检索结果-内蒙古大学图书馆

arXiv 2025年

作者： Kou, Wei-Bin Zhu, Guangxu Ye, Rongguang Wang, Shuai Tang, Ming Wu, Yik-Chung Department of Electrical and Electronic Engineering The University of Hong Kong Hong Kong Department of Computer Science and Engineering Southern University of Science and Technology Shenzhen China Shenzhen International Center For Industrial And Applied Mathematics Shenzhen Research Institute of Big Data Shenzhen China Shenzhen Institute of Advanced Technology Chinese Academy of Sciences Shenzhen China

Learning-based street scene semantic understanding in autonomous driving (AD) has advanced significantly recently, but the performance of the AD model is heavily dependent on the quantity and quality of the annotated training data. However, traditional manual labeling involves high cost to annotate the vast amount of required data for training robust model. To mitigate this cost of manual labeling, we propose a Label Anything Model (denoted as LAM), serving as an interpretable, high-fidelity, and prompt-free data annotator. Specifically, we firstly incorporate a pretrained Vision Transformer (ViT) to extract the latent features. On top of ViT, we propose a semantic class adapter (SCA) and an optimization-oriented unrolling algorithm (OptOU), both with a quite small number of trainable parameters. SCA is proposed to fuse ViT-extracted features to consolidate the basis of the subsequent automatic annotation. OptOU consists of multiple cascading layers and each layer contains an optimization formulation to align its output with the ground truth as closely as possible, though which OptOU acts as being interpretable rather than learning-based blackbox nature. In addition, training SCA and OptOU requires only a single pre-annotated RGB seed image, owing to their small volume of learnable parameters. Extensive experiments clearly demonstrate that the proposed LAM can generate high-fidelity annotations (almost 100% in mIoU) for multiple real-world datasets (i.e., Camvid, Cityscapes, and Apolloscapes) and CARLA simulation dataset. © 2025, CC BY-NC-ND.

关键词： Adversarial machine learning

来源：评论

学校读者我要写书评

暂无评论

ADDRESSING PARAMETER CHOICE ISSUES IN UNSUPERVISED DOMAIN ADAPTATION BY AGGREGATION

arXiv

引用

arXiv 2023年

作者： Dinu, Marius-Constantin Holzleitner, Markus Beck, Maximilian Nguyen, Duc Hoan Huber, Andrea Eghbal-Zadeh, Hamid Moser, Bernhard A. Pereverzyev, Sergei V. Hochreiter, Sepp Zellinger, Werner Ellis Unit Linz Lit Ai Lab Institute for Machine Learning Johannes Kepler University Linz Austria Dynatrace Research Austria Institute of Advanced Research in Artificial Intelligence Austria Software Competence Center Hagenberg Austria Johann Radon Institute for Computational and Applied Mathematics Austrian Academy of Sciences Austria

We study the problem of choosing algorithm hyper-parameters in unsupervised domain adaptation, i.e., with labeled data in a source domain and unlabeled data in a target domain, drawn from a different input distribution. We follow the strategy to compute several models using different hyper-parameters, and, to subsequently compute a linear aggregation of the models. While several heuristics exist that follow this strategy, methods are still missing that rely on thorough theories for bounding the target error. In this turn, we propose a method that extends weighted least squares to vector-valued functions, e.g., deep neural networks. We show that the target error of the proposed algorithm is asymptotically not worse than twice the error of the unknown optimal aggregation. We also perform a large scale empirical comparative study on several datasets, including text, images, electroencephalogram, body sensor signals and signals from mobile phones. Our method outperforms deep embedded validation (DEV) and importance weighted validation (IWV) on all datasets, setting a new state-of-the-art performance for solving parameter choice issues in unsupervised domain adaptation with theoretical error guarantees. We further study several competitive heuristics, all outperforming IWV and DEV on at least five datasets. However, our method outperforms each heuristic on at least five of seven datasets. © 2023, CC BY.

