检索结果-内蒙古大学图书馆

SSRN 2024年

作者： Wang, Qin Wang, Xizhao Big Data Institute College of Computer Science and Software Engineering Shenzhen University Shenzhen518060 China The Guangdong Key Laboratory of Intelligent Information Processing Shenzhen University Shenzhen518060 China

Long-tail distributed data hinders the practical application of state-of-the-art deep models in computer vision. Consequently, exclusive methodologies for handling the long-tailed problem are proposed, focusing on different hierarchies. For embedding hierarchy, existing works manually augment the diversity of tail-class features for specific datasets. However, prior knowledge about datasets is not always available for practical use, which brings unsatisfactory generalization ability in human fine-turned augmentation under such circumstances. To figure out this problem, we introduce a novel model named Bilinear-Experts Network (BENet) with Self-Adaptive Sampler (SAS). This model leverages model-driven perturbations to tail-class embeddings while preserving generalization capability on head classes through a designed bilinear experts system. The designed perturbations adaptively augment tail-class space and shift the class boundary away from the tail-class centers. Moreover, we surprisingly find that SAS automatically assigns more significant perturbations to specific tail classes rather than fewer-sample classes, which is against the common assumption that fewer-sample classes deserve greater attention. Also, experiments conducted across various long-tailed benchmarks validate the comparable efficacy of proposed BENet. © 2024, The Authors. All rights reserved.

关键词： Embeddings

来源：评论

学校读者我要写书评

暂无评论

Generative Replay Method Based on Integrating Random Gating and Attention Mechanism

Generative Replay Method Based on Integrating Random Gating ...

引用

International Conference on Computer and Communications (ICCC)

作者： Yao He Jing Yang Qinglang Li Hongchao An Fengyuan Zhang School of Mechanical Engineering Guizhou University State Key Laboratory of Public Big Data Guizhou University Guiyang China School of Mechanical Engineering Guizhou University Guiyang China

Artificial neural networks aspire to mimic human intelligence by constantly learning from a series of tasks without forgetting past knowledge. The most typical way to achieve this kind of learning is to store previously learned task data and replay previously stored data when training a new task. However, the performance of these methods will be affected with the reduction of memory during training. To solve this problem, a new generative replay algorithm is proposed in this paper —— A generative replay method based on the fusion of random gating and attention mechanism. This method is used to generate visual significance features for the model to remember past sample information. First, we introduce an attention mechanism into the generated model to address the issue of the quality of the generated replay data. This mechanism enhances the data salience of feature information during large-scale model training and allows the generated replay network to produce visual salience features, which essentially mimic the way a human observes. Secondly, because of the overfitting phenomenon in the training process of the model, a random gating mechanism is introduced to improve the generalization of the model and improve the accuracy of the model. Finally, we use the CIFAR100 and Permuted MNIST datasets to validate the efficacy of our method.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Dual Encoders for Diffusion-based Image Inpainting

Dual Encoders for Diffusion-based Image Inpainting

引用

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

作者： Dezhi Zheng Kaijun Deng Jinbao Wang Linlin Shen Computer Vision Institute School of Computer Science and Software Engineering Shenzhen University Shenzhen China National Engineering Laboratory for Big Data System Computing Technology Shenzhen University Shenzhen China Guangdong Provincial Key Laboratory of Intelligent Information Processing Shenzhen China

ISBN: (数字)9798350368741

ISBN: (纸本)9798350368758

Current diffusion-based inpainting models struggle to preserve unmasked regions or generate highly coherent content. Additionally, it is hard for them to generate meaningful content for 3D inpainting. To tackle these challenges, we design a plug-and-play branch that runs through the entire generation process to enhance existing models. Specifically, we utilize dual encoders - a Convolutional Neural Network (CNN) encoder and the pre-trained Variational AutoEncoder (VAE) encoder, to encode masked images. The latent code and the feature map from the dual encoders are fed to diffusion models simultaneously. In addition, we apply Zero-padded initialization to solve the problem of mode collapse caused by this branch. Experiments on BrushBench and EditBench demonstrate that models with our plug-and-play branch can improve the coherence of inpainting, and our model achieves new state-of-the-art results.

关键词： Visualization Three-dimensional displays Codes Autoencoders Coherence Signal processing Diffusion models Decoding Convolutional neural networks Speech processing

来源：评论

学校读者我要写书评

暂无评论

big-MOE: BYPASS ISOLATED GATING MOE FOR GENERALIZED MULTIMODAL FACE ANTI-SPOOFING

arXiv

引用

arXiv 2024年

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

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/bigMoE. Copyright © 2024, The Authors. All rights reserved.

