检索结果-内蒙古大学图书馆

arXiv 2024年

作者： Wang, Junda Hu, Minghui Li, Ning Al-Ali, Abdulaziz Suganthan, Ponnuthurai Nagaratnam The Key Laboratory of System Control and Information Processing Ministry of Education of China China The Department of Automation Shanghai Jiao Tong University Shanghai200240 China The Shanghai Engineering Research Center of Intelligent Control and Management Shanghai200240 China The School of Electrical and Electronic Nanyang Technological University Singapore The KINDI Computing Research Center College of Engineering Qatar University Qatar

Online learning of deep neural networks suffers from challenges such as hysteretic non-incremental updating, increasing memory usage, past retrospective retraining, and catastrophic forgetting. To alleviate these drawbacks and achieve progressive immediate decision-making, we propose a novel Incremental Online Learning (IOL) process of Randomized Neural Networks (Randomized NN), a framework facilitating continuous improvements to Randomized NN performance in restrictive online scenarios. Within the framework, we further introduce IOL with ridge regularization (-R) and IOL with forward regularization (-F). -R generates stepwise incremental updates without retrospective retraining and avoids catastrophic forgetting. Moreover, we substituted -R with -F as it enhanced precognition learning ability using semi-supervision and realized better online regrets to offline global experts compared to -R during IOL. The algorithms of IOL for Randomized NN with -R/-F on non-stationary batch stream were derived respectively, featuring recursive weight updates and variable learning rates. Additionally, we conducted a detailed analysis and theoretically derived relative cumulative regret bounds of the Randomized NN learners with -R/-F in IOL under adversarial assumptions using a novel methodology and presented several corollaries, from which we observed the superiority on online learning acceleration and regret bounds of employing -F in IOL. Finally, our proposed methods were rigorously examined across regression and classification tasks on diverse datasets, which distinctly validated the efficacy of IOL frameworks of Randomized NN and the advantages of forward regularization. Copyright © 2024, The Authors. All rights reserved.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Heterogeneous Graph Convolutional Network for Visual Reinforcement Learning of Action Detection

Heterogeneous Graph Convolutional Network for Visual Reinfor...

引用

Automation, control and Robotics Engineering (CACRE), International Conference on

作者： Liangliang Wang Chengxi Huang Xinwei Chen School of Computer Science and Artificial Intelligence Wuhan University of Technology Wuhan China Fujian(Quanzhou)-HIT Research Institute of Engineering and Technology Quanzhou China Fujian Provincial Key Laboratory of Information Processing and Intelligent Control Minjiang University Fuzhou China

Existing action detection approaches do not take spatio-temporal structural relationships of action clips into account, which leads to a low applicability in real-world scenarios and can benefit detecting if exploited. To this end, this paper proposes to formulate the action detection problem as a reinforcement learning process which is rewarded by observing both the clip sampling and classification results via adjusting the detection schemes. In particular, our framework consists of a heterogeneous graph convolutional network to represent the spatio-temporal features capturing the inherent relation, a policy network which determines the probabilities of a predefined action sampling spaces, and a classification network for action clip recognition. We accomplish the network joint learning by considering the temporal intersection over union and Euclidean distance between detected clips and ground-truth. Experiments on ActivityNet v1.3 and THUMOS14 demonstrate our method.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Exploiting Distilled Learning for Deep Siamese Tracking

Exploiting Distilled Learning for Deep Siamese Tracking

引用

International Conference on Pattern Recognition

作者： Chengxin Liu Zhiguo Cao Wei Li Yang Xiao Shuaiyuan Du Angfan Zhu Key Laboratory of Image Processing and Intelligent Control Ministry of Education School of Artificial Intelligence and Automation Huazhong University of Science and Technology Wuhan China Queen Mary University of London

Existing deep siamese trackers are typically built on off-the-shelf CNN models for feature learning, with the demand for huge power consumption and memory storage. This limits current deep siamese trackers to be carried on resource-constrained devices like mobile phones, given factor that such a deployment normally requires cost-effective considerations. In this work, we address this issue by presenting a novel Distilled Learning Framework(DLF) for siamese tracking, which aims at learning tracking model with efficiency and high accuracy. Specifically, we propose two simple yet effective knowledge distillation strategies, denote as point-wise distillation and pairwise distillation, which are designed for transferring knowledge from a more discriminative teacher tracker into a compact student tracker. In this way, cost-effective and high performance tracking could be achieved. Extensive experiments on several tracking benchmarks demonstrate the effectiveness of our proposed method.