关键词： Errors

来源：评论

学校读者我要写书评

暂无评论

Implicit Counterfactual Data Augmentation for Robust Learning

arXiv

引用

arXiv 2023年

作者： Zhou, Xiaoling Wu, Ou Ng, Michael K. Center for Applied Mathematics Tianjin University Tianjin300072 China National Engineering Research Center for Software Engineering Peking University Beijing100091 China Hangzhou Institute for Advanced Study University of Chinese Academy of Sciences Hangzhou310024 China Department of Mathematics Hong Kong Baptist University 999077 Hong Kong

Machine learning models are prone to capturing the spurious correlations between non-causal attributes and classes, with counterfactual data augmentation being a promising direction for breaking these spurious associations. However, generating counterfactual data explicitly poses a challenge, and incorporating augmented data into the training process decreases training efficiency. This study proposes an Implicit Counterfactual Data Augmentation (ICDA) method to remove spurious correlations and make stable predictions. Specifically, first, a novel sample-wise augmentation strategy is developed that generates semantically and counterfactually meaningful deep features with distinct augmentation strength for each sample. Second, we derive an easy-to-compute surrogate loss on the augmented feature set when the number of augmented samples becomes infinite. Third, two concrete schemes are proposed, including direct quantification and meta-learning, to derive the key parameters for the robust loss. In addition, ICDA is explained from a regularization perspective, revealing its capacity to improve intra-class compactness and augment margins at both class and sample levels. Extensive experiments have been conducted across various biased learning scenarios covering both image and text datasets, demonstrating that ICDA consistently enhances the generalization and robustness performance of popular networks. © 2023, CC BY.

关键词： Contrastive Learning

来源：评论

学校读者我要写书评

暂无评论

Application of Lasso regression model in the analysis of success probability of electronic experiments

Application of Lasso regression model in the analysis of suc...

引用

2021 IEEE International Conference on Computer Science, Electronic Information Engineering and Intelligent Control Technology, CEI 2021

作者： Wei, Haomin Wang, Ruihua Guo, Zhangxia Yang, Zhou Wang, Jiajia College of Mechatronic Engineering North University of China Taiyuan China PLA Academy of Military Science China Innovation Center for Intelligent System on Recognition and Decision China Aerospace Science and Industry Corporation Applied Mathematics Research Center Beijing Jinghang Research Institute of Computing and Communication Beijing China

ISBN: (纸本)9780738146492

The multifactorial electronic experiment design and evaluation process suffer from many test constraints, complex and diverse test factors, and multiple indicators coupled with each other. In the face of these problems, this paper firstly elaborates the role relationship between different multifactorial electronic experiment states and influencing factors, and the basic explanation of parametric modeling and regression analysis. The logic of the Lasso regression model are elaborated, and the parametric modeling method is used to evaluate and model the factors and their relationships that affect the success probability of a trial in one case with multiple regression models, and the results are analyzed and evaluated horizontally. The results prove that the Lasso regression method is more controllable and the results are more interpretable by adjusting the parameters, and the maximum error is reduced, which has better applicability;the Least Squares method and the Logistic method also have their excellent characteristics, and in practical applications, suitable regression algorithms can be selected for use according to the requirements of the scenario. © 2021 IEEE.

关键词： Regression analysis

来源：评论

学校读者我要写书评

暂无评论

High-rate generation and ultrafast real-time observation of optical non-Gaussian states encoded in sub-nanosecond wavepackets

High-rate generation and ultrafast real-time observation of ...

引用

Quantum 2.0, QUANTUM 2024 in Quantum 2.0 Conference and Exhibition

作者： Kawasaki, Akito Ide, Ryuhoh Brunel, Hector Suzuki, Takumi Nehra, Rajveer Nakashima, Katsuki Kashiwazaki, Takahiro Inoue, Asuka Umeki, Takeshi China, Fumihiro Yabuno, Masahiro Miki, Shigehito Terai, Hirotaka Yamashima, Taichi Sakaguchi, Atsushi Takase, Kan Endo, Mamoru Asavanant, Warit Furusawa, Akira Department of Applied Physics School of Engineering The University of Tokyo 7-3-1 Hongo Bunkyo-ku Tokyo113-8656 Japan Department of Physics Ecole Normale Supérieure 24 rue Lhomond Paris75005 France Department of Electrical and Computer Engineering University of Massachusetts-Amherst AmherstMA01003 United States Department of Physics University of Massachusetts-Amherst AmherstMA01003 United States NTT Device Technology Labs NTT Corporation 3-1 Morinosato Wakamiya Kanagawa Atsugi243-0198 Japan Advanced ICR Research Institute National Institute of Information and Communications Technology 588-2 Iwaoka Nishi Kobe651-2492 Japan Optical Quantum Computing Research Team RIKEN Center for Quantum Computing 2-1 Hirosawa Saitama Wako351-0198 Japan

