which attributes a user currently cares the most and comparing the recommended substitutes with her/his currently browsed items at an attribute level. The recommendation effectiveness and interpretation quality of A2CF are demonstrated via extensive experiments on three real datasets.

cs.IR↗

arXiv2020

Spectrum is rational in dimension one

A bounded measurable set $Ω\subset{\mathbb R}^d$ is called a spectral set if it admits some exponential orthonormal basis $\{e^{2πi \langleλ,x\rangle}: λ\inΛ\}$ for $L^2(Ω)$. In this paper, we show that in dimension one $d=1$, any spectrum $Λ$ with $0\inΛ$ of a spectral set $Ω$ with Lebesgue measure normalized to 1 must be rational. Combining previous results that spectrum must be periodic, the Fuglede's conjecture on ${\mathbb R}^1$ is now equivalent to the corresponding conjecture on all cyclic groups ${\mathbb Z}_{n}.$

math.FA↗

arXiv2020

SimpleMKKM: Simple Multiple Kernel K-means

We propose a simple yet effective multiple kernel clustering algorithm, termed simple multiple kernel k-means (SimpleMKKM). It extends the widely used supervised kernel alignment criterion to multi-kernel clustering. Our criterion is given by an intractable minimization-maximization problem in the kernel coefficient and clustering partition matrix. To optimize it, we re-formulate the problem as a smooth minimization one, which can be solved efficiently using a reduced gradient descent algorithm. We theoretically analyze the performance of SimpleMKKM in terms of its clustering generalization error. Comprehensive experiments on 11 benchmark datasets demonstrate that SimpleMKKM outperforms state of the art multi-kernel clustering alternatives.

cs.LG↗

arXiv2020

Barred galaxies in the Illustris-1 and TNG100 simulations

We carry out a comparison study on the bar structure in the Illustris-1 and TNG100 simulations. At $z=0$, 8.9\% of 1232 disc galaxies with stellar mass $>10^{10.5}M_{\odot}$ in Illustris-1 are barred, while the numbers are 55\% of 1269 in TNG100. The bar fraction as a function of stellar mass in TNG100 agrees well with the survey $S^4G$. The median redshift of bar formation are $\sim 0.4-0.5$ and $\sim 0.25$ in TNG100 and Illustris-1 respectively. Bar fraction generally increases with stellar mass and decreases with gas fraction in both simulations. Barred galaxy had higher gas fraction at high redshift tend to form bar later. When the bars were formed, the disc gas fractions were mostly lower than 0.4. The much higher bar fraction in TNG100 probably have benefit from much lower gas fraction in massive disc galaxies since $z\sim3$, which may result from the combination of more effective stellar and AGN feedback. The latter may be the primary factor at $z<2$. Meanwhile, in both simulations, barred galaxies have higher star formation rate before bar formation, and stronger AGN feedback all the time than unbarred galaxies. The properties of dark matter halos hosting massive disc galaxies are similar between two simulations, and should have minor effect on the different bar frequency. For individual galaxies under similar halo environment cross two simulations, different baryonic physics can lead to striking discrepancy on morphology. The morphology of individual galaxies is subject to combined effects of environment and internal baryonic physics, and is often not predictable.

astro-ph.GA↗

arXiv2020

Satellite Alignment: III. Satellite Galaxies Spatial Distribution and their Dependence on Redshift with A Novel Galaxy Finder

After extensively explored, broad agreement between observations and theories has been reached that satellites are preferentially aligned with major axes of their host centrals. There are still some issues unsolved on this topic. In this paper, we present studies on satellite spatial distribution. To fairly compare with observations, we develop a novel galaxy finder and reconstruction algorithm in hydrodynamical simulation, which is based on the projected mock image, taking into account the full consideration of the point spread function, pixel size, surface brightness limit, resolution and redshift dimming effects. With galaxy samples constructed using such an algorithm, the satellite alignment is examined by comparing with observational results. It is found that the observational alignment can be reproduced for red galaxies, which dominate the sample in this study, but not for blue galaxies. Satellites' radial distribution is also investigated. It exhibits that outer satellites within host halos show stronger alignment signal than satellites in the inner regions, especially for red satellites, which is in contrast with previous studies. The disagreement is mainly due to extra galaxies identified by our new galaxy finder, which are mainly located in the inner region of host halos. Our study illustrates that at lower redshift, the alignment strength becomes stronger, while radial distribution curve becomes flatter. This suggests differences in the evolution of the angular distribution between satellites residing in the inner and outer halos, and implies that the post-infall evolution reduces the original alignment signal, that the impact decreases for satellites with later infall times.

astro-ph.GA↗

arXiv2020

Long distance measurement using single soliton microcomb

Dispersive interferometry (DPI) takes a major interest in optical frequency comb (OFC) based long distance laser-based light detection and ranging (LIDAR) for the merits of strong anti-interference ability and long coherent length. However, the mismatch between the repetition rate of OFC and the resolution of optical spectrum acquisition system induces a large dead-zone which is a major obstacle for practical applications. Here, a new DPI LIDAR on the strength of high-repetition-rate soliton microcomb is demonstrated, which reaches a minimum Allan deviation of 27 nm for an outdoor 1179 m ranging experiment. The proposed scheme approaches a compact, high-accuracy, and none-dead-zone long distance ranging system, opening up new opportunities for emerging applications of frontier scientific researches and advanced manufacturing.

physics.ins-det↗

arXiv2020

Tunable capacitance in all-inkjet-printed nanosheet heterostructures

Heterostructures constructed from two-dimensional building blocks have shown promise for field-effect transistors, memory devices, photosensors and other electronic applications1,2. 2D nanosheet crystals can be constructed into multilayer heterostructures using layer-by-layer methods3, but that method cannot be used to fabricate large-scale and thick heterostructures, due to the time-consuming nature and low efficiency of the process. An alternative approach to deposit different two-dimensional materials is by inkjet printing4-7. Here we show the fabrication of a nanosheet supercapacitor by inkjet printing Ti3C2Tx MXene nanosheets as electrodes, and graphene oxide nanosheets as solid-state electrolyte. The free water molecules trapped between graphene oxide sheets facilitate proton movement through the layered solid electrolyte8. The as-made supercapacitor shows high areal capacitance, good cycling stability and high areal energy and power densities comparable with existing printed supercapacitors. Moreover, the specific capacitance can be increased further by addition of liquid electrolytes.

physics.chem-ph↗