arXiv subjects

Shuo Zhang

Publications and source records attributed to Shuo Zhang.

At least 271 records · Page 15Linked to original sources

arXiv2021

Domain-Specific Suppression for Adaptive Object Detection

Domain adaptation methods face performance degradation in object detection, as the complexity of tasks require more about the transferability of the model. We propose a new perspective on how CNN models gain the transferability, viewing the weights of a model as a series of motion patterns. The directions of weights, and the gradients, can be divided into domain-specific and domain-invariant parts, and the goal of domain adaptation is to concentrate on the domain-invariant direction while eliminating the disturbance from domain-specific one. Current UDA object detection methods view the two directions as a whole while optimizing, which will cause domain-invariant direction mismatch even if the output features are perfectly aligned. In this paper, we propose the domain-specific suppression, an exemplary and generalizable constraint to the original convolution gradients in backpropagation to detach the two parts of directions and suppress the domain-specific one. We further validate our theoretical analysis and methods on several domain adaptive object detection tasks, including weather, camera configuration, and synthetic to real-world adaptation. Our experiment results show significant advance over the state-of-the-art methods in the UDA object detection field, performing a promotion of $10.2\sim12.2\%$ mAP on all these domain adaptation scenarios.

cs.CV↗

arXiv2021

Simulating User Satisfaction for the Evaluation of Task-oriented Dialogue Systems

Evaluation is crucial in the development process of task-oriented dialogue systems. As an evaluation method, user simulation allows us to tackle issues such as scalability and cost-efficiency, making it a viable choice for large-scale automatic evaluation. To help build a human-like user simulator that can measure the quality of a dialogue, we propose the following task: simulating user satisfaction for the evaluation of task-oriented dialogue systems. The purpose of the task is to increase the evaluation power of user simulations and to make the simulation more human-like. To overcome a lack of annotated data, we propose a user satisfaction annotation dataset, USS, that includes 6,800 dialogues sampled from multiple domains, spanning real-world e-commerce dialogues, task-oriented dialogues constructed through Wizard-of-Oz experiments, and movie recommendation dialogues. All user utterances in those dialogues, as well as the dialogues themselves, have been labeled based on a 5-level satisfaction scale. We also share three baseline methods for user satisfaction prediction and action prediction tasks. Experiments conducted on the USS dataset suggest that distributed representations outperform feature-based methods. A model based on hierarchical GRUs achieves the best performance in in-domain user satisfaction prediction, while a BERT-based model has better cross-domain generalization ability.

cs.IR↗

arXiv2021

WTR: A Test Collection for Web Table Retrieval

We describe the development, characteristics and availability of a test collection for the task of Web table retrieval, which uses a large-scale Web Table Corpora extracted from the Common Crawl. Since a Web table usually has rich context information such as the page title and surrounding paragraphs, we not only provide relevance judgments of query-table pairs, but also the relevance judgments of query-table context pairs with respect to a query, which are ignored by previous test collections. To facilitate future research with this benchmark, we provide details about how the dataset is pre-processed and also baseline results from both traditional and recently proposed table retrieval methods. Our experimental results show that proper usage of context labels can benefit previous table retrieval methods.

cs.IR↗

arXiv2021

PSF-LO: Parameterized Semantic Features Based Lidar Odometry

Lidar odometry (LO) is a key technology in numerous reliable and accurate localization and mapping systems of autonomous driving. The state-of-the-art LO methods generally leverage geometric information to perform point cloud registration. Furthermore, obtaining point cloud semantic information which can describe the environment more abundantly will help for the registration. We present a novel semantic lidar odometry method based on self-designed parameterized semantic features (PSFs) to achieve low-drift ego-motion estimation for autonomous vehicle in realtime. We first use a convolutional neural network-based algorithm to obtain point-wise semantics from the input laser point cloud, and then use semantic labels to separate the road, building, traffic sign and pole-like point cloud and fit them separately to obtain corresponding PSFs. A fast PSF-based matching enable us to refine geometric features (GeFs) registration, reducing the impact of blurred submap surface on the accuracy of GeFs matching. Besides, we design an efficient method to accurately recognize and remove the dynamic objects while retaining static ones in the semantic point cloud, which are beneficial to further improve the accuracy of LO. We evaluated our method, namely PSF-LO, on the public dataset KITTI Odometry Benchmark and ranked #1 among semantic lidar methods with an average translation error of 0.82% in the test dataset at the time of writing.

