arXiv subjects

Yang Xiao

Publications and source records attributed to Yang Xiao.

At least 253 records · Page 14Linked to original sources

arXiv2021

1st Place Solution for the UVO Challenge on Image-based Open-World Segmentation 2021

We describe our two-stage instance segmentation framework we use to compete in the challenge. The first stage of our framework consists of an object detector, which generates object proposals in the format of bounding boxes. Then, the images and the detected bounding boxes are fed to the second stage, where a segmentation network is applied to segment the objects in the bounding boxes. We train all our networks in a class-agnostic way. Our approach achieves the first place in the UVO 2021 Image-based Open-World Segmentation Challenge.

cs.CV↗

arXiv2021

Nonlinear level attraction of cavity axion polariton in antiferromagnetic topological insulator

Strong coupling between cavity photons and various excitations in condensed matters boosts the field of light-matter interaction and generates several exciting sub-fields, such as cavity optomechanics and cavity magnon polariton. Axion quasiparticles, emerging in topological insulators, were predicted to strongly couple with the light and generate the so-called axion polariton. Here, we demonstrate that there arises a gapless level attraction in cavity axion polariton of antiferromagnetic topological insulators, which originates from a nonlinear interaction between axion and the odd-order resonance of cavity. Such a novel level attraction is essentially different from conventional level attractions with the mechanism of either a linear coupling or a dissipation-mediated interaction, and also different from the level repulsion induced by the strong coupling in common polaritons. Our results reveal a new mechanism of level attractions, and open up new roads for exploring the axion polariton with cavity technologies. They have potential applications for quantum information and dark matter research.

cond-mat.mes-hall↗

arXiv2021

Learning to Better Segment Objects from Unseen Classes with Unlabeled Videos

The ability to localize and segment objects from unseen classes would open the door to new applications, such as autonomous object learning in active vision. Nonetheless, improving the performance on unseen classes requires additional training data, while manually annotating the objects of the unseen classes can be labor-extensive and expensive. In this paper, we explore the use of unlabeled video sequences to automatically generate training data for objects of unseen classes. It is in principle possible to apply existing video segmentation methods to unlabeled videos and automatically obtain object masks, which can then be used as a training set even for classes with no manual labels available. However, our experiments show that these methods do not perform well enough for this purpose. We therefore introduce a Bayesian method that is specifically designed to automatically create such a training set: Our method starts from a set of object proposals and relies on (non-realistic) analysis-by-synthesis to select the correct ones by performing an efficient optimization over all the frames simultaneously. Through extensive experiments, we show that our method can generate a high-quality training set which significantly boosts the performance of segmenting objects of unseen classes. We thus believe that our method could open the door for open-world instance segmentation using abundant Internet videos.

cs.CV↗

arXiv2021

Remote generation of magnon Schrödinger cat state via magnon-photon entanglement

Magnon cat state represents a macroscopic quantum superposition of collective magnetic excitations of large number spins that not only provides fundamental tests of macroscopic quantum effects but also finds applications in quantum metrology and quantum computation. In particular, remote generation and manipulation of Schrödinger cat states are particularly interesting for the development of long-distance and large-scale quantum information processing. Here, we propose an approach to remotely prepare magnon even/odd cat states by performing local non-Gaussian operations on the optical mode that is entangled with magnon mode through pulsed optomagnonic interaction. By evaluating key properties of the resulting cat states, we show that for experimentally feasible parameters they are generated with both high fidelity and nonclassicality, and with a size large enough to be useful for quantum technologies. Furthermore, the effects of experimental imperfections such as the error of projective measurements and dark count when performing single-photon operations have been discussed, where the lifetime of the created magnon cat states is expected to be $t\sim1\,μ$s.

