检索结果-内蒙古大学图书馆

arXiv 2025年

作者： Pan, Linchao Gao, Can Zhou, Jie Wang, Jinbao College of Computer Science and Software Engineering Shenzhen University China Guangdong Provincial Key Laboratory of Intelligent Information Processing China National Engineering Laboratory for Big Data System Computing Technology Shenzhen University China

Learning with Noisy Labels (LNL) aims to improve the model generalization when facing data with noisy labels, and existing methods generally assume that noisy labels come from known classes, called closed-set noise. However, in real-world scenarios, noisy labels from similar unknown classes, i.e., open-set noise, may occur during the training and inference stage. Such open-world noisy labels may significantly impact the performance of LNL methods. In this study, we propose a novel dual-space joint learning method to robustly handle the open-world noise. To mitigate model overfitting on closed-set and open-set noises, a dual representation space is constructed by two networks. One is a projection network that learns shared representations in the prototype space, while the other is a One-Vs-All (OVA) network that makes predictions using unique semantic representations in the class-independent space. Then, bi-level contrastive learning and consistency regularization are introduced in two spaces to enhance the detection capability for data with unknown classes. To benefit from the memorization effects across different types of samples, class-independent margin criteria are designed for sample identification, which selects clean samples, weights closed-set noise, and filters open-set noise effectively. Extensive experiments demonstrate that our method outperforms the state-of-the-art methods and achieves an average accuracy improvement of 4.55% and an AUROC improvement of 6.17% on CIFAR80N. Copyright © 2025, The Authors. All rights reserved.

关键词： Contrastive Learning

来源：评论

学校读者我要写书评

暂无评论

Enhanced Second-Harmonic Generation Driven by Dual-Quasi Bound States in the Continuum

Enhanced Second-Harmonic Generation Driven by Dual-Quasi Bou...

引用

2023 International Applied Computational Electromagnetics Society Symposium, ACES-China 2023

作者： Liu, Yuhang Ren, Xingang Niu, Kaikun Huang, Zhixiang School of Electronic and Information Engineer Anhui University Hefei230601 China Engineering Technology Research Center of Specific Power Devices with Novel Semiconductor Materials Anhui Province Chizhou247100 China Anhui University Key Laboratory of Intelligent Computing & Signal Processing Ministry of Education Hefei230601 China

ISBN: (纸本)9781733509657

Bound state in the continuum (BIC) is a dark mode with infinitely high quality factors(Q-factors), it has recently attracted considerable research attention in photonics. Here, we present a metasurface that can support two BICs, which consists of AlGaAs. By breaking the structural symmetry, the two BICs are transformed into quasi-bic modes because they are not protected by the symmetry. Furthermore, it is found that the two quasi-BICs resonate near the fundamental and the second harmonic respectively, which can be used to enhance efficiency of second harmonic generation. By exploiting the high Q characteristics of this structure at both frequencies, we can obtain a second harmonic generation efficiency of nearly 10-3 with 1GW/cm2of pump intensity. Our proposed metasurface will offer good prospects for nonlinear operation. © 2023 Applied Computational Electromagnetics Society (ACES).

关键词： Harmonic generation

来源：评论

学校读者我要写书评

暂无评论

Observation of quantum oscillations near the Mott-Ioffe-Regel limit in CaAs3

引用

National Science Review 2024年第12期11卷 122-133页

作者： Yuxiang Wang Minhao Zhao Jinglei Zhang Wenbin Wu Shichao Li Yong Zhang Wenxiang Jiang Nesta Benno Joseph Liangcai Xu Yicheng Mou Yunkun Yang Pengliang Leng Yong Zhang Li Pi Alexey Suslov Mykhaylo Ozerov Jan Wyzula Milan Orlita Fengfeng Zhu Yi Zhang Xufeng Kou Zengwei Zhu Awadhesh Narayan Dong Qian Jinsheng Wen Xiang Yuan Faxian Xiu Cheng Zhang State Key Laboratory of Surface Physics and Institute for Nanoelectronic Devices and Quantum Computing Fudan University State Key Laboratory of Surface Physics and Department of Physics Fudan University Anhui Province Key Laboratory of Condensed Matter Physics at Extreme Conditions High Magnetic Field Laboratory of the Chinese Academy of Sciences State Key Laboratory of Precision Spectroscopy East China Normal University National Laboratory of Solid State Microstructures and Department of Physics Nanjing University Key Laboratory of Artificial Structures and Quantum Control(Ministry of Education) School of Physics and Astronomy Shanghai Jiao Tong University Solid State and Structural Chemistry Unit Indian Institute of Science Wuhan National High Magnetic Field Center and School of Physics Huazhong University of Science and Technology School of Information Science and Technology Shanghai Tech University National High Magnetic Field Laboratory LNCMI-CNRS UPR3228 Université Grenoble Alpes International Center for Quantum Materials School of Physics Peking University School of Physics and Electronic Science East China Normal University Shanghai Center of Brain-Inspired Intelligent Materials and Devices East China Normal University Shanghai Qi Zhi Institute Zhangjiang Fudan International Innovation Center Fudan University Shanghai Research Center for Quantum Sciences