cs.CV↗

arXiv2021

A low-degree strictly conservative finite element method for incompressible flows

In this paper, a new $P_{2}-P_{1}$ finite element pair is proposed for incompressible fluid. For this pair, the discrete inf-sup condition and the discrete Korn's inequality hold on general triangulations. It yields exactly divergence-free velocity approximations when applied to models of incompressible flows. The robust capacity of the pair for incompressible flows are verified theoretically and numerically.

math.NA↗

arXiv2021

A simple low-degree optimal finite element scheme for the elastic transmission eigenvalue problem

The paper presents a finite element scheme for the elastic transmission eigenvalue problem written as a fourth order eigenvalue problem. The scheme uses piecewise cubic polynomials and obtains optimal convergence rate. Compared with other low-degree and nonconforming finite element schemes, the scheme inherits the continuous bilinear form which does not need extra stabilizations and is thus simple to implement.

math.NA↗

arXiv2020

Learning to Check Contract Inconsistencies

Contract consistency is important in ensuring the legal validity of the contract. In many scenarios, a contract is written by filling the blanks in a precompiled form. Due to carelessness, two blanks that should be filled with the same (or different)content may be incorrectly filled with different (or same) content. This will result in the issue of contract inconsistencies, which may severely impair the legal validity of the contract. Traditional methods to address this issue mainly rely on manual contract review, which is labor-intensive and costly. In this work, we formulate a novel Contract Inconsistency Checking (CIC) problem, and design an end-to-end framework, called Pair-wise Blank Resolution (PBR), to solve the CIC problem with high accuracy. Our PBR model contains a novel BlankCoder to address the challenge of modeling meaningless blanks. BlankCoder adopts a two-stage attention mechanism that adequately associates a meaningless blank with its relevant descriptions while avoiding the incorporation of irrelevant context words. Experiments conducted on real-world datasets show the promising performance of our method with a balanced accuracy of 94.05% and an F1 score of 90.90% in the CIC problem.

cs.CL↗

arXiv2020

M Subdwarf Research. II. Atmospheric Parameters and Kinematics

Applying the revised M subdwarf classification criteria discussed in Paper I to LAMOST DR7, combining the M subdwarf sample from Savcheva et al, a new M subdwarf sample was constructed for further study. The atmospheric parameters for each object were derived fitting with the PHOENIX grid, combining with Gaia DR2, the relationship between the gravity and metallicity were explored according to the locus both in the color-absolute magnitude diagram and the reduced proper motion diagram. Objects that have both the largest gravity and the lowest metallicity are located away from the main-sequence cloud and may be considered as the intrinsic M subdwarfs, which can be classified as luminosity class VI. Another group of objects whose spectra show typical M subdwarf characters have lower gravity and relatively moderate metal deficiency and occupy part of the ordinary M dwarf region in both diagrams. The Galactic U , V , W space velocity components and their dispersion show that the local Galactic halo population sampled in the solar neighborhood is represented by objects of high gravity and an inconspicuous bimodal metallicity distribution, with a fraction of prograde orbits. The other M subdwarfs seem to partly belong to the thick disk component with a significant fraction of thin disk moderately metal-poor objects intricately mixed with them. However, the selection effects, especially the favored anti-center direction of investigation in the LAMOST sub-sample, but also contamination by multiplicity and parameter coupling could play important roles and need to be further investigated.

astro-ph.SR↗

arXiv2020

591 high velocity stars in the Galactic halo selected from LAMOST DR7 and Gaia DR2