We generate and observe optical non-Gaussian states defined in wavepackets of sub-nanosecond time width—O(103) faster than previous research—using waveguide optical parametric amplifier made of PPLN crystal, enablin... 详细信息

ISBN: (纸本)9781557525185

关键词： Parametric amplifiers

来源：评论

学校读者我要写书评

暂无评论

Engineering quantum states with neutral atoms

arXiv

引用

arXiv 2024年

作者： Balewski, Jan Kornjača, Milan Klymko, Katherine Darbha, Siva Hirsbrunner, Mark R. Lopes, Pedro L.S. Liu, Fangli Camps, Daan National Energy Research Scientific Computing Center Lawrence Berkeley National Laboratory BerkeleyCA United States QuEra Computing Inc. BostonMA United States Applied Mathematics and Computational Research Division Lawrence Berkeley National Laboratory BerkeleyCA United States Dept. of Physics Institute for Condensed Matter Theory University of Illinois at Urbana-Champaign UrbanaIL United States

Aquila, an analog quantum simulation platform developed by QuEra computing, supports control of the position and coherent evolution of up to 256 neutral atoms. This study details novel experimental protocols designed for analog quantum simulators that generate Bell state entanglement far away from the blockade regime, construct a Z2 state with a defect induced by an ancilla, and optimize the driving fields schedule to prepare excited states with enhanced fidelity. We additionally evaluate the effectiveness of readout error mitigation techniques in improving the fidelity of measurement results. All experiments were executed on Aquila from QuEra and facilitated by the AWS Braket interface. Our experimental results closely align with theoretical predictions and numerical simulations. The insights gained from this study showcase Aquila’s capabilities in handling complex quantum simulations and computations, and also pave the way for new avenues of research in quantum information processing and physics that employ programmable analog hardware platforms. Copyright © 2024, The Authors. All rights reserved.

关键词： Excited states

来源：评论

学校读者我要写书评

暂无评论

Linear Combination of Hamiltonian Simulation for Nonunitary Dynamics with Optimal State Preparation Cost

引用

Physical Review Letters 2023年第15期131卷 150603-150603页

作者： Dong An Jin-Peng Liu Lin Lin Joint Center for Quantum Information and Computer Science University of Maryland College Park Maryland 20742 USA Department of Mathematics University of California Berkeley California 94720 USA Simons Institute for the Theory of Computing University of California Berkeley California 94720 USA Center for Theoretical Physics Massachusetts Institute of Technology Cambridge Massachusetts 02139 USA Lawrence Berkeley National Laboratory Applied Mathematics and Computational Research Division Berkeley California 94720 USA Challenge Institute for Quantum Computation University of California Berkeley California 94720 USA

We propose a simple method for simulating a general class of nonunitary dynamics as a linear combination of Hamiltonian simulation (LCHS) problems. LCHS does not rely on converting the problem into a dilated linear system problem or on the spectral mapping theorem. The latter is the mathematical foundation of many quantum algorithms for solving a wide variety of tasks involving nonunitary processes, such as the quantum singular value transformation. The LCHS method can achieve optimal cost in terms of state preparation. We also demonstrate an application for open quantum dynamics simulation using the complex absorbing potential method with near-optimal dependence on all parameters.