The Mott-Ioffe-Regel limit sets the lower bound of the carrier mean free path for coherent quasiparticle transport. Metallicity beyond this limit is of great interest because it is often closely related to quantum criticality and unconventional superconductivity. Progress along this direction mainly focuses on the strange-metal behaviors originating from the evolution of the quasiparticle scattering rate, such as linear-in-temperature resistivity, while the quasiparticle coherence phenomena in this regime are much less explored due to the short mean free path at the diffusive bound. Here we report the observation of quantum oscillations from Landau quantization near the Mott-Ioffe-Regel limit in CaAs3. Despite the insulator-like temperature dependence of resistivity, CaAs3presents giant magnetoresistance and prominent Shubnikov–de Haas oscillations from Fermi surfaces, indicating highly coherent band transport. In contrast,quantum oscillation is absent in the magnetic torque. The quasiparticle effective mass increases systematically with magnetic fields, manifesting a much larger value than what is expected based on magneto-infrared spectroscopy. This suggests a strong many-body renormalization effect near the Fermi surface. We find that these unconventional behaviors may be explained by the interplay between the mobility edge and the van Hove singularity, which results in the formation of coherent cyclotron orbits emerging at the diffusive bound. Our results call for further study on the electron correlation effect of the van Hove singularity.

关键词： Mott-Ioffe-Regel limit quantum oscillations van Hove singularity mobility edge

来源：评论

学校读者我要写书评

暂无评论

Learning with Open-world Noisy Data via Class-independent Margin in Dual Representation Space 39

Learning with Open-world Noisy Data via Class-independent Ma...

引用

39th Annual AAAI Conference on Artificial Intelligence, AAAI 2025

ISBN: (纸本)157735897X

关键词： Contrastive Learning

来源：评论

学校读者我要写书评

暂无评论

Hierarchical Policies of Subgoals for Safe Deep Reinforcement Learning 2nd

Hierarchical Policies of Subgoals for Safe Deep Reinforcem...

引用

2nd International Conference on Ubiquitous Security, UbiSec 2022

作者： Yu, Fumin Gao, Feng Yuan, Yao Xing, Xiaofei Dai, Yinglong College of Information Science and Engineering Hunan Normal University Changsha410081 China School of Computer Science and Cyber Engineering Guangzhou University Guangzhou510006 China College of Liberal Arts and Sciences National University of Defense Technology Changsha410073 China Hunan Provincial Key Laboratory of Intelligent Computing and Language Information Processing Changsha410081 China

ISBN: (纸本)9789819902712

Reinforcement learning is a machine learning method that relies on the agent to learn by trial and error to solve decision optimization problems. It is well known that an agent based on deep reinforcement learning in complex environments is difficult to train. Moreover, the agent will generate unsafe and strange actions due to the lack of sufficient reward feedback from the environment. To make the agent converge to a better policy and make its behavior safer and more controllable under sparse rewards, we propose a subgoal embedding method based on prior knowledge and hierarchical strategy that can make the training process converge faster. The subgoal embedding method can be combined with existing reinforcement learning methods. In this paper, we combine the subgoal embedding method with REINFORCE algorithm and PPO(Proximal Policy Optimization) algorithm to test the method in the MiniGrid-Doorkey game environment of the gym platform. The experiments demonstrate the effectiveness of the subgoal embedding method. © 2023, The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd.

关键词： Reinforcement learning

来源：评论

学校读者我要写书评

暂无评论

Big-Moe: Bypassing Isolated Gating For Generalized Multimodal Face Anti-Spoofing

Big-Moe: Bypassing Isolated Gating For Generalized Multimoda...

