检索结果-内蒙古大学图书馆

Interpolation Method of Head-Related Transfer Functions Based on Common-Pole/Zero Modeling

学校读者我要写书评

暂无评论

China Communications 2020年第10期17卷 170-182页

作者： Wei Chen Xiaochen Wang Ruimin Hu Gang Li Weiping Tu National Engineering Research Center for Multimedia Software School of Computer ScienceWuhan UniversityWuhan 430072China Hubei Key Laboratory of Multimedia and Network Communication Engineering Wuhan UniversityWuhan 430072China Research Institute of Wuhan University in Shenzhen China

The head-related transfer function(HRTF)involves the cues for human auditory localization,which turns it into an essential item of virtual auditory display *** practice,the interpolation of HRTF is necessary for the virtual auditory display systems to achieve high spatial *** geometric-based interpolation methods are generally restrained by the spatial distribution of reference on *** the spatial distribution is sparse,the accuracy of interpolation decreases ***,an interpolation method using the common-pole/zero model and the fitting neural network is ***,we propose a common-pole/zero model to represent HRTFs across multiple subjects,in which the low-dimensional features of the measured HRTFs are ***,for a new spatial direction,we predict the corresponding low-dimensional HRTF with a fitting neural ***,we reconstruct the high-dimensional HRTF from the predicted low-dimensional *** simulation results suggest that the proposed method outperforms other interpolation methods such as Linear_AMBC,Bilinear_AMBC,and the Combination method.

关键词： HRTF interpolation fitting neural network common-pole/zero model

Interpretability is a Kind of Safety: An Interpreter-based Ensemble for Adversary Defense

学校读者我要写书评

暂无评论

arXiv 2023年

作者： Wang, Jingyuan Wu, Yufan Li, Mingxuan Lin, Xin Wu, Junjie Li, Chao MOE Engineering Research Center of ACAT School of Computer Science Engineering Beihang University China Beijing Key Laboratory of ESSTCO School of Economics and Management Beihang University Beijing China State Key Laboratory of Software Development Environment Beihang University Beijing100191 China Beijing Advanced Innovation Center for BDBC Beihang University Beijing China

While having achieved great success in rich real-life applications, deep neural network (DNN) models have long been criticized for their vulnerability to adversarial attacks. Tremendous research efforts have been dedicated to mitigating the threats of adversarial attacks, but the essential trait of adversarial examples is not yet clear, and most existing methods are yet vulnerable to hybrid attacks and suffer from counterattacks. In light of this, in this paper, we first reveal a gradient-based correlation between sensitivity analysis-based DNN interpreters and the generation process of adversarial examples, which indicates the Achilles's heel of adversarial attacks and sheds light on linking together the two long-standing challenges of DNN: fragility and unexplainability. We then propose an interpreter-based ensemble framework called X-Ensemble for robust adversary defense. X-Ensemble adopts a novel detection-rectification process and features in building multiple sub-detectors and a rectifier upon various types of interpretation information toward target classifiers. Moreover, X-Ensemble employs the Random Forests (RF) model to combine sub-detectors into an ensemble detector for adversarial hybrid attacks defense. The non-differentiable property of RF further makes it a precious choice against the counterattack of adversaries. Extensive experiments under various types of state-of-the-art attacks and diverse attack scenarios demonstrate the advantages of X-Ensemble to competitive baseline methods. Copyright © 2023, The Authors. All rights reserved.

关键词： Deep neural networks

科学研究的第五范式——以智能驱动的材料设计为例

学校读者我要写书评

暂无评论

engineering 2023年第5期24卷 126-137,I0003,I0004页

作者： Can Leng Zhuo Tang Yi-Ge Zhou Zean Tian Wei-Qing Huang Jie Liu Keqin Li Kenli Li Science and Technology on Parallel and Distributed Processing Laboratory National University of Defense TechnologyChangsha 410073China Laboratory of Software Engineering for Complex Systems National University of Defense TechnologyChangsha 410073China National Supercomputing Center in Changsha Changsha 410082China College of Computer Science and Electronic Engineering Hunan UniversityChangsha 410082China Institute of Chemical Biology and Nanomedicine State Key Laboratory of Chemo/Biosensing and ChemometricsCollege of Chemistry and Chemical EngineeringHunan UniversityChangsha 410082China Department of Applied Physics School of Physics and ElectronicsHunan UniversityChangsha 410082China Department of Computer Science State University of New YorkNew PaltzNY 12561USA