In this paper, we report 591 high velocity star candidates (HiVelSCs) selected from over 10 million spectra of the data release seven (DR7) of the Large Sky Area Multi-object Fiber Spectroscopic Telescope and the second Gaia data release, with three-dimensional velocities in the Galactic rest-frame larger than 445 km/s. We show that at least 43 HiVelSCs are unbound to the Galaxy with escape probabilities larger than 50%, and this number decreases to eight if the possible parallax zero-point error is corrected. Most of these HiVelSCs are metal-poor and slightly alpha-enhanced inner halo stars. Only 14% of them have [Fe/H] > -1, which may be the metal-rich "in situ" stars in halo formed in the initial collapse of the Milky Way or metal-rich stars formed in the disk or bulge but kinematically heated. The low ratio of 14% implies that the bulk of stellar halo was formed from the accretion and tidal disruption of satellite galaxies. In addition, HiVelSCs on the retrograde orbits have a slightly lower metallicities on average compared with these on the prograde orbits, meanwhile metal-poor HiVelSCs with [Fe/H] < -1 have an even faster mean retrograde velocity compared with metal-rich HiVelSCs. To investigate the origins of HiVelSCs, we perform orbit integrations and divide them into four types, i.e., hypervelocity stars, hyper-runaway stars, runaway stars and fast halo stars. A catalog for these 591 HiVelSCs, including radial velocities, atmospheric parameters, Gaia astrometric parameters, spatial positions, and velocities, etc., is available at http://paperdata.chinavo.org/LYB/lamostdr7_gaiadr2_hvs_591.csv.

astro-ph.GA↗

arXiv2020

Fast Cooling of Trapped Ion in Strong Sideband Coupling Regime

Trapped ion in the Lamb-Dicke regime with the Lamb-Dicke parameter $η\ll1$ can be cooled down to its motional ground state using sideband cooling. Standard sideband cooling works in the weak sideband coupling limit, where the sideband coupling strength is small compared to the natural linewidth $γ$ of the internal excited state, with a cooling rate much less than $γ$. Here we consider cooling schemes in the strong sideband coupling regime, where the sideband coupling strength is comparable or even greater than $γ$. We derive analytic expressions for the cooling rate and the average occupation of the motional steady state in this regime, based on which we show that one can reach a cooling rate which is proportional to $γ$, while at the same time the steady state occupation increases by a correction term proportional to $η^{2}$ compared to the weak sideband coupling limit. We demonstrate with numerical simulations that our analytic expressions faithfully recover the exact dynamics in the strong sideband coupling regime.

quant-ph↗

arXiv2020

Molecular Mechanics-Driven Graph Neural Network with Multiplex Graph for Molecular Structures

The prediction of physicochemical properties from molecular structures is a crucial task for artificial intelligence aided molecular design. A growing number of Graph Neural Networks (GNNs) have been proposed to address this challenge. These models improve their expressive power by incorporating auxiliary information in molecules while inevitably increase their computational complexity. In this work, we aim to design a GNN which is both powerful and efficient for molecule structures. To achieve such goal, we propose a molecular mechanics-driven approach by first representing each molecule as a two-layer multiplex graph, where one layer contains only local connections that mainly capture the covalent interactions and another layer contains global connections that can simulate non-covalent interactions. Then for each layer, a corresponding message passing module is proposed to balance the trade-off of expression power and computational complexity. Based on these two modules, we build Multiplex Molecular Graph Neural Network (MXMNet). When validated by the QM9 dataset for small molecules and PDBBind dataset for large protein-ligand complexes, MXMNet achieves superior results to the existing state-of-the-art models under restricted resources.

cs.LG↗

arXiv2020

IAI MovieBot: A Conversational Movie Recommender System

Conversational recommender systems support users in accomplishing recommendation-related goals via multi-turn conversations. To better model dynamically changing user preferences and provide the community with a reusable development framework, we introduce IAI MovieBot, a conversational recommender system for movies. It features a task-specific dialogue flow, a multi-modal chat interface, and an effective way to deal with dynamically changing user preferences. The system is made available open source and is operated as a channel on Telegram.

cs.IR↗

arXiv2020

Multi-Dimension Fusion Network for Light Field Spatial Super-Resolution using Dynamic Filters

Light field cameras have been proved to be powerful tools for 3D reconstruction and virtual reality applications. However, the limited resolution of light field images brings a lot of difficulties for further information display and extraction. In this paper, we introduce a novel learning-based framework to improve the spatial resolution of light fields. First, features from different dimensions are parallelly extracted and fused together in our multi-dimension fusion architecture. These features are then used to generate dynamic filters, which extract subpixel information from micro-lens images and also implicitly consider the disparity information. Finally, more high-frequency details learned in the residual branch are added to the upsampled images and the final super-resolved light fields are obtained. Experimental results show that the proposed method uses fewer parameters but achieves better performances than other state-of-the-art methods in various kinds of datasets. Our reconstructed images also show sharp details and distinct lines in both sub-aperture images and epipolar plane images.

