arXiv subjects

Shuo Zhang

Publications and source records attributed to Shuo Zhang.

At least 217 records · Page 12Linked to original sources

arXiv2023

Stellar Parameters and Chemical Abundances Estimated from LAMOST-II DR8 MRS based on Cycle-StarNet

Deriving stellar atmospheric parameters and chemical abundances from stellar spectra is crucial for understanding the evolution of the Milky Way. By performing a fitting with MARCS model atmospheric theoretical synthetic spectra combined with a domain-adaptation method, we estimate the fundamental stellar parameters (Teff, log g, [Fe/H], vmic, and vmac) and 11 chemical abundances for 1.38 million FGKM-type stars of the Medium-Resolution Spectroscopic Survey (MRS) from LAMOST-II DR8. The domain-adaptation method, Cycle-StarNet, is employed to reduce the gap between observed and synthetic spectra, and the L-BFGS algorithm is used to search for the best-fit synthetic spectra. By combining the 2MASS photometric survey data, Gaia EDR3 parallax, and MIST isochrones, the surface gravities of the stars are constrained after estimating their bolometric luminosities. The accuracy of Teff, log g, and [Fe/H] can reach 150 K, 0.11 dex, and 0.15 dex, evaluated by the PASTEL catalog, asteroseismic samples, and other spectroscopic surveys. The precision of these parameters and elemental abundances ([C/Fe], [Na/Fe], [Mg/Fe], [Si/Fe], [Ca/Fe], [Ti/Fe], [Cr/Fe], [Mn/Fe], [Co/Fe], [Ni/Fe], and [Cu/Fe]) is assessed by repeated observations and validated by cluster members. For spectra with signal-to-noise (S/N) ratios greater than 10, the precision of the three stellar parameters and elemental abundances can achieve 76 K, 0.014 dex, 0.096 dex, and 0.04-0.15 dex. For spectra with S/N ratios higher than 100, the precision stabilizes at 22 K, 0.006 dex, 0.043 dex, and 0.01-0.06 dex. The full LAMOST MRS stellar properties catalog is available online.

astro-ph.SR↗

arXiv2023

Improved Deterministic Algorithms for Non-monotone Submodular Maximization

Submodular maximization is one of the central topics in combinatorial optimization. It has found numerous applications in the real world. In the past decades, a series of algorithms have been proposed for this problem. However, most of the state-of-the-art algorithms are randomized. There remain non-negligible gaps with respect to approximation ratios between deterministic and randomized algorithms in submodular maximization. In this paper, we propose deterministic algorithms with improved approximation ratios for non-monotone submodular maximization. Specifically, for the matroid constraint, we provide a deterministic $0.283-o(1)$ approximation algorithm, while the previous best deterministic algorithm only achieves a $1/4$ approximation ratio. For the knapsack constraint, we provide a deterministic $1/4$ approximation algorithm, while the previous best deterministic algorithm only achieves a $1/6$ approximation ratio. For the linear packing constraints with large widths, we provide a deterministic $1/6-ε$ approximation algorithm. To the best of our knowledge, there is currently no deterministic approximation algorithm for the constraints.

cs.DS↗

arXiv2023

V2V4Real: A Real-world Large-scale Dataset for Vehicle-to-Vehicle Cooperative Perception

Modern perception systems of autonomous vehicles are known to be sensitive to occlusions and lack the capability of long perceiving range. It has been one of the key bottlenecks that prevents Level 5 autonomy. Recent research has demonstrated that the Vehicle-to-Vehicle (V2V) cooperative perception system has great potential to revolutionize the autonomous driving industry. However, the lack of a real-world dataset hinders the progress of this field. To facilitate the development of cooperative perception, we present V2V4Real, the first large-scale real-world multi-modal dataset for V2V perception. The data is collected by two vehicles equipped with multi-modal sensors driving together through diverse scenarios. Our V2V4Real dataset covers a driving area of 410 km, comprising 20K LiDAR frames, 40K RGB frames, 240K annotated 3D bounding boxes for 5 classes, and HDMaps that cover all the driving routes. V2V4Real introduces three perception tasks, including cooperative 3D object detection, cooperative 3D object tracking, and Sim2Real domain adaptation for cooperative perception. We provide comprehensive benchmarks of recent cooperative perception algorithms on three tasks. The V2V4Real dataset can be found at https://research.seas.ucla.edu/mobility-lab/v2v4real/.