关键词： HTTP

来源：评论

学校读者我要写书评

暂无评论

A First Look at LLM-powered Smartphones

A First Look at LLM-powered Smartphones

引用

IEEE/ACM International Conference on Automated Software engineering - Workshops (ASE Workshops)

作者： Liangxuan Wu Yanjie Zhao Chao Wang Tianming Liu Haoyu Wang Huazhong University of Science and Technology Wuhan China Hubei Key Laboratory of Distributed System Security Hubei Engineering Research Center on Big Data Security School of Cyber Science and Engineering Huazhong University of Science and Technology

ISBN: (数字)9798400712494

ISBN: (纸本)9798331523169

The integration of Large Language Models (LLMs) into edge devices such as smartphones represents a significant leap in mobile technology, promising enhanced user experiences and novel functionalities. This paper presents a first look at LLM-powered smartphones, addressing four key aspects: the current market landscape, core functions enabled by integrated LLMs, potential security risks, and user perceptions. The findings reveal a rapidly evolving market with major manufacturers competing to integrate LLMs, innovative features that improve user interaction, significant security challenges, and mixed user perceptions that balance enthusiasm for new capabilities with privacy concerns. This study contributes to understanding LLM integration in mobile devices and its implications for users, manufacturers, and the broader technological landscape.

关键词： Industries Privacy Technological innovation Ethics Large language models Conferences User experience Security Smart phones Software engineering

来源：评论

学校读者我要写书评

暂无评论

Solid-SQL: Enhanced Schema-linking based In-context Learning for Robust Text-to-SQL

arXiv

引用

arXiv 2024年

作者： Liu, Geling Tan, Yunzhi Zhong, Ruichao Xie, Yuanzhen Zhao, Lingchen Wang, Qian Hu, Bo Li, Zang School of Cyber Science and Engineering Wuhan University China Big Data and AI Platform Department Tencent China Key Laboratory of Aerospace Information Security and Trusted Computing Ministry of Education China

Recently, large language models (LLMs) have significantly improved the performance of text-to-SQL systems. Nevertheless, many state-of-the-art (SOTA) approaches have overlooked the critical aspect of system robustness. Our experiments reveal that while LLM-driven methods excel on standard datasets, their accuracy is notably compromised when faced with adversarial perturbations. To address this challenge, we propose a robust text-to-SQL solution, called Solid-SQL, designed to integrate with various LLMs. We focus on the pre-processing stage, training a robust schema-linking model enhanced by LLM-based data augmentation. Additionally, we design a two-round, structural similarity-based example retrieval strategy for in-context learning. Our method achieves SOTA SQL execution accuracy levels of 82.1% and 58.9% on the general Spider and Bird benchmarks, respectively. Furthermore, experimental results show that Solid-SQL delivers an average improvement of 11.6% compared to baselines on the perturbed Spider-Syn, Spider-Realistic, and Dr. Spider benchmarks. Copyright © 2024, The Authors. All rights reserved.

关键词： Adversarial machine learning

来源：评论

学校读者我要写书评

暂无评论

USED: Universal Speaker Extraction and Diarization

IEEE Transactions on Audio, Speech and Language Processing

引用

IEEE Transactions on Audio, Speech and Language Processing 2024年 33卷 96-110页

作者： Junyi Ao Mehmet Sinan Yıldırım Ruijie Tao Meng Ge Shuai Wang Yanmin Qian Haizhou Li Shenzhen Research Institute of Big Data School of Data Science The Chinese University of Hong Kong Shenzhen China Department of Electrical and Computer Engineering National University of Singapore Singapore Saw Swee Hock School of Public Health National University of Singapore Singapore Shenzhen Research Institute of Big Data Shenzhen China Auditory Cognition and Computational Acoustics Lab Department of Computer Science and Engineering and the MoE Key Laboratory of Artificial Intelligence AI Institute Shanghai Jiao Tong University Shanghai China

Speaker extraction and diarization are two enabling techniques for real-world speech applications. Speaker extraction aims to extract a target speaker's voice from a speech mixture, while speaker diarization demarcates speech segments by speaker, annotating ‘who spoke when’. Previous studies have typically treated the two tasks independently. In practical applications, it is more meaningful to have knowledge about ‘who spoke what and when’, which is captured by the two tasks. The two tasks share a similar objective of disentangling speakers. Speaker extraction operates in the frequency domain, whereas diarization is in the temporal domain. It is logical to believe that speaker activities obtained from speaker diarization can benefit speaker extraction, while the extracted speech offers more accurate speaker activity detection than the speech mixture. In this paper, we propose a unified model called Universal Speaker Extraction and Diarization (USED) to address output inconsistency and scenario mismatch issues. It is designed to manage speech mixtures with varying overlap ratios and variable number of speakers. We show that the USED model significantly outperforms the competitive baselines for speaker extraction and diarization tasks on LibriMix and SparseLibriMix datasets. We further validate the diarization performance on CALLHOME, a dataset based on real recordings, and experimental results indicate that our model surpasses recently proposed approaches.

关键词： Speech recognition data mining Training Multitasking Speech enhancement Time-domain analysis Recording Predictive models Particle separators Oral communication

来源：评论

学校读者我要写书评

暂无评论

Two-Layer Network Configuration Optimization Approach Considering Primary And Backup Paths

Two-Layer Network Configuration Optimization Approach Consid...