eess.IV↗

arXiv2020

Scatting theory for reflective Fourier ptychographic diffraction tomography

A forward model is presented to an inverse scattering problem that arises in the application of reflective Fourier ptychographic microscopy. The model allows us to determine the 3D distributions of refractive index for weakly scattering semi-transparent objects using Fourier ptychographic tomography. The derivation results show that both transmission types reported previously and reflective type present in this article are corresponding to a specific application in Wolf's work (Emil Wolf, Opt. Commun. 1969 1(4) pp. 153-156). The transmission type measures the forward scattering field while the reflective type measures the backward scattering field. This model is also available for holographic method

physics.optics↗

arXiv2020

Generating Categories for Sets of Entities

Category systems are central components of knowledge bases, as they provide a hierarchical grouping of semantically related concepts and entities. They are a unique and valuable resource that is utilized in a broad range of information access tasks. To aid knowledge editors in the manual process of expanding a category system, this paper presents a method of generating categories for sets of entities. First, we employ neural abstractive summarization models to generate candidate categories. Next, the location within the hierarchy is identified for each candidate. Finally, structure-, content-, and hierarchy-based features are used to rank candidates to identify by the most promising ones (measured in terms of specificity, hierarchy, and importance). We develop a test collection based on Wikipedia categories and demonstrate the effectiveness of the proposed approach.

cs.IR↗

arXiv2020

Summarizing and Exploring Tabular Data in Conversational Search

Tabular data provide answers to a significant portion of search queries. However, reciting an entire result table is impractical in conversational search systems. We propose to generate natural language summaries as answers to describe the complex information contained in a table. Through crowdsourcing experiments, we build a new conversation-oriented, open-domain table summarization dataset. It includes annotated table summaries, which not only answer questions but also help people explore other information in the table. We utilize this dataset to develop automatic table summarization systems as SOTA baselines. Based on the experimental results, we identify challenges and point out future research directions that this resource will support.

cs.IR↗

arXiv2020

Lowest-degree robust finite element scheme for a fourth-order elliptic singular perturbation problem on rectangular grids

In this paper, a piecewise quadratic nonconforming finite element method on rectangular grids for a fourth-order elliptic singular perturbation problem is presented. This proposed method is robustly convergent with respect to the perturbation parameter. Numerical results are presented to verify the theoretical findings. The new method uses piecewise quadratic polynomials, and is of the lowest degree possible. Optimal order approximation property of the finite element space is proved by means of a locally-averaged interpolation operator newly constructed. This interpolator, however, is not a projection. Indeed, we establish a general theory and show that no locally defined interpolation associated with the locally supported basis functions can be projective for the finite element space in use. Particularly, the general theory gives an answer to a long-standing open problem presented in [Demko, J. Approx. Theory, $\bf{43}$(2):151--156, 1985].

math.NA↗

arXiv2020

Lowest-degree piecewise polynomial de Rham complex on general quadrilateral grids

This paper is devoted to the construction of finite elements on grids that consist of general quadrilaterals not limited in parallelograms. Two finite elements defined as Ciarlet's triple are established for the $H^1$ and $H(\rm rot)$ elliptic problems, respectively. An $\mathcal{O}(h)$ order convergence rate in energy norm for both of them and an $\mathcal{O}(h^2)$ order convergence in $L^2$ norm for the $H^1$ scheme are proved under the asymptotic-parallelogram assumption on the grids. Further, the two finite element spaces on general quadrilateral grids, together with the space of piecewise constant functions, formulate a discretized de Rham complex. The finite element spaces consist of piecewise polynomial functions, and, thus, are nonconforming on general quadrilateral grids. Indeed, a rigorous analysis is given in this paper that it is impossible to construct a practically useful finite element defined as Ciarlet's triple that can formulate a finite element space which consists of continuous piecewise polynomial functions on a grid that may include arbitrary quadrilaterals.

math.NA↗