关键词： Power demand Pipelines Memory management Benchmark testing Mobile handsets Pattern recognition

来源：评论

学校读者我要写书评

暂无评论

Learning to Learn Transferable Generative Attack for Person Re-Identification

arXiv

引用

arXiv 2024年

作者： Bian, Yuan Liu, Min Wang, Xueping Ma, Yunfeng Wang, Yaonan The College of Electrical and Information Engineering Hunan University National Engineering Research Center of Robot Visual Perception and Control Technology Hunan Changsha China The College of Information Science and Engineering Hunan Normal University Hunan Provincial Key Laboratory of Intelligent Computing and Language Information Processing Hunan Changsha China

Deep learning-based person re-identification (re-id) models are widely employed in surveillance systems and inevitably inherit the vulnerability of deep networks to adversarial attacks. Existing attacks merely consider cross-dataset and cross-model transferability, ignoring the cross-test capability to perturb models trained in different domains. To powerfully examine the robustness of real-world re-id models, the Meta Transferable Generative Attack (MTGA) method is proposed, which adopts meta-learning optimization to promote the generative attacker producing highly transferable adversarial examples by learning comprehensively simulated transfer-based cross-model&dataset&test black-box meta attack tasks. Specifically, cross-model&dataset black-box attack tasks are first mimicked by selecting different re-id models and datasets for meta-train and meta-test attack processes. As different models may focus on different feature regions, the Perturbation Random Erasing module is further devised to prevent the attacker from learning to only corrupt model-specific features. To boost the attacker learning to possess cross-test transferability, the Normalization Mix strategy is introduced to imitate diverse feature embedding spaces by mixing multi-domain statistics of target models. Extensive experiments show the superiority of MTGA, especially in cross-model&dataset and cross-model&dataset&test attacks, our MTGA outperforms the SOTA methods by 21.5% and 11.3% on mean mAP drop rate, respectively. The code of MTGA will be released after the paper is accepted. Copyright © 2024, The Authors. All rights reserved.

关键词： Generative adversarial networks

来源：评论

学校读者我要写书评

暂无评论

A Performance-Based Model Recovery Anti-Windup Design for Linear Systems Subject to Actuator Saturation

A Performance-Based Model Recovery Anti-Windup Design for Li...

引用

American control Conference (ACC)

作者： Wenxin Lai Yuanlong Li Zongli Lin Department of Automation Shanghai Jiao Tong University Shanghai China Key Laboratory of System Control and Information Processing Ministry of Education of China Shanghai China Shanghai Engineering Research Center of Intelligent Control and Management Shanghai China Charles L. Brown Department of Electrical and Computer Engineering University of Virginia Char-lottesville VA U.S.A.

ISBN: (数字)9798350382655

ISBN: (纸本)9798350382662

In this paper, we investigate the problem of reference tracking for a class of linear systems subject to actuator saturation and propose a performance-based model recovery anti-windup strategy. We adopt the classic model recovery anti-windup framework and regard the states or one of the outputs of the anti-windup compensator as the tracking error, by which the difference between the unconstrained system and the saturated system is quantified. Then, instead of employing the commonly used $\mathcal{L}_{2}$ gain, we present the prescribed performance functions (PPFs) to characterize the real-time tracking error such that the system performance can be captured more specifically. In particular, to avoid singular issues arising from the occurrence of saturation, we modify the existing PPFs with an auxiliary system when saturation occurs. Based on these modified performance functions, we follow a modified prescribed performance control approach and design the remaining output of the anti-windup compensator. Such a design procedure is constructive, making it more promising for extension to nonlinear systems. Theoretical results establish the boundedness of all signals in the closed-loop system. Simulation results verify the effectiveness of our design strategy.

关键词： Linear systems Actuators Simulation System performance Stability analysis Real-time systems Trajectory

来源：评论

学校读者我要写书评

暂无评论

AoI-Reliability Analysis with Block Length over Erasure Channels Using Rateless Codes

AoI-Reliability Analysis with Block Length over Erasure Chan...