quant-ph↗

arXiv2021

GUT-scale constrained SUSY in light of E989 muon g-2 measurement

The new FNAL result of the muon $g-2$, combined with the BNL result, shows a 4.2$σ$ deviation from the SM. We use the new data of the muon $g-2$ to revisit several GUT-scale constrained SUSY models with the constraints from the LHC searches, the dark matter detection, the flavor data and the electroweak vacuum stability. We first demonstrate the tension between the muon $g-2$ and other experimental measurements in the CMSSM/mSUGRA. Then after discussing the possible ways to alleviate such a tension and showing the muon $g-2$ in pMSSM under relevant experimental constraints, we survey several extensions of the CMSSM/mSUGRA with different types of universal boundary conditions at the GUT scale. Finally, we briefly discuss the muon $g-2$ in other popular SUSY breaking mechanisms, namely the GMSB and AMSB mechanisms and their extensions.

hep-ph↗

arXiv2021

ExplainaBoard: An Explainable Leaderboard for NLP

With the rapid development of NLP research, leaderboards have emerged as one tool to track the performance of various systems on various NLP tasks. They are effective in this goal to some extent, but generally present a rather simplistic one-dimensional view of the submitted systems, communicated only through holistic accuracy numbers. In this paper, we present a new conceptualization and implementation of NLP evaluation: the ExplainaBoard, which in addition to inheriting the functionality of the standard leaderboard, also allows researchers to (i) diagnose strengths and weaknesses of a single system (e.g.~what is the best-performing system bad at?) (ii) interpret relationships between multiple systems. (e.g.~where does system A outperform system B? What if we combine systems A, B, and C?) and (iii) examine prediction results closely (e.g.~what are common errors made by multiple systems, or in what contexts do particular errors occur?). So far, ExplainaBoard covers more than 400 systems, 50 datasets, 40 languages, and 12 tasks. ExplainaBoard keeps updated and is recently upgraded by supporting (1) multilingual multi-task benchmark, (2) meta-evaluation, and (3) more complicated task: machine translation, which reviewers also suggested.} We not only released an online platform on the website \url{http://explainaboard.nlpedia.ai/} but also make our evaluation tool an API with MIT Licence at Github \url{https://github.com/neulab/explainaBoard} and PyPi \url{https://pypi.org/project/interpret-eval/} that allows users to conveniently assess their models offline. We additionally release all output files from systems that we have run or collected to motivate "output-driven" research in the future.

cs.CL↗

arXiv2021

Curriculum CycleGAN for Textual Sentiment Domain Adaptation with Multiple Sources

Sentiment analysis of user-generated reviews or comments on products and services in social networks can help enterprises to analyze the feedback from customers and take corresponding actions for improvement. To mitigate large-scale annotations on the target domain, domain adaptation (DA) provides an alternate solution by learning a transferable model from other labeled source domains. Existing multi-source domain adaptation (MDA) methods either fail to extract some discriminative features in the target domain that are related to sentiment, neglect the correlations of different sources and the distribution difference among different sub-domains even in the same source, or cannot reflect the varying optimal weighting during different training stages. In this paper, we propose a novel instance-level MDA framework, named curriculum cycle-consistent generative adversarial network (C-CycleGAN), to address the above issues. Specifically, C-CycleGAN consists of three components: (1) pre-trained text encoder which encodes textual input from different domains into a continuous representation space, (2) intermediate domain generator with curriculum instance-level adaptation which bridges the gap across source and target domains, and (3) task classifier trained on the intermediate domain for final sentiment classification. C-CycleGAN transfers source samples at instance-level to an intermediate domain that is closer to the target domain with sentiment semantics preserved and without losing discriminative features. Further, our dynamic instance-level weighting mechanisms can assign the optimal weights to different source samples in each training stage. We conduct extensive experiments on three benchmark datasets and achieve substantial gains over state-of-the-art DA approaches. Our source code is released at: https://github.com/WArushrush/Curriculum-CycleGAN.

cs.CL↗

arXiv2020

Two-Pion-Exchange contributions to the nucleon-nucleon interactions in covariant baryon chiral perturbation theory