引用

International Conference on big data and Information Analytics (bigDIA)

作者： Boyang Diao Luohao Tang Zhong Yang Xianyi Fu Zhuoting Yu Cheng Zhu National Key Laboratory of Information Systems Engineering National University of Defense Technology Changsha China Laboratory for Big Data and Decision National University of Defense Technology Changsha China College of Systems Engineering National University of Defense Technology Changsha China

ISBN: (数字)9798350354621

ISBN: (纸本)9798350354638

The study of logical-physical networks has signifi-cant meaning, as these networks play a vital role in our daily life. The analysis of their configurations is of paramount importance for ensuring their stability and resilience. In this paper, we propose a mixed-integer planning model that considers primary and backup paths to improve the robustness of the two-layer logical-physical networks. Based on the Monte Carlo simulation method and genetic algorithm, the configuration scheme with the highest expectation of the robustness metric is presented. Experiments are conducted on a case study of network configu-ration with and without backup paths considering random edge failures. The findings illustrate that the incorporation of backup paths can markedly enhance the expectation of robustness metric, thereby reinforcing its stability and resilience of the logical-nhvsical network.

关键词： Measurement Monte Carlo methods big data Robustness Stability analysis Planning Optimization Resilience Genetic algorithms

来源：评论

学校读者我要写书评

暂无评论

Vehicle platoon in road traffic: A survey of modeling, communication, controlling and perspectives

引用

Physica A: Statistical Mechanics and its Applications 2025年 674卷

作者： Li, Haijian Meng, Weizhe Han, ZongLin Zhang, Zihan Yang, Yanfang Beijing Key Laboratory of Traffic Engineering Beijing University of Technology Beijing100124 China China Academy of Urban Planning & Design Beijing100044 China Laboratory of Transport Industry of Big Data Application Technologies for Comprehensive Transport China Academy of Transportation Sciences Beijing100029 China

This paper reviews the important role of vehicle platooning in road transportation, analyzing key aspects including modeling, communication, and control strategies. It provides a detailed examination of following and lane-changing models, emphasizing their significance in autonomous platooning control, while also identifying potential future directions for model development. The paper explores key communication technologies like Vehicle-to-Vehicle (V2V) communication and 5 G, discussing their applications in platooning systems. In terms of control strategies, the paper delves into both vertical and horizontal control methods for platooning, evaluating the stability of control mechanisms. This review aims to offer a comprehensive understanding of platooning technology and presents valuable insights to guide future research and development in this field. © 2025 Elsevier B.V.

关键词： Truck transportation

来源：评论

学校读者我要写书评

暂无评论

面向排放测算的随机性对跟驰模型车队稳定性的影响研究

引用

Journal of Central South University 2023年第8期30卷 2772-2789页

作者：孟冬利宋国华鲁洪语吴亦政翟志强于雷 Key Laboratory of Transport Industry of Big Data Application Technologies for Comprehensive Transport Beijing Jiaotong UniversityBeijing 100044China School of Civil and Environmental Engineering Georgia Institute of TechnologyAtlantaGA 30332USA Department of Transportation Studies Texas Southern UniversityHoustonTX 77004USA

在基于微观交通仿真模型进行交通能耗排放评估时,跟驰模型生成的车辆轨迹无法代表实际交通环境的驾驶特性,从而导致显著的排放测算误差,同时车辆排放在车队中的稳定性未被充分考虑。本文基于真实的车队轨迹比较了Gipps跟驰模型、全速差... 详细信息

在基于微观交通仿真模型进行交通能耗排放评估时,跟驰模型生成的车辆轨迹无法代表实际交通环境的驾驶特性,从而导致显著的排放测算误差,同时车辆排放在车队中的稳定性未被充分考虑。本文基于真实的车队轨迹比较了Gipps跟驰模型、全速差模型(FVDM)、智能驾驶员模型(IDM)和Wiedemann模型的面向排放测算的车队稳定性,分析了参数敏感性和随机性对跟驰模型的影响,提出了考虑随机参数的Gipps跟驰模型。结果表明,与Wiedemann模型相比,FVD模型和IDM模型在排放测算方面的误差较小,并且上述三个模型的排放测算误差沿车队是稳定的。Gipps模型能够真实地刻画车队中第一辆跟驰车的车辆动力学,但排放测算误差沿车队逐渐增大。参数敏感性分析表明模型参数标定难以提高Gipps模型的车队稳定性。结合随机参数对Gipps跟驰模型进行优化后,加速度分布均方根误差、VSP分布均方根误差和排放因子相对误差分别降低了5.00%、2.52%和11.04%,车队误差的标准差分别为0.18%、0.08%和0.86%,这表明随机参数能够提高Gipps跟驰模型面向排放测算的车队稳定性,提升仿真轨迹用于车辆能耗排放评估的准确性。

关键词：跟驰模型车队稳定性随机性排放测算 VSP分布

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：