引用

International Conference on Acoustics, Speech, and Signal processing (ICASSP)

作者： Yingjie Ma Zitong Yu Xun Lin Weicheng Xie Linlin Shen College of Computer Science and Software Engineering Shenzhen University Great Bay University National Engineering Laboratory for Big Data System Computing Technology Shenzhen University Guangdong Provincial Key Laboratory of Intelligent Information Processing

ISBN: (数字)9798350368741

ISBN: (纸本)9798350368758

In the domain of facial recognition security, multimodal Face Anti-Spoofing (FAS) is essential for countering presentation attacks. However, existing technologies encounter challenges due to modality biases and imbalances, as well as domain shifts. Our research introduces a Mixture of Experts (MoE) model to address these issues effectively. We identified three limitations in traditional MoE approaches to multimodal FAS: (1) Coarse-grained experts’ inability to capture nuanced spoofing indicators; (2) Gated networks’ susceptibility to input noise affecting decision-making; (3) MoE’s sensitivity to prompt tokens leading to overfitting with conventional learning methods. To mitigate these, we propose the Bypass Isolated Gating MoE (BIG-MoE) framework, featuring: (1) Fine-grained experts for enhanced detection of subtle spoofing cues; (2) An isolation gating mechanism to counteract input noise; (3) A novel differential convolutional prompt bypass enriching the gating network with critical local features, thereby improving perceptual capabilities. Extensive experiments on four benchmark datasets demonstrate significant generalization performance improvement in multimodal FAS task. The code is released at https://***/murInJ/BIG-MoE.

关键词： Convolutional codes Sensitivity Convolution Face recognition Noise Logic gates Feature extraction Security Speech processing Overfitting

来源：评论

学校读者我要写书评

暂无评论

LEARNING MONOTONIC ATTENTION IN TRANSDUCER FOR STREAMING GENERATION

arXiv

引用

arXiv 2024年

作者： Ma, Zhengrui Feng, Yang Zhang, Min Key Laboratory of Intelligent Information Processing Institute of Computing Technology Chinese Academy of Sciences China Key Laboratory of AI Safety Chinese Academy of Sciences China University of Chinese Academy of Sciences China School of Future Science and Engineering Soochow University China

Streaming generation models are increasingly utilized across various fields, with the Transducer architecture being particularly popular in industrial applications. However, its input-synchronous decoding mechanism presents challenges in tasks requiring non-monotonic alignments, such as simultaneous translation, leading to suboptimal performance in these contexts. In this research, we address this issue by tightly integrating Transducer’s decoding with the history of input stream via a learnable monotonic attention mechanism. Our approach leverages the forward-backward algorithm to infer the posterior probability of alignments between the predictor states and input timestamps, which is then used to estimate the context representations of monotonic attention in training. This allows Transducer models to adaptively adjust the scope of attention based on their predictions, avoiding the need to enumerate the exponentially large alignment space. Extensive experiments demonstrate that our MonoAttn-Transducer significantly enhances the handling of non-monotonic alignments in streaming generation, offering a robust solution for Transducer-based frameworks to tackle more complex streaming generation tasks. Codes: https://***/ictnlp/MonoAttn-Transducer. Copyright © 2024, The Authors. All rights reserved.

关键词： Decoding

来源：评论

学校读者我要写书评

暂无评论

Stacking monolayers at will:A scalable device optimization strategy for two-dimensional semiconductors

引用

Nano Research 2022年第7期15卷 6620-6627页

作者： Xiaojiao Guo Honglei Chen Jihong Bian Fuyou Liao Jingyi Ma Simeng Zhang Xinzhi Zhang Junqiang Zhu Chen Luo Zijian Zhang Lingyi Zong Yin Xia Chuming Sheng Zihan Xu Saifei Gou Xinyu Wang Peng Gong Liwei Liu Xixi Jiang Zhenghua An Chunxiao Cong Zhijun Qiu Xing Wu Peng Zhou Xinyu Chen Ling Tong Wenzhong Bao State Key Laboratory of ASIC and System School of MicroelectronicsZhangjiang Fudan International Innovation CenterFudan UniversityShanghai 200433China The Hong Kong Polytechnic University Shenzhen Research Institute Shenzhen 518057China Department of Physics State Key Laboratory of Surface PhysicsInstitute of Nanoelectronic Devices and Quantum Computing and Key Laboratory of MicroFudan UniversityShanghai 200433China State Key Laboratory of ASIC and System School of Information Science and EngineeringFudan UniversityShanghai 200433China Shanghai Key Laboratory of Multidimensional Information Processing Department of Electronic Engineering East China Normal UniversityShanghai 200241China Shenzhen Six Carbon Technology Shenzhen 518055China Department of Chemistry and Shanghai Key Laboratory of Molecular Catalysis and Innovative Materials Fudan UniversityShanghai 200433China