引用

International Conference on Communication Technology (ICCT)

作者： Haobo Huang Yusun Fu Yue Qiao Junpeng Yin Weiwu Yan Ningbo Artificial Intelligence Institute Shanghai Jiao Tong University Ningbo China School of Electronic Information and Electrical Engineering Shanghai Jiao Tong University Shanghai China Key Laboratory of System Control and Information Processing Ministry of Education of China Shanghai China Shanghai Engineering Research Center of Intelligent Control and Management Shanghai Jiao Tong University Shanghai China

ISBN: (数字)9798350363760

ISBN: (纸本)9798350363777

As a metric to measure the information freshness, Age of Information (AoI) is widely used to evaluate low-latency high-reliability communication. Since the communication in Industrial Internet of Things (IIoT) often has the special requirements, the relationship among AoI, reliability and block length in time-critical scenarios with bounded latency and non-time-critical scenarios without bounded latency is explored respectively in this paper, based on erasure channels using rateless codes. We build a model using LT codes over erasure channels and consider two metrics: average AoI and bounded AoI. Theoretical analysis and simulation results show that AoI has a minimum value with different block lengths. Furthermore, we draw a conclusion that the minimum value of AoI under different reliability is monotonically decreasing functioned with reliability. Finally, the impact of overhead on reliability and AoI of LT codes in time-critical scenarios is studied.

关键词： Measurement Codes Simulation Reliability theory Information age Communications technology Time factors Low latency communication Industrial Internet of Things

来源：评论

学校读者我要写书评

暂无评论

Enhancing the McEliece Scheme Based on Concatenation of Polar Codes and Blocked QC-LDPC Codes

Enhancing the McEliece Scheme Based on Concatenation of Pola...

引用

IEEE Conference on Communications and Network Security (CNS)

作者： Xin Lin Yusun Fu Zihao Wang Junpeng Yin Ningbo Artificial Intelligence Institute Shanghai Jiao Tong University Ningbo China School of Electronic Information and Electrical Engineering Shanghai Jiao Tong University Shanghai China Key Laboratory of System Control and Information Processing Ministry of Education of China Shanghai China Shanghai Engineering Research Center of Intelligent Control and Management Shanghai Jiao Tong University Shanghai China

ISBN: (数字)9798350375961

ISBN: (纸本)9798350375978

This paper proposes an enhanced McEliece cryptosystem, leveraging a concatenation scheme of Polar codes and blocked QC-LDPC codes. During the key generation phase, the generator matrices for both Polar and blocked QC-LDPC codes are employed as private keys. These matrices are subsequently multiplied by reversible and random permutation matrices respectively. The products of these multiplications are then combined to form the public key, effectively concealing the structural properties of the generator matrices. In the encryption phase, the plaintext is encrypted sequentially through the Polar codes and the blocked QC-LDPC codes. This process introduces two layers of random error vectors, culminating in the generation of the encrypted ciphertext. The proposed scheme reduces the public key length by 54% and doubles the security level compared to the original McEliece scheme with similar parameters. It also significantly reduces the total key length compared to improved schemes based on Polar codes and QC-LDPC/MDPC codes at an 80-bit security level, and shortens the private key length compared to schemes based on Polar-LDPC concatenated codes. Notably, the scheme is secure against known structural and decoding attacks while increases resistance to information set decoding (ISD) attacks. Through the randomization and hashing of the plaintext, the proposed scheme can achieve IND-CCA2 security.

关键词： Resistance Codes Public key Network security Generators Vectors Decoding Encryption Concatenated codes Polar codes

来源：评论

学校读者我要写书评

暂无评论

A Stronger Baseline for Ego-Centric Action Detection

arXiv

引用

arXiv 2021年

作者： Qing, Zhiwu Huang, Ziyuan Wang, Xiang Feng, Yutong Zhang, Shiwei Jiang, Jianwen Tang, Mingqian Gao, Changxin Ang, Marcelo H. Sang, Nong Key Laboratory of Image Processing and Intelligent Control School of Artificial Intelligence and Automation Huazhong University of Science and Technology ARC National University of Singapore Tsinghua University Alibaba Group