cs.CV↗

arXiv2023

View Adaptive Light Field Deblurring Networks with Depth Perception

The Light Field (LF) deblurring task is a challenging problem as the blur images are caused by different reasons like the camera shake and the object motion. The single image deblurring method is a possible way to solve this problem. However, since it deals with each view independently and cannot effectively utilize and maintain the LF structure, the restoration effect is usually not ideal. Besides, the LF blur is more complex because the degree is affected by the views and depth. Therefore, we carefully designed a novel LF deblurring network based on the LF blur characteristics. On one hand, since the blur degree varies a lot in different views, we design a novel view adaptive spatial convolution to deblur blurred LFs, which calculates the exclusive convolution kernel for each view. On the other hand, because the blur degree also varies with the depth of the object, a depth perception view attention is designed to deblur different depth areas by selectively integrating information from different views. Besides, we introduce an angular position embedding to maintain the LF structure better, which ensures the model correctly restores the view information. Quantitative and qualitative experimental results on synthetic and real images show that the deblurring effect of our method is better than other state-of-the-art methods.

cs.CV↗

arXiv2023

HiSSNet: Sound Event Detection and Speaker Identification via Hierarchical Prototypical Networks for Low-Resource Headphones

Modern noise-cancelling headphones have significantly improved users' auditory experiences by removing unwanted background noise, but they can also block out sounds that matter to users. Machine learning (ML) models for sound event detection (SED) and speaker identification (SID) can enable headphones to selectively pass through important sounds; however, implementing these models for a user-centric experience presents several unique challenges. First, most people spend limited time customizing their headphones, so the sound detection should work reasonably well out of the box. Second, the models should be able to learn over time the specific sounds that are important to users based on their implicit and explicit interactions. Finally, such models should have a small memory footprint to run on low-power headphones with limited on-chip memory. In this paper, we propose addressing these challenges using HiSSNet (Hierarchical SED and SID Network). HiSSNet is an SEID (SED and SID) model that uses a hierarchical prototypical network to detect both general and specific sounds of interest and characterize both alarm-like and speech sounds. We show that HiSSNet outperforms an SEID model trained using non-hierarchical prototypical networks by 6.9 - 8.6 percent. When compared to state-of-the-art (SOTA) models trained specifically for SED or SID alone, HiSSNet achieves similar or better performance while reducing the memory footprint required to support multiple capabilities on-device.

cs.LG↗

arXiv2023

Multi-Action Dialog Policy Learning from Logged User Feedback

Multi-action dialog policy, which generates multiple atomic dialog actions per turn, has been widely applied in task-oriented dialog systems to provide expressive and efficient system responses. Existing policy models usually imitate action combinations from the labeled multi-action dialog examples. Due to data limitations, they generalize poorly toward unseen dialog flows. While reinforcement learning-based methods are proposed to incorporate the service ratings from real users and user simulators as external supervision signals, they suffer from sparse and less credible dialog-level rewards. To cope with this problem, we explore to improve multi-action dialog policy learning with explicit and implicit turn-level user feedback received for historical predictions (i.e., logged user feedback) that are cost-efficient to collect and faithful to real-world scenarios. The task is challenging since the logged user feedback provides only partial label feedback limited to the particular historical dialog actions predicted by the agent. To fully exploit such feedback information, we propose BanditMatch, which addresses the task from a feedback-enhanced semi-supervised learning perspective with a hybrid objective of semi-supervised learning and bandit learning. BanditMatch integrates pseudo-labeling methods to better explore the action space through constructing full label feedback. Extensive experiments show that our BanditMatch outperforms the state-of-the-art methods by generating more concise and informative responses. The source code and the appendix of this paper can be obtained from https://github.com/ShuoZhangXJTU/BanditMatch.

cs.CL↗

arXiv2023

MPS-AMS: Masked Patches Selection and Adaptive Masking Strategy Based Self-Supervised Medical Image Segmentation

Existing self-supervised learning methods based on contrastive learning and masked image modeling have demonstrated impressive performances. However, current masked image modeling methods are mainly utilized in natural images, and their applications in medical images are relatively lacking. Besides, their fixed high masking strategy limits the upper bound of conditional mutual information, and the gradient noise is considerable, making less the learned representation information. Motivated by these limitations, in this paper, we propose masked patches selection and adaptive masking strategy based self-supervised medical image segmentation method, named MPS-AMS. We leverage the masked patches selection strategy to choose masked patches with lesions to obtain more lesion representation information, and the adaptive masking strategy is utilized to help learn more mutual information and improve performance further. Extensive experiments on three public medical image segmentation datasets (BUSI, Hecktor, and Brats2018) show that our proposed method greatly outperforms the state-of-the-art self-supervised baselines.