科学正在进入一个新时代——第五范式——它被认为是知识整合到不同领域的主要特征,是基于无所不在的机器学习系统的计算社区中智能驱动的工作。在此,我们通过在天河一号超级计算机系统上构建的催化材料专门设计的典型平台案例,生动地... 详细信息

科学正在进入一个新时代——第五范式——它被认为是知识整合到不同领域的主要特征,是基于无所不在的机器学习系统的计算社区中智能驱动的工作。在此,我们通过在天河一号超级计算机系统上构建的催化材料专门设计的典型平台案例,生动地阐明了第五范式的本质,旨在促进第五范式在其他领域的培养。第五范式平台主要包括模型自动构建(原始数据提取)、指纹自动构建(神经网络特征选择)以及跨学科知识串联的重复迭代(“火山图”)。与分解一起进行的是对迭代中实现的体系结构的性能评估。通过讨论,第五范式的智能驱动平台可以极大地简化和改进研究中极其繁琐和具有挑战性的工作,并通过补偿机器学习中缺少样本和替代一些由于计算资源不足而导致的数值计算来实现数值计算与机器学习之间的相互反馈,从而加速探索过程。在数据驱动的学科中,跨学科专家的协同作用和对动态数据需求的急剧增长仍然是一个挑战。我们相信,对第五范式平台的一瞥可以为其在其他领域的应用铺平道路。

关键词：机器学习自动构建天河一号数据驱动神经网络动态数据知识整合科学研究

DeepSolo++: Let Transformer Decoder with Explicit Points Solo for Multilingual Text Spotting

学校读者我要写书评

暂无评论

arXiv 2023年

作者： Ye, Maoyuan Zhang, Jing Zhao, Shanshan Liu, Juhua Liu, Tongliang Du, Bo Tao, Dacheng School of Computer Science National Engineering Research Center for Multimedia Software Institute of Artificial Intelligence Hubei Key Laboratory of Multimedia and Network Communication Engineering Wuhan University Wuhan China School of Computer Science Faculty of Engineering The University of Sydney Australia JD Explore Academy *** China College of Computing & Data Science Nanyang Technological University Singapore

End-to-end text spotting aims to integrate scene text detection and recognition into a unified framework. Dealing with the relationship between the two sub-tasks plays a pivotal role in designing effective spotters. Although Transformer-based methods eliminate the heuristic post-processing, they still suffer from the synergy issue between the sub-tasks and low training efficiency. Besides, they overlook the exploring on multilingual text spotting which requires an extra script identification task. In this paper, we present DeepSolo++, a simple DETR-like baseline that lets a single Decoder with Explicit Points Solo for text detection, recognition, and script identification simultaneously. Technically, for each text instance, we represent the character sequence as ordered points and model them with learnable explicit point queries. After passing a single decoder, the point queries have encoded requisite text semantics and locations, thus can be further decoded to the center line, boundary, script, and confidence of text via very simple prediction heads in parallel. Furthermore, we show the surprisingly good extensibility of our method, in terms of character class, language type, and task. On the one hand, our method not only performs well in English scenes but also masters the transcription with complex font structure and a thousand-level character classes, such as Chinese. On the other hand, our DeepSolo++ achieves better performance on the additionally introduced script identification task with a simpler training pipeline compared with previous methods. Extensive experiments on public benchmarks demonstrate that our simple approach achieves better training efficiency compared with Transformer-based models and outperforms the previous state-of-the-art. For example, on ICDAR 2019 ReCTS for Chinese text, our method boosts the 1-NED metric to a new record of 78.3%. On ICDAR 2019 MLT, DeepSolo++ achieves absolute 5.5% H-mean and 8.0% AP improvements on joint detection an

关键词： Semantics

Cramér-Rao Bound Minimization for a Passive Sensing Multi-ISAC System

学校读者我要写书评

暂无评论

IEEE Transactions on Vehicular Technology 2025年

作者： Chen, Jian Chen, Qikai Deng, Yansha Jia, Jie Yin, Baoxin Wang, Xingwei Northeastern University School of Computer Science and Engineering Shenyang110819 China Northeastern University Engineering Research Center of Security Technology of Complex Network System Ministry of Education Shenyang110819 China Northeastern University Key Laboratory of Intelligent Computing in Medical Image Ministry of Education Shenyang110819 China King's College London LondonWC2R 2LS United Kingdom