This technical report analyzes an egocentric video action detection method we used in the 2021 EPIC-KITCHENS-100 competition hosted in CVPR2021 Workshop. The goal of our task is to locate the start time and the end time of the action in the long untrimmed video, and predict action category. We adopt sliding window strategy to generate proposals, which can better adapt to short-duration actions. In addition, we show that classification and proposals are conflict in the same network. The separation of the two tasks boost the detection performance with high efficiency. By simply employing these strategy, we achieved 16.10% performance on the test set of EPIC-KITCHENS-100 Action Detection challenge using a single model, surpassing the baseline method by 11.7% in terms of average mAP. Copyright © 2021, The Authors. All rights reserved.

关键词： Machine learning

来源：评论

学校读者我要写书评

暂无评论

Boltzmann Robust Soliton Distribution for Rateless Codes

Boltzmann Robust Soliton Distribution for Rateless Codes

引用

International Conference on Communication Technology (ICCT)

作者： Jinhui Tang Yusun Fu Yue Qiao Junpeng Yin Haobo Huang School of Electronic Information and Electrical Engineering Shanghai Jiao Tong University Shanghai China Ningbo Artificial Intelligence Institute Shanghai Jiao Tong University Ningbo China Key Laboratory of System Control and Information Processing Ministry of Education of China Shanghai China Shanghai Engineering Research Center of Intelligent Control and Management Shanghai Jiao Tong University Shanghai China

ISBN: (数字)9798350363760

ISBN: (纸本)9798350363777

The decoding success rate may be worse when classical degree distributions are used in short-packet transmission of rateless codes, especially in industrial communication scenarios. A novel Boltzmann degree distribution is proposed for Luby Transform (LT) codes. The Boltzmann degree distribution has a high decoding success rate for short-packet transmission but a lower decoding success rate in long-packet transmission. To balance the performance of rateless codes for short and long packet transmission, the Boltzmann degree distribution and the robust soliton distribution (RSD) are combined with a new joint degree distribution, called Boltzmann Robust Soliton Distribution (BRSD). Simulation results show that compared with RSD and Poisson robust soliton distribution (PRSD), the proposed joint distribution can achieve a higher decoding success rate and reduce the average degree, especially in short-packet transmission of industrial communication.

关键词： Codes Simulation Industrial communication Symbols Solitons Transforms Robustness Decoding Complexity theory Physics

来源：评论

学校读者我要写书评

暂无评论

Resource Allocation for Coupled Slices in Edge-Assisted Industrial IoT Systems

Resource Allocation for Coupled Slices in Edge-Assisted Indu...

引用

IEEE International Conference on Communications in China (ICCC)

作者： Xiaojing Wen Cailian Chen Cheng Ren Ling Lyu Xinping Guan Department of Automation Shanghai Jiao Tong University and Key Laboratory of System Control and Information Processing Ministry of Education of China and Shanghai Engineering Research Center of Intelligent Control and Management Shanghai P. R. China School of Information Science and Technology Dalian Maritime University Dalian China

Multiple types of sensors are utilized for remote monitoring of single industrial process to compensate for the limited accuracy of a single type of sensor. Network slicing technology is considered promising for collecting data from heterogeneous sensors and meeting diverse Quality of Service (QoS) requirements. However, existing research on network slicing optimization mainly focuses on inter-slice resource constraints based on slice heterogeneity, neglecting slice coupling feature. In this regard, this paper proposes a novel network slicing framework for edge-assisted industrial IoT systems. The framework includes a slice coupling model and network resource allocation (transmission and computing) to address the problem of improving estimation performance while ensuring system convergence. The slice coupling model is primarily composed of the estimation error covariance of two slices, calculated using the Age of Task (AoT) as a bridge, which reflects the accuracy and freshness of the estimation. To reduce the complexity of the direct solution, the optimization problem is scaled down and decoupled. The iterative Particle Swarm Optimization (PSO) algorithm is proposed to determine the allocation rates of inter-slice transmission and computing resources. Simulation results demonstrate that the proposed algorithm achieves a flexible balance under heterogeneous estimation weights and exhibits near-optimal performance.

关键词：

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：