cs.CV↗

arXiv2023

Multi-Head Feature Pyramid Networks for Breast Mass Detection

Analysis of X-ray images is one of the main tools to diagnose breast cancer. The ability to quickly and accurately detect the location of masses from the huge amount of image data is the key to reducing the morbidity and mortality of breast cancer. Currently, the main factor limiting the accuracy of breast mass detection is the unequal focus on the mass boxes, leading the network to focus too much on larger masses at the expense of smaller ones. In the paper, we propose the multi-head feature pyramid module (MHFPN) to solve the problem of unbalanced focus of target boxes during feature map fusion and design a multi-head breast mass detection network (MBMDnet). Experimental studies show that, comparing to the SOTA detection baselines, our method improves by 6.58% (in AP@50) and 5.4% (in TPR@50) on the commonly used INbreast dataset, while about 6-8% improvements (in AP@20) are also observed on the public MIAS and BCS-DBT datasets.

cs.CV↗

arXiv2023

Semantic Segmentation Enhanced Transformer Model for Human Attention Prediction

Saliency Prediction aims to predict the attention distribution of human eyes given an RGB image. Most of the recent state-of-the-art methods are based on deep image feature representations from traditional CNNs. However, the traditional convolution could not capture the global features of the image well due to its small kernel size. Besides, the high-level factors which closely correlate to human visual perception, e.g., objects, color, light, etc., are not considered. Inspired by these, we propose a Transformer-based method with semantic segmentation as another learning objective. More global cues of the image could be captured by Transformer. In addition, simultaneously learning the object segmentation simulates the human visual perception, which we would verify in our investigation of human gaze control in cognitive science. We build an extra decoder for the subtask and the multiple tasks share the same Transformer encoder, forcing it to learn from multiple feature spaces. We find in practice simply adding the subtask might confuse the main task learning, hence Multi-task Attention Module is proposed to deal with the feature interaction between the multiple learning targets. Our method achieves competitive performance compared to other state-of-the-art methods.

cs.CV↗

arXiv2023

UserSimCRS: A User Simulation Toolkit for Evaluating Conversational Recommender Systems

We present an extensible user simulation toolkit to facilitate automatic evaluation of conversational recommender systems. It builds on an established agenda-based approach and extends it with several novel elements, including user satisfaction prediction, persona and context modeling, and conditional natural language generation. We showcase the toolkit with a pre-existing movie recommender system and demonstrate its ability to simulate dialogues that mimic real conversations, while requiring only a handful of manually annotated dialogues as training data.

cs.IR↗

arXiv2022

Ring That Bell: A Corpus and Method for Multimodal Metaphor Detection in Videos

We present the first openly available multimodal metaphor annotated corpus. The corpus consists of videos including audio and subtitles that have been annotated by experts. Furthermore, we present a method for detecting metaphors in the new dataset based on the textual content of the videos. The method achieves a high F1-score (62\%) for metaphorical labels. We also experiment with other modalities and multimodal methods; however, these methods did not out-perform the text-based model. In our error analysis, we do identify that there are cases where video could help in disambiguating metaphors, however, the visual cues are too subtle for our model to capture. The data is available on Zenodo.

cs.MM↗

arXiv2022

A Scheme to fabricate magnetic graphene-like cobalt nitride CoN4monolayer proposed by first-principles calculations

We propose a scheme to fabricate the cobalt nitride CoN4 monolayer, a magnetic graphene-like two-dimensional material, in which all Co and N atoms are in a plane. Under the pressure above 40 GPa, the bulk CoN4 is stabilized in a triclinic phase. With the pressure decreasing, the triclinic phase of CoN4 is transformed into an orthorhombic phase, and the latter is a layered compound with large interlayer spacing. At ambient condition, the weak interlayer couplings are so small that single CoN4 layer can be exfoliated by the mechanical method.

cond-mat.mtrl-sci↗

arXiv2022

Sideband Cooling of a Trapped Ion in Strong Sideband Coupling Regime

Conventional theoretical studies on the ground-state laser cooling of a trapped ion have mostly focused on the weak sideband coupling (WSC) regime, where the cooling rate is inverse proportional to the linewidth of the excited state. In a recent work~[New J. Phys. 23, 023018 (2021)], we proposed a theoretical framework to study the ground state cooling of a trapped ion in the strong sideband coupling (SSC) regime, under the assumption of a vanishing carrier transition. Here we extend this analysis to more general situations with nonvanishing carrier transitions, where we show that by properly tuning the coupling lasers a cooling rate proportional to the linewidth can be achieved. Our theoretical predictions closely agree with the corresponding exact solutions in the SSC regime, which provide an important theoretical guidance for sideband cooling experiments.

quant-ph↗

arXiv2022

A mixed element scheme of Helmholtz transmission eigenvalue problem for anisotropic media