In comparison to monolayer(1L),multilayer(ML)two-dimensional(2D)semiconducting transition metal dichalcogenides(TMDs)exhibit more application potential for electronic and optoelectronic devices due to their improved current carrying capability,higher mobility,and broader spectral ***,the investigation of devices based on wafer-scale ML-TMDs is still restricted by the synthesis of uniform and high-quality ML *** this work,we propose a strategy of stacking MoS_(2) monolayers via a vacuum transfer method,by which one could obtain wafer-scale high-quality MoS_(2) films with the desired number of layers at *** optical characteristics of these stacked ML-MoS_(2) films(>2L)indicate a weak interlayer *** stacked MLMoS_(2) phototransistors show improved optoelectrical performances and a broader spectral response(approximately 300-1,000 nm)than that of 1L-MoS_(2).Additionally,the dual-gate ML-MoS_(2) transistors enable enhanced electrostatic control over the stacked ML-MoS_(2) channel,and the 3L and 4L thicknesses exhibit the optimal device performances according to the turning point of the current on/off ratio and the subthreshold swing.

关键词： two-dimensional semiconductor field-effect transistors chemical vapor deposition(CVD)synthesis interlayer coupling vacuum transfer method dual-gate transistor

来源：评论

学校读者我要写书评

暂无评论

Enhanced Repetition Pilot Based Timing Synchronization and Channel Estimation for DCO-OFDM OWC Systems

引用

IEEE Wireless Communications Letters 2025年第6期14卷 1608-1612页

作者： Ji, Zhihong Jiang, Yufei Zhu, Xu School of Electronic and Information Engineering Harbin Institute of Technology Shenzhen518055 China The Guangxi Key Laboratory of Brain Inspired Computing and Intelligent Chips School of Electronic and Information Engineering Guangxi Normal University Guilin China Guangdong Provincial Key Laboratory of Aerospace Communication and Networking Technology Harbin Institute of Technology Shenzhen China Shenzhen Key Laboratory of Wireless AIoT Communication Shenzhen518055 China

We design pilots that include some repetition parts to allow timing synchronization and channel estimation for direct current biased optical-orthogonal frequency division multiplexing (DCO-OFDM) optical wireless communication (OWC) systems. On one hand, we propose an enhanced repetition pilot (eRP) based timing synchronization approach, robust against low correlation between real-and-positive signals and against inter-symbol interference (ISI) caused by light emitting diode (LED)'s limited bandwidth, much more than the previous works. We define a new timing metric using the ratio of auto-correlation to power, between the first and second halves of the received pilots. Maximizing the defined timing metric allows the timing offset in the cyclic prefixed (CP) area. The phase difference between a number of adjacent subcarriers is utilized to refine timing synchronization. On the other hand, we propose an eRP based channel estimation enhancement (CEE) approach and an imaginary component minimization (ICM) based channel estimation approach, utilizing pilots the same as timing synchronization. The proposed CEE approach allows the repeated parts of pilots to be averaged for channel estimation enhancement. The proposed ICM approach is divided into LED's limited bandwidth estimation and line-of-sight (LoS) channel estimation, exploring the correlation between the least-square (LS) estimated channel estimate information (CSI) and the trial LED frequency response. The proposed CEE approach provides low complexity, while the proposed ICM approach provides good performance. Simulation results show that, using a single DCO-OFDM symbol, the proposed structure provides bit error rate (BER) close to ideal case with perfect CSI and perfect timing synchronization. © 2012 IEEE.

关键词： Light emitting diodes

来源：评论

学校读者我要写书评

暂无评论

Nonmonotonic propositional logic

引用

Frontiers of Computer Science 2021年第3期15卷 215-216页

作者： Wei LI Yuefei SUI Yuhui WANG State Key Laboratory of Software Development Environment Beihang UniversityBeijing 100191China Key Laboratory of Intelligent Information Processing Institute of Computing TechnologyChinese Academy of SciencesBeijing 100190China School of Computer and Control Engineering University of Chinese Academy of SciencesBeijing 100049China Information Technology Center China Reinsurance(Group)CorporationBeijing 100033China

Propositional logic[1]is basic,based on which other logics are *** deduction system for propositional logic is *** logics are a class of logics which deduction systems are *** ones are default logic[2,3],R-calculus[4]... 详细信息

关键词： default propositional Nonmonotonic

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：