Employing the covariant baryon chiral perturbation theory, we calculate the leading and next-to-leading order two-pion exchange (TPE) contributions to $NN$ interaction up to order $O(p^3)$. We compare the so-obtained $NN$ phase shifts with $2\leq L\leq 6$ and mixing angles with $2\leq J\leq6$ with those obtained in the nonrelativistic baryon chiral perturbation theory, which allows us to check the relativistic corrections to the medium-range part of $NN$ interactions. We show that the contributions of relativistic TPE are more moderate than those of the nonrelativistic TPE. The relativistic corrections play an important role in F-waves especially the $^3\text{F}_2$ partial wave. Moreover, the relativistic results seem to converge faster than the nonrelativistic results in almost all the partial waves studied in the present work, consistent with the studies performed in the one-baryon sector.

nucl-th↗

arXiv2020

$Λ_c N$ interaction in leading order covariant chiral effective field theory

We study the $Λ_c N$ interaction in the covariant chiral effective field theory (ChEFT) at leading order. All the relevant low-energy constants are determined by fitting to the lattice QCD simulations from the HAL QCD Collaboration. Extrapolating the results to the physical point, we show that the $Λ_c N$ interaction is weakly attractive in the $^1S_0$ channel, but in the $^3S_1$ channel, it is only attractive at extremely low energies and soon turns repulsive for larger laboratory energy. Furthermore, we show that the neglect of the $^3S_1-{}^3D_1$ coupling provided by the leading order covariant ChEFT would result in an attractive interaction in the $^3S_1$ channel at the physical point, which coincides with the previous non-relatistic ChEFT study. As a byproduct, we predict the $^3D_1$ phase shifts and the mixing angel $\varepsilon_1$, which can be checked by future lattice QCD simulations. In addition, we compare the $Λ_c N$ interaction with the $ΛN$ and $NN$ interactions to study how the baryon-nucleon ($BN$) interactions evolve as a function of the baryon mass with the replacement of a light quark by a strange or charm quark in the baryon ($B$).

nucl-th↗

arXiv2020

Pion-mass dependence of the nucleon-nucleon interaction

Nucleon-nucleon interactions, both bare and effective, play an important role in our understanding of the non-perturbative strong interaction, as well as nuclear structure and reactions. In recent years, tremendous efforts have been seen in the lattice QCD community to derive nucleon-nucleon interactions from first principles. Because of the daunting computing resources needed, most of such simulations were still performed with larger than physical light quark masses. In the present work, employing the recently proposed covariant chiral effective field theory (ChEFT), we study the light quark mass dependence of the nucleon-nucleon interaction extracted by the HALQCD group. It is shown that the pion-full version of the ChEFT can describe the lattice QCD data with $m_π=469$ MeV and their experimental counterpart reasonably well, while the pion-less version can describe the lattice QCD data with $m_π=672, 837, 1015, 1171$ MeV, for both the $^1S_0$ and $^3S_1$-$^3D_1$ channels. The slightly better description of the single channel than the triplet channel indicates that higher order studies are necessary for the latter. Our results confirmed previous studies that the nucleon-nucleon interaction becomes more attractive for both the singlet and triplet channels as the pion mass decreases towards its physical value. It is shown that the virtual bound state in the $^1S_0$ channel remains virtual down to the chiral limit, while the deuteron only appears for a pion mass smaller than about 400 MeV. It seems that proper chiral extrapolations of nucleon-nucleon interaction are possible for pion masses smaller than 500 MeV, similar to the mesonic and one-baryon sectors.

nucl-th↗

arXiv2020

Measuring Generalisation to Unseen Viewpoints, Articulations, Shapes and Objects for 3D Hand Pose Estimation under Hand-Object Interaction

We study how well different types of approaches generalise in the task of 3D hand pose estimation under single hand scenarios and hand-object interaction. We show that the accuracy of state-of-the-art methods can drop, and that they fail mostly on poses absent from the training set. Unfortunately, since the space of hand poses is highly dimensional, it is inherently not feasible to cover the whole space densely, despite recent efforts in collecting large-scale training datasets. This sampling problem is even more severe when hands are interacting with objects and/or inputs are RGB rather than depth images, as RGB images also vary with lighting conditions and colors. To address these issues, we designed a public challenge (HANDS'19) to evaluate the abilities of current 3D hand pose estimators (HPEs) to interpolate and extrapolate the poses of a training set. More exactly, HANDS'19 is designed (a) to evaluate the influence of both depth and color modalities on 3D hand pose estimation, under the presence or absence of objects; (b) to assess the generalisation abilities w.r.t. four main axes: shapes, articulations, viewpoints, and objects; (c) to explore the use of a synthetic hand model to fill the gaps of current datasets. Through the challenge, the overall accuracy has dramatically improved over the baseline, especially on extrapolation tasks, from 27mm to 13mm mean joint error. Our analyses highlight the impacts of: Data pre-processing, ensemble approaches, the use of a parametric 3D hand model (MANO), and different HPE methods/backbones.