The integrated sensing and communication (ISAC) system can simultaneously provide communication and radar sensing, effectively improving spectrum utilization. However, existing research mainly focuses on the mono-static sensing ISAC system, which has shortcomings in limited sensing range and accuracy. We thus investigate a passive sensing multi-ISAC system with multiple communication users and sensing targets, and consider two cases for multi-target sensing without and with prior target knowledge at the base stations (BSs), in which the BSs are interested in estimating the targets' response matrix and channel coefficients, respectively. We also formulate a joint beamforming problem to minimize the Cramér-Rao bound (CRB) of the worst estimation constrained by communication requirements, and obtain the optimal solution with semidefinite relaxation (SDR) assisted transformation. To verify the advantages of our proposed scheme, we consider the bi-static BSs system (B-B) and beamforming with sensing interference cancellation (W-S) as two benchmark schemes. Numerical results illustrate that the proposed scheme obtains better sensing performance and effectively alleviates the effect caused by sensing interference. © 1967-2012 IEEE.

关键词： Cramer-Rao bounds

E2S2: Encoding-Enhanced Sequence-to-Sequence Pretraining for Language Understanding and Generation

学校读者我要写书评

暂无评论

arXiv 2022年

作者： Zhong, Qihuang Ding, Liang Liu, Juhua Du, Bo Tao, Dacheng The School of Computer Science National Engineering Research Center for Multimedia Software Institute of Artificial Intelligence Hubei Key Laboratory of Multimedia and Network Communication Engineering Wuhan University Wuhan China The School of Computer Science Faculty of Engineering The University of Sydney Australia

Sequence-to-sequence (seq2seq) learning is a popular fashion for large-scale pretraining language models. However, the previous seq2seq pretraining models generally focus on reconstructive objectives on the decoder side and neglect the effect of encoder-side supervision, which we argue may lead to sub-optimal performance. To verify our hypothesis, we first empirically study the functionalities of the encoder and decoder in seq2seq pretrained language models, and find that the encoder takes an important but under-exploitation role than the decoder regarding the downstream performance and neuron activation. Therefore, we propose an encoding-enhanced seq2seq pretraining strategy, namely E2S2, which improves the seq2seq models via integrating more efficient self-supervised information into the encoders. Specifically, E2S2 adopts two self-supervised objectives on the encoder side from two aspects: 1) locally denoising the corrupted sentence (denoising objective);and 2) globally learning better sentence representations (contrastive objective). With the help of both objectives, the encoder can effectively distinguish the noise tokens and capture high-level (i.e., syntactic and semantic) knowledge, thus strengthening the ability of seq2seq model to accurately achieve the conditional generation. On a large diversity of downstream natural language understanding and generation tasks, E2S2 dominantly improves the performance of its powerful backbone models, e.g., BART and T5. For example, upon BART backbone, we achieve +1.1% averaged gain on the general language understanding evaluation (GLUE) benchmark and +1.75% F0.5 score improvement on CoNLL2014 dataset. We also provide in-depth analyses to show the improvement stems from better linguistic representation. We hope that our work will foster future self-supervision research on seq2seq language model pretraining. Copyright © 2022, The Authors. All rights reserved.

关键词： Semantics

Hierarchical Reverse Games for the Resource Ecosystem in Cloud-Edge Computing

学校读者我要写书评

暂无评论

IEEE Transactions on Consumer Electronics 2024年

作者： Pei, Manlin Wang, Chenyu Wang, Xia Zheng, Zhigao Huang, Jianhui Wang, Shengling Guo, Yufei School of Computer and Information Technology Beijing Jiaotong University Beijing China Department of Computer Science Georgia State University United States Beijing University of Technology School of Statistics and Data Science Faculty of Science Beijing China Institute of Artificial Intelligence School of Computer Science National Engineering Research Center for Multimedia Software Hubei Key Laboratory of Multimedia and Network Communication Engineering Hubei Luojia Laboratory Wuhan University Wuhan China Chinese Academy of Sciences Institute of Computing Technology Beijing China Beijing Normal University School of Artificial Intelligence Beijing China George Washington University Department of Statistics United States