In this paper, we study the Helmholtz transmission eigenvalue problem for inhomogeneous anisotropic media with the index of refraction $n(x)\equiv 1$ in two and three dimension. Starting with a nonlinear fourth order formulation established by Cakoni, Colton and Haddar [2009], by introducing some auxiliary variables, we present an equivalent mixed formulation for this problem, followed up with the finite element discretization. Using the proposed scheme, we rigorously show that the optimal convergence rate for the transmission eigenvalues both on convex and nonconvex domains can be expected. Moreover, by this scheme, we will obtain a sparse generalized eigenvalue problem whose size is so demanding even with a coarse mesh that its smallest few real eigenvalues fail to be solved by the shift and invert method. We partially overcome this critical issue by deflating the almost all of the $\infty$ eigenvalue of huge multiplicity, resulting in a drastic reduction of the matrix size without deteriorating the sparsity. Extensive numerical examples are reported to demonstrate the effectiveness and efficiency of the proposed scheme.

math.NA↗

arXiv2022

M Subdwarf Research III. Spectroscopic Diagnostics for Breaking Parameter Degeneracy

To understand the parameter degeneracy of M subdwarf spectra at low resolution, we assemble a large number of spectral features in the wavelength range of 0.6-2.5 μm with band strength quantified by narrowband indices. Based on the index trends of BT-Settl model sequences, we illustrate how the main atmospheric parameters (Teff, log g, [M/H], and [alpha/Fe]) affect each spectral feature differently. Furthermore, we propose a four-step process to determine the four parameters sequentially, which extends the basic idea proposed by Jao et al. Each step contains several spectral features that break the degeneracy effect when determining a specific stellar parameter. Finally, the feasibility of each spectroscopic diagnostic with different spectral qualities is investigated. The result is resolution-independent down to R~200.

astro-ph.SR↗

arXiv2022

Realistic Data Augmentation Framework for Enhancing Tabular Reasoning

Existing approaches to constructing training data for Natural Language Inference (NLI) tasks, such as for semi-structured table reasoning, are either via crowdsourcing or fully automatic methods. However, the former is expensive and time-consuming and thus limits scale, and the latter often produces naive examples that may lack complex reasoning. This paper develops a realistic semi-automated framework for data augmentation for tabular inference. Instead of manually generating a hypothesis for each table, our methodology generates hypothesis templates transferable to similar tables. In addition, our framework entails the creation of rational counterfactual tables based on human written logical constraints and premise paraphrasing. For our case study, we use the InfoTabs, which is an entity-centric tabular inference dataset. We observed that our framework could generate human-like tabular inference examples, which could benefit training data augmentation, especially in the scenario with limited supervision.

cs.CL↗

arXiv2022

Enhancing Tabular Reasoning with Pattern Exploiting Training

Recent methods based on pre-trained language models have exhibited superior performance over tabular tasks (e.g., tabular NLI), despite showing inherent problems such as not using the right evidence and inconsistent predictions across inputs while reasoning over the tabular data. In this work, we utilize Pattern-Exploiting Training (PET) (i.e., strategic MLM) on pre-trained language models to strengthen these tabular reasoning models' pre-existing knowledge and reasoning abilities. Our upgraded model exhibits a superior understanding of knowledge facts and tabular reasoning compared to current baselines. Additionally, we demonstrate that such models are more effective for underlying downstream tasks of tabular inference on InfoTabs. Furthermore, we show our model's robustness against adversarial sets generated through various character and word level perturbations.

cs.CL↗

arXiv2022

Two-dimensional binary transition metal nitride $M$N$_4$ ($M$ = V, Cr, Mn, Fe, Co) with a graphene-like structure and strong magnetic properties

Binary transition metal nitride with a graphene-like structure and strong magnetic properties is rare. Based on the first-principles calculations, we design two kinds of $M$N$_4$ ($M$ =transition metal) monolayers, which are transition metal nitrides with a planar structure, made up of $M$N$_4$ units aligned in the rhombic and square patterns. The two structural lattices have robust stability and good compatibility with different metal atoms, and the underlying mechanism is the combination of $sp^2$ hybridization, coordinate bond, and $π$ conjugation. With the metal atom changing from V, Cr, Mn, Fe to Co, the total charge of $M$N$_4$ system increases by one electron in turn, which results in continuous adjustability of the electronic and magnetic properties. The planar ligand field is another feature of the two $M$N$_4$ lattices, which brings about the special splitting of five suborbitals of 3$d$ metal atom and gives rise to strong magnetism. Moreover, room-temperature ferromagnetism in square-CoN$_4$ monolayer with the Curie temperatures of 321 K is determined by solving the Heisenberg model combined with Monte Carlo method.

cond-mat.mtrl-sci↗