cs.CV↗

arXiv2020

Modeling the Impact of Network Connectivity on Consensus Security of Proof-of-Work Blockchain

Blockchain, the technology behind the popular Bitcoin, is considered a "security by design" system as it is meant to create security among a group of distrustful parties yet without a central trusted authority. The security of blockchain relies on the premise of honest-majority, namely, the blockchain system is assumed to be secure as long as the majority of consensus voting power is honest. And in the case of proof-of-work (PoW) blockchain, adversaries cannot control more than 50% of the network's gross computing power. However, this 50% threshold is based on the analysis of computing power only, with implicit and idealistic assumptions on the network and node behavior. Recent researches have alluded that factors such as network connectivity, presence of blockchain forks, and mining strategy could undermine the consensus security assured by the honest-majority, but neither concrete analysis nor quantitative evaluation is provided. In this paper we fill the gap by proposing an analytical model to assess the impact of network connectivity on the consensus security of PoW blockchain under different adversary models. We apply our analytical model to two adversarial scenarios: 1) honest-but-potentially-colluding, 2) selfish mining. For each scenario, we quantify the communication capability of nodes involved in a fork race and estimate the adversary's mining revenue and its impact on security properties of the consensus protocol. Simulation results validated our analysis. Our modeling and analysis provide a paradigm for assessing the security impact of various factors in a distributed consensus system.

cs.CR↗

arXiv2020

Deep Learning Methods for Lung Cancer Segmentation in Whole-slide Histopathology Images -- the ACDC@LungHP Challenge 2019

Accurate segmentation of lung cancer in pathology slides is a critical step in improving patient care. We proposed the ACDC@LungHP (Automatic Cancer Detection and Classification in Whole-slide Lung Histopathology) challenge for evaluating different computer-aided diagnosis (CADs) methods on the automatic diagnosis of lung cancer. The ACDC@LungHP 2019 focused on segmentation (pixel-wise detection) of cancer tissue in whole slide imaging (WSI), using an annotated dataset of 150 training images and 50 test images from 200 patients. This paper reviews this challenge and summarizes the top 10 submitted methods for lung cancer segmentation. All methods were evaluated using the false positive rate, false negative rate, and DICE coefficient (DC). The DC ranged from 0.7354$\pm$0.1149 to 0.8372$\pm$0.0858. The DC of the best method was close to the inter-observer agreement (0.8398$\pm$0.0890). All methods were based on deep learning and categorized into two groups: multi-model method and single model method. In general, multi-model methods were significantly better ($\textit{p}$<$0.01$) than single model methods, with mean DC of 0.7966 and 0.7544, respectively. Deep learning based methods could potentially help pathologists find suspicious regions for further analysis of lung cancer in WSI.

eess.IV↗

arXiv2020

Pixel-Pair Occlusion Relationship Map(P2ORM): Formulation, Inference & Application

We formalize concepts around geometric occlusion in 2D images (i.e., ignoring semantics), and propose a novel unified formulation of both occlusion boundaries and occlusion orientations via a pixel-pair occlusion relation. The former provides a way to generate large-scale accurate occlusion datasets while, based on the latter, we propose a novel method for task-independent pixel-level occlusion relationship estimation from single images. Experiments on a variety of datasets demonstrate that our method outperforms existing ones on this task. To further illustrate the value of our formulation, we also propose a new depth map refinement method that consistently improve the performance of state-of-the-art monocular depth estimation methods. Our code and data are available at http://imagine.enpc.fr/~qiux/P2ORM/.