关键词： Open quantum systems Quantum algorithms Quantum algorithms & computation Quantum simulation Differential equations

来源：评论

学校读者我要写书评

暂无评论

DPA-2:a large atomic model as a multitask learner

引用

npj Computational Materials 2024年第1期10卷 185-199页

作者： Duo Zhang Xinzijian Liu Xiangyu Zhang Chengqian Zhang Chun Cai Hangrui Bi Yiming Du Xuejian Qin Anyang Peng Jiameng Huang Bowen Li Yifan Shan Jinzhe Zeng Yuzhi Zhang Siyuan Liu Yifan Li Junhan Chang Xinyan Wang Shuo Zhou Jianchuan Liu Xiaoshan Luo Zhenyu Wang Wanrun Jiang Jing Wu Yudi Yang Jiyuan Yang Manyi Yang Fu-Qiang Gong Linshuang Zhang Mengchao Shi Fu-Zhi Dai Darrin M.York Shi Liu Tong Zhu Zhicheng Zhong Jian Lv Jun Cheng Weile Jia Mohan Chen Guolin Ke Weinan E Linfeng Zhang Han Wang AI for Science Institute BeijingP.R.China DP Technology BeijingP.R.China Academy for Advanced Interdisciplinary Studies Peking UniversityBeijingP.R.China State Key Lab of Processors Institute of Computing TechnologyChinese Academy of SciencesBeijingP.R.China University of Chinese Academy of Sciences BeijingP.R.China HEDPS CAPTCollege of EngineeringPeking UniversityBeijingP.R.China Ningbo Institute of Materials Technology and Engineering Chinese Academy of SciencesNingboP.R.China CAS Key Laboratory of Magnetic Materials and Devices and Zhejiang Province Key Laboratory of Magnetic Materials and Application Technology Chinese Academy of SciencesNingboP.R.China School of Electronics Engineering and Computer Science Peking UniversityBeijingP.R.China Shanghai Engineering Research Center of Molecular Therapeutics&New Drug Development School of Chemistry and Molecular EngineeringEast China Normal UniversityShanghaiP.R.China Laboratory for Biomolecular Simulation Research Institute for Quantitative Biomedicine and Department of Chemistry and Chemical BiologyRutgers UniversityPiscatawayNJUSA Department of Chemistry Princeton UniversityPrincetonNJUSA College of Chemistry and Molecular Engineering Peking UniversityBeijingP.R.China Yuanpei College Peking UniversityBeijingP.R.China School of Electrical Engineering and Electronic Information Xihua UniversityChengduP.R.China State Key Laboratory of Superhard Materials College of PhysicsJilin UniversityChangchunP.R.China Key Laboratory of Material Simulation Methods&Software of Ministry of Education College of PhysicsJilin UniversityChangchunP.R.China International Center of Future Science Jilin UniversityChangchunP.R.China Key Laboratory for Quantum Materialsof Zhejiang Province Department of PhysicsSchool of ScienceWestlake UniversityHangzhouP.R.China Atomistic Simulations Italian Institute of TechnologyGenovaItaly State Key Laboratory of Physical Chemistry of Solid Surface iChEMCollege of Chemistry and Chemical EngineeringXiame

The rapid advancements in artificial intelligence(AI)are catalyzing transformative changes in atomic modeling,simulation,and ***-driven potential energy models havedemonstrated the capability to conduct large-scale,long-duration simulations with the accuracy of ab initio electronic structure ***,the model generation process remains a bottleneck for large-scale *** propose a shift towards a model-centric ecosystem,wherein a large atomic model(LAM),pretrained across multiple disciplines,can be efficiently fine-tuned and distilled for various downstream tasks,thereby establishing a new framework for molecular *** this study,we introduce the DPA-2 architecture as a prototype for ***-trained on a diverse array of chemical and materials systemsusing a multi-task approach,DPA-2demonstrates superior generalization capabilities across multiple downstream tasks compared to the traditional single-task pre-training and fine-tuning *** approach sets the stage for the development and broad application of LAMs in molecular and materials simulation research.

