检索结果-内蒙古大学图书馆

Investigating Bi-level optimization for learning and vision from a unified perspective: A survey and beyond

学校读者我要写书评

暂无评论

arXiv 2021年

作者： Liu, Risheng Gao, Jiaxin Zhang, Jin Meng, Deyu Lin, Zhouchen DUT-RU International School of Information Science & Engineering Dalian University of Technology Key Laboratory for Ubiquitous Network Service Software of Liaoning Province Dalian116024 China Department of Mathematics Southern University of Science and Technology National Center for Applied Mathematics Shenzhen China School of Mathematics and Statistics Ministry of Education Key Lab of Intelligent Networks and Network Security Xi’an Jiaotong University Xi’an Shaanxi China School of Electronics Engineering and Computer Science Peking University Beijing100871 China Cooperative Medianet Innovation Center Shanghai Jiao Tong University Shanghai200240 China

Bi-Level Optimization (BLO) is originated from the area of economic game theory and then introduced into the optimization community. BLO is able to handle problems with a hierarchical structure, involving two levels of optimization tasks, where one task is nested inside the other. In machine learning and computer vision fields, despite the different motivations and mechanisms, a lot of complex problems, such as hyper-parameter optimization, multi-task and meta learning, neural architecture search, adversarial learning and deep reinforcement learning, actually all contain a series of closely related subproblms. In this paper, we first uniformly express these complex learning and vision problems from the perspective of BLO. Then we construct a best-response-based single-level reformulation and establish a unified algorithmic framework to understand and formulate mainstream gradient-based BLO methodologies, covering aspects ranging from fundamental automatic differentiation schemes to various accelerations, simplifications, extensions and their convergence and complexity properties. Last but not least, we discuss the potentials of our unified BLO framework for designing new algorithms and point out some promising directions for future research. © 2021, CC BY.

关键词： Deep learning

A chunk-based multi-strategy machine translation method 5th

学校读者我要写书评

暂无评论

A chunk-based multi-strategy machine translation method

5th Euro-China Conference on intelligent Data Analysis and Applications, ECC 2018

作者： Wang, Yiou Zhang, Fuquan Beijing Institute of Science and Technology Information Beijing100044 China Digital Performance and Simulation Technology Lab School of Computer Science and Technology Beijing Institute of Technology Beijing100081 China Fujian Provincial Key Laboratory of Information Processing and Intelligent Control Minjiang University Fuzhou350121 China

ISBN: (纸本)9783030037659

In this paper, a chunk-based multi-strategy machine translation method is proposed. Firstly, an English-Chinese bilingual tree-bank is constructed. Then, a translation strategy based on the chunk that combines statistics and rules is used in the translation stage. Through hierarchical sub-chunks, the input sentence is divided into a set of chunk sequence. Each chunk searches the corresponding instance in the corpus. Translation is completed by recursive refinement from chunks to words. Conditional Random Fields model is used to divide chunks. An experimental English-Chinese translation system is deployed, and experimental results show that the system performs better than the Systran system. © Springer Nature Switzerland AG 2019.

关键词： Machine translation

Resonant beam communications with echo interference elimination

学校读者我要写书评

暂无评论

arXiv 2021年

作者： Xiong, Mingliang Liu, Qingwen Wang, Gang Giannakis, Georgios B. Zhang, Sihai Zhu, Jinkang Huang, Chuan College of Electronics and Information Engineering Tongji University Shanghai201804 China State Key Lab of Intelligent Control and Decision of Complex Systems School of Automation Beijing Institute of Technology Beijing100081 China Department of Electrical and Computer Engineering University of Minnesota MinneapolisMN55455 United States Key Lab of Wireless-Optical Communications University of Science and Technology of China Hefei Anhui230026 China School of Science and Engineering Chinese University of Hong Kong Shenzhen Guangdong518172 Hong Kong

Resonant beam communications (RBCom) is capable of providing wide bandwidth when using light as the carrier. Besides, the RBCom system possesses the characteristics of mobility, high signal-to-noise ratio (SNR), and multiplexing. Nevertheless, the channel of the RBCom system is distinct from other light communication technologies due to the echo interference issue. In this paper, we reveal the mechanism of the echo interference and propose the method to eliminate the interference. Moreover, we present an exemplary design based on frequency shifting and optical filtering, along with its mathematic model and performance analysis. The numerical evaluation shows that the channel capacity is greater than 15 bit/s/Hz. Copyright © 2021, The Authors. All rights reserved.