cs.CV↗

arXiv2020

PrivacyGuard: Enforcing Private Data Usage Control with Blockchain and Attested Off-chain Contract Execution

The abundance and rich varieties of data are enabling many transformative applications of big data analytics that have profound societal impacts. However, there are also increasing concerns regarding the improper use of individual data owner's private data. In this paper, we propose PrivacyGuard, a system that leverages blockchain smart contract and trusted execution environment (TEE) to enable individual's control over the access and usage of their private data. Smart contracts are used to specify data usage policy, i.e., who can use what data under which conditions and what analytics to perform, while the distributed blockchain ledger is used to keep an irreversible and non-repudiable data usage record. To address the efficiency problem of on-chain contract execution and to prevent exposing private data on the publicly viewable blockchain, PrivacyGuard incorporates a novel TEE-based off-chain contract execution engine along with a protocol to securely commit the execution result onto blockchain. We have built and deployed a prototype of PrivacyGuard with Ethereum and Intel SGX. Our experiment result demonstrates that PrivacyGuard fulfills the promised privacy goal and supports analytics on data from a considerable number of data owners.

cs.CR↗

arXiv2020

ECML: An Ensemble Cascade Metric Learning Mechanism towards Face Verification

Face verification can be regarded as a 2-class fine-grained visual recognition problem. Enhancing the feature's discriminative power is one of the key problems to improve its performance. Metric learning technology is often applied to address this need, while achieving a good tradeoff between underfitting and overfitting plays the vital role in metric learning. Hence, we propose a novel ensemble cascade metric learning (ECML) mechanism. In particular, hierarchical metric learning is executed in the cascade way to alleviate underfitting. Meanwhile, at each learning level, the features are split into non-overlapping groups. Then, metric learning is executed among the feature groups in the ensemble manner to resist overfitting. Considering the feature distribution characteristics of faces, a robust Mahalanobis metric learning method (RMML) with closed-form solution is additionally proposed. It can avoid the computation failure issue on inverse matrix faced by some well-known metric learning approaches (e.g., KISSME). Embedding RMML into the proposed ECML mechanism, our metric learning paradigm (EC-RMML) can run in the one-pass learning manner. Experimental results demonstrate that EC-RMML is superior to state-of-the-art metric learning methods for face verification. And, the proposed ensemble cascade metric learning mechanism is also applicable to other metric learning approaches.

cs.CV↗

arXiv2020

Characterizing covers via simple closed curves

Given two finite covers $p: X \to S$ and $q: Y \to S$ of a connected, oriented, closed surface $S$ of genus at least $2$, we attempt to characterize the equivalence of $p$ and $q$ in terms of which curves lift to simple curves. Using Teichmüller theory and the complex of curves, we show that two regular covers $p$ and $q$ are equivalent if for any closed curve $γ\subset S$, $γ$ lifts to a simple closed curve on $X$ if and only if it does to $Y$. When the covers are abelian, we also give a characterization of equivalence in terms of which powers of simple closed curves lift to closed curves.

math.GT↗

arXiv2020

P2B: Point-to-Box Network for 3D Object Tracking in Point Clouds

Towards 3D object tracking in point clouds, a novel point-to-box network termed P2B is proposed in an end-to-end learning manner. Our main idea is to first localize potential target centers in 3D search area embedded with target information. Then point-driven 3D target proposal and verification are executed jointly. In this way, the time-consuming 3D exhaustive search can be avoided. Specifically, we first sample seeds from the point clouds in template and search area respectively. Then, we execute permutation-invariant feature augmentation to embed target clues from template into search area seeds and represent them with target-specific features. Consequently, the augmented search area seeds regress the potential target centers via Hough voting. The centers are further strengthened with seed-wise targetness scores. Finally, each center clusters its neighbors to leverage the ensemble power for joint 3D target proposal and verification. We apply PointNet++ as our backbone and experiments on KITTI tracking dataset demonstrate P2B's superiority (~10%'s improvement over state-of-the-art). Note that P2B can run with 40FPS on a single NVIDIA 1080Ti GPU. Our code and model are available at https://github.com/HaozheQi/P2B.

cs.CV↗