关键词： DPA establishing thereby

来源：评论

学校读者我要写书评

暂无评论

Optical waveform engineering of non-Gaussian states

Optical waveform engineering of non-Gaussian states

引用

2023 Conference on Lasers and Electro-Optics Europe and European Quantum Electronics Conference, CLEO/Europe-EQEC 2023

作者： Kawasaki, Akito Takase, Kan Jeong, Byung Kyu Kashiwazaki, Takahiro Kazama, Takushi Enbutsu, Koji Watanabe, Kei Umeki, Takeshi Miki, Shigehito Terai, Hirotaka Yabuno, Masahiro China, Fumihiro Asavanant, Warit Endo, Mamoru Yoshikawa, Jun-Ichi Furusawa, Akira Department of Applied Physics School of Engineering The University of Tokyo 7-3-1 Hongo Bunkyo-ku Tokyo113-8656 Japan Optical Quantum Computing Research Team RIKEN Center for Quantum Computing 2-1 Hirosawa Saitama Wako351-0198 Japan NTT Device Technology Labs NTT Corporation 3-1 Morinosato Wakamiya Kanagawa Atsugi243-0198 Japan Graduate School of Engineering Kobe University 1-1 Rokkodai-cho Nada-ku Hyogo Kobe657-0013 Japan Advanced ICT Research Institute National Institute of Information and Communications Technology 588-2 Iwaoka Nishi-ku Hyogo Kobe651-2492 Japan

ISBN: (纸本)9798350345995

Toward the realization of quantum information processing (QIP), continuous-variable (CV) system is a promising candidate, where scalable quantum information processors are already demonstrated [1]. The next milestone is the demonstration of universality and fault-tolerance on these processors by injecting highly non-classical quantum states, non-Gaussian states (NGSs), with a proper temporal waveform [2]. NGSs are very fragile to optical losses, however, and engineering temporal waveform of NGSs is a quite nontrivial task that requires completely different methodology from conventional optical wave shaping. © 2023 IEEE.

关键词： Fault tolerance

来源：评论

学校读者我要写书评

暂无评论

Search for the Sagittarius tidal stream of axion dark matter around 4.55 μeV

引用

Physical Review D 2023年第2期108卷 L021304-L021304页

作者： Andrew K. Yi Saebyeok Ahn Çağlar Kutlu JinMyeong Kim Byeong Rok Ko Boris I. Ivanov HeeSu Byun Arjan F. van Loo SeongTae Park Junu Jeong Ohjoon Kwon Yasunobu Nakamura Sergey V. Uchaikin Jihoon Choi Soohyung Lee MyeongJae Lee Yun Chang Shin Jinsu Kim Doyu Lee Danho Ahn SungJae Bae Jiwon Lee Younggeun Kim Violeta Gkika Ki Woong Lee Seonjeong Oh Taehyeon Seong DongMin Kim Woohyun Chung Andrei Matlashov SungWoo Youn Yannis K. Semertzidis Department of Physics Korea Advanced Institute of Science and Technology Daejeon 34141 Republic of Korea Center for Axion and Precision Physics Research Institute for Basic Science Daejeon 34051 Republic of Korea RIKEN Center for Quantum Computing (RQC) Wako Saitama 351-0198 Japan Department of Applied Physics Graduate School of Engineering The University of Tokyo Bunkyo-ku Tokyo 113-8656 Japan

We report the first search for the Sagittarius tidal stream of axion dark matter around 4.55 μeV using CAPP-12 TB haloscope data acquired in March of 2022. Our result excluded the Sagittarius tidal stream of Dine-Fischler-Srednicki-Zhitnitskii and Kim-Shifman-Vainshtein-Zakharov axion dark matter densities of ρa≳0.184 and ≳0.025 GeV/cm3, respectively, over a mass range from 4.51 to 4.59 μeV at a 90% confidence level.

关键词： Dark matter Particle dark matter Axions Galactic halos Dark matter detectors Microwave techniques

来源：评论

学校读者我要写书评

暂无评论

建议与咨询留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

时间限定

文献类型

馆藏选择

核心期刊

语言

文献类型

帮助

文字说明：

检索规则说明：

检索范例：

分类表

所选分类

限定检索结果

文献类型

馆藏范围

日期分布

学科分类号

主题

机构

作者

语言

请选择保存的检索档案：

请选择收藏分类：

通借通还

建议与咨询 留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

时间限定

文献类型

馆藏选择

核心期刊

语言

文献类型

帮助

文字说明：

检索规则说明：

检索范例：

分类表

所选分类

限定检索结果

文献类型

馆藏范围

日期分布

学科分类号

主题

机构

作者

语言

请选择保存的检索档案： 新增检索档案 确定 取消

请选择收藏分类： 新增自定义分类 确定 取消

通借通还

建议与咨询留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

请选择保存的检索档案：

请选择收藏分类：