关键词： Internet of things

Confidence-Regulated Generative Diffusion Models for Reliable AI Agent Migration in Vehicular Metaverses

学校读者我要写书评

暂无评论

arXiv 2025年

作者： Kang, Yingkai Kang, Jiawen Wen, Jinbo Zhang, Tao Yang, Zhaohui Niyato, Dusit Zhang, Yan School of Automation Guangdong University of Technology Guangzhou510006 China College of Computer Science and Technology Nanjing University of Aeronautics and Astronautics Nanjing210016 China School of Cyberspace Science and Technology Beijing Jiaotong University Beijing100044 China College of Information Science and Electronic Engineering Zhejiang Provincial Key Lab of information processing communication and networking Zhejiang University Hangzhou310007 China College of Computing and Data Science Nanyang Technological University Singapore Department of Informatics University of Oslo the Simula Research Laboratory Norway

Vehicular metaverses are an emerging paradigm that merges intelligent transportation systems with virtual spaces, leveraging advanced digital twin and Artificial Intelligence (AI) technologies to seamlessly integrate vehicles, users, and digital environments. In this paradigm, vehicular AI agents are endowed with environment perception, decision-making, and action execution capabilities, enabling real-time processing and analysis of multi-modal data to provide users with customized interactive services. Since vehicular AI agents require substantial resources for real-time decision-making, given vehicle mobility and network dynamics conditions, the AI agents are deployed in RoadSide Units (RSUs) with sufficient resources and dynamically migrated among them. However, AI agent migration requires frequent data exchanges, which may expose vehicular metaverses to potential cyber attacks. To this end, we propose a reliable vehicular AI agent migration framework, achieving reliable dynamic migration and efficient resource scheduling through cooperation between vehicles and RSUs. Additionally, we design a trust evaluation model based on the theory of planned behavior to dynamically quantify the reputation of RSUs, thereby better accommodating the personalized trust preferences of users. We then model the vehicular AI agent migration process as a partially observable markov decision process and develop a Confidence-regulated Generative Diffusion Model (CGDM) to efficiently generate AI agent migration decisions. Numerical results demonstrate that the CGDM algorithm significantly outperforms baseline methods in reducing system latency and enhancing robustness against cyber attacks. Copyright © 2025, The Authors. All rights reserved.

关键词： Markov processes

A novel singer identification method using GMM-UBM 6th

学校读者我要写书评

暂无评论

A novel singer identification method using GMM-UBM

6th Conference on Sound and Music technology, CSMT 2018

作者： Zhang, Xulong Jiang, Yiliang Deng, Jin Li, Juanjuan Tian, Mi Li, Wei School of Computer Science Fudan University Shanghai201203 China Centre for Digital Music Queen Mary University of London London United Kingdom Shanghai Key Laboratory of Intelligent Information Processing Fudan University Shanghai201203 China

ISBN: (纸本)9789811387067

This paper presents a novel method for singer identification from polyphonic music audio signals. It is based on the universal background model (UBM), which is a singer-independent Gaussian mixture model (GMM) trained on many songs to model the singer characteristics. For our model, singing voice separation on a polyphonic signal is used to cope with the negative influences caused by background accompaniment. Then, we construct UBM for each singer trained with the Mel-frequency Cepstral Coefficients (MFCCs) feature, using the maximum a posterior (MAP) estimation. Singer identification is realized by matching test samples to the obtained UBMs for individual singers. Another major contribution of our work is to present two new large singer identification databases with over 100 singers. The proposed system is evaluated on two public datasets and two new ones. Results indicate that UBM can build more accurate statistical models of the singer’s voice than conventional methods. The evaluation carried out on the public dataset shows that our method achieves 16% improvement in accuracy compared with the state-of-the-art singer identification system. © Springer Nature Singapore Pte Ltd. 2019.

关键词： Gaussian distribution

Locally repairable codes with strict availability from linear functions

学校读者我要写书评

暂无评论

science China(information sciences) 2018年第10期61卷 269-271页

作者： Yu ZHANG Haibin KAN Shanghai Key Laboratory of Intelligent Information Processing School of Computer ScienceFudan University Fudan-Zhongan Joint Laboratory of Blockchain and Information Security Shanghai Institute of Intelligent Electronics & Systems

Dear editor,In distributed storage systems, data is divided into small pieces and stored across a number of nodes. Since node failures are inevitable, redundancy is necessary. During the long run, the redundancy needs to be replenished. Regenerating codes were proposed to decrease repair bandwidth of distributed storage systems by accessing more nodes and downloading less data from each node [1, 2]. Locally repairable codes [3] improve the repairability of distributed storage system by