Edge computing has emerged as a killer technology for a hyper-connected world due to its distributed architecture and customer-proximity property. Combined edge nodes with the cloud data center, a cloud-edge computing paradigm is formed, whose resource ecosystem calls for competitive pricing and optimal resource allocation. However, it is not feasible to realize global information-based optimization since some information is kept private to their owners. To solve this challenge, this paper develops the user-independent hierarchical reverse game and the user-assisted hierarchical reverse game to depict the relationship among the resource provider, the resource tenant, and the resource user. The aim is to seek the optimal strategies for players without revealing any private information. The common trait of both games is to force the players to report the optimal strategies based on their actual private information. This salient trait can produce privacy-preservation optimization since there is no requirement for the players to release their individual information directly, and the optimal strategies of other players can be deduced naturally. The difference between the user-independent hierarchical reverse game and the user-assisted one is that the game rules are stipulated entirely by the provider and the tenants (edge nodes) in the former, while some game rules can be customized according to the advice of users in the latter. This leads the user-independent hierarchical reverse game is more concise and easy to guarantee the incentive compatibility constraint, while the user-assisted hierarchical reverse game can attract more users since the game rules can adapt to their economic status, requirements, and preferences. © 1975-2011 IEEE.

关键词： Cloud platforms

RFL-CDNet: Towards Accurate Change Detection via Richer Feature Learning

学校读者我要写书评

暂无评论

arXiv 2024年

作者： Gan, Yuhang Xuan, Wenjie Chen, Hang Liu, Juhua Du, Bo School of Computer Science Wuhan University Wuhan China National Engineering Research Center for Multimedia Software Wuhan University Wuhan China Institute of Artificial Intelligence Wuhan University Wuhan China Hubei Key Laboratory of Multimedia and Network Communication Engineering Wuhan University Wuhan China Land Satellite Remote Sensing Application Center MNR Beijing China

Change Detection is a crucial but extremely challenging task of remote sensing image analysis, and much progress has been made with the rapid development of deep learning. However, most existing deep learning-based change detection methods mainly focus on intricate feature extraction and multi-scale feature fusion, while ignoring the insufficient utilization of features in the intermediate stages, thus resulting in sub-optimal results. To this end, we propose a novel framework, named RFL-CDNet, that utilizes richer feature learning to boost change detection performance. Specifically, we first introduce deep multiple supervision to enhance intermediate representations, thus unleashing the potential of backbone feature extractor at each stage. Furthermore, we design the Coarse-To-Fine Guiding (C2FG) module and the Learnable Fusion (LF) module to further improve feature learning and obtain more discriminative feature representations. The C2FG module aims to seamlessly integrate the side prediction from previous coarse-scale into the current fine-scale prediction in a coarse-to-fine manner, while LF module assumes that the contribution of each stage and each spatial location is independent, thus designing a learnable module to fuse multiple predictions. Experiments on several benchmark datasets show that our proposed RFL-CDNet achieves state-of-the-art performance on WHU cultivated land dataset and CDD dataset, and the second best performance on WHU building dataset. The source code and models are publicly available at https://***/Hhaizee/RFL-CDNet. Copyright © 2024, The Authors. All rights reserved.

关键词： Change detection

Self-Evolution Learning for Discriminative Language Model Pretraining

学校读者我要写书评

暂无评论

arXiv 2023年

作者： Zhong, Qihuang Ding, Liang Liu, Juhua Du, Bo Tao, Dacheng National Engineering Research Center for Multimedia Software Institute of Artificial Intelligence School of Computer Science Hubei Key Laboratory of Multimedia and Network Communication Engineering Wuhan University China JD Explore Academy China Research Center for Graphic Communication Printing and Packaging Institute of Artificial Intelligence Wuhan University China University of Sydney Australia

Masked language modeling, widely used in discriminative language model (e.g., BERT) pretraining, commonly adopts a random masking strategy. However, random masking does not consider the importance of the different words in the sentence meaning, where some of them are more worthy to be predicted. Therefore, various masking strategies (e.g., entity-level masking) are proposed, but most of them require expensive prior knowledge and generally train from scratch without reusing existing model weights. In this paper, we present Self-Evolution learning (SE), a simple and effective token masking and learning method to fully and wisely exploit the knowledge from data. SE focuses on learning the informative yet under-explored tokens and adaptively regularizes the training by introducing a novel Token-specific Label Smoothing approach. Experiments on 10 tasks show that our SE brings consistent and significant improvements (+1.43∼2.12 average scores) upon different PLMs. In-depth analyses demonstrate that SE improves linguistic knowledge learning and generalization. Copyright © 2023, The Authors. All rights reserved.

关键词： Computational linguistics