关键词： Locally repairable codes with strict availability from linear functions

Ordinal distribution regression for gait-based age estimation

学校读者我要写书评

暂无评论

arXiv 2019年

作者： Zhu, Haiping Zhang, Yuheng Li, Guohao Zhang, Junping Shan, Hongming Shanghai Key Lab of Intelligent Information Processing School of Computer Science Fudan University Shanghai200433 China

computer vision researchers prefer to estimate the age from face images due to informative facial features. Estimating the age from face images becomes challenging when people are far away from camcorders or occluded. As the unique biometric feature that can be perceived efficiently at a distance, gait can be an alternative way to predict the age in case that face images are not available. However, existing gait-based classification or regression methods ignore the ordinal relationship of different ages, which is an important clue to the age estimation. In this paper, we propose an ordinal distribution regression with a global and local convolutional neural network for gait-based age estimation. Specifically, we decompose the gait-based age regression into a series of binary classifications to incorporate the ordinal information of the age. Then an ordinal distribution loss is proposed to take inner relationship among these classifications into account by penalizing the distribution discrepancy between the estimated and the ground-truth. In addition, our neural network consists of a global and three local sub-networks, which is capable of learning the global structure and more local details from head, body and feet of gait, respectively. By comparing with the state-of-the-art methods of gait-based age estimation, this paper highlights, experimentally, that the proposed approach has a better predictive performance on the OULP-Age dataset. Copyright © 2019, The Authors. All rights reserved.

关键词： Regression analysis

Optimization of Missile Path Planning Based on APMO-HV Algorithm

学校读者我要写书评

暂无评论

Optimization of Missile Path Planning Based on APMO-HV Algor...

2019 IEEE International Conference on Unmanned Systems, ICUS 2019

作者： Zhang, Hu Wang, Shuai Liu, Tonglin Zhou, Aimin Zhang, Yi Beijing Electro-mechanical Engineering Institute Science and Technology on Complex System Control and Intelligent Agent Cooperation Laboratory Beijing China Changzhou University School of Mechanical Engineering Changzhou China East China Normal University Shanghai Key Laboratory of Multidimensional Information Processing School of Computer Science and Technology Shanghai China

ISBN: (纸本)9781728137926

In this paper, with considerations of low efficiency of missile path planning (MPP) by traditional aggregation technology, it uses affinity propagation based multi-objective evolutionary algorithm with hypervolume environment selection (APMO-HV) to solve the problem of MPP after establishing the MPP model. The experimental part compares and analyzes APMO-HV with six state-of-the-art algorithms, and applies it to address the MPP problem. The experimental results show that compared with the other six algorithms, APMO-HV has achieved the best solution performance in both the GLT test suite and MPP problem. This not only validates the effect of the proposed algorithm, but also enriches and improves the research results of MPP. © 2019 IEEE.

关键词： Evolutionary algorithms

DPNet: Dynamic Pooling Network for Accurate and Efficient Size-Aware Tiny Object Detection

学校读者我要写书评

暂无评论

IEEE Internet of Things Journal 2025年

作者： Gong, Luqi Chen, Haotian Chen, Yikun Yao, Tianliang Li, Chao Zhao, Shuai Han, Guangjie Beijing University of Posts and Telecommunications School of Computer Science Beijing China Zhejiang Lab Research Center for Space Computing System Hangzhou China Southwest Jiaotong University SWJTU-LEEDS Joint School Chengdu China LTD Guangdong Zhiyun City construction Technology Co Zhuhai China Tongji University College of Electronic and Information Engineering Department of Control Science and Engineering Shanghai China Hohai University Key Laboratory of Maritime Intelligent Network Information Technology Ministry of Education China

In unmanned aerial systems, especially in complex environments, accurately detecting tiny objects is crucial. Resizing images is a common strategy to improve detection accuracy, particularly for small objects. However, simply enlarging images significantly increases computational costs and the number of negative samples, severely degrading detection performance and limiting its applicability. This paper proposes a Dynamic Pooling Network (DPNet) for tiny object detection to mitigate these issues. DPNet employs a flexible down-sampling strategy by introducing a factor (df) to relax the fixed down-sampling process of the feature map to an adjustable one. Furthermore, we design a lightweight predictor to predict df for each input image, which will be used to decrease the resolution of feature map in backbone. Thus, we achieve input-aware down-sampling. We design an Adaptive Normalization Module (ANM) to make a unified detector well compatible with different dfs. At the same time, we also design a guidance loss to supervise the predictor’s training. DPNet realizes the dynamic allocation of computing resources to trade off detection accuracy and efficiency through this. Experiments on the TinyCOCO and TinyPerson datasets show that our DPNet can save over 35% and 25% GFLOPs, respectively, while maintaining comparable detection *** code will be made publicly available. © 2014 IEEE.

关键词： Object detection