检索结果-内蒙古大学图书馆

arXiv 2022年

作者： Zhang, Zekang Gao, Guangyu Fang, Zhiyuan Jiao, Jianbo Wei, Yunchao School of Computer Science Beijing Institute of Technology China School of Computer Science University of Birmingham United Kingdom WEI Lab Institute of Information Science Beijing Jiaotong University China Beijing Key Laboratory of Advanced Information Science and Network China

Incremental or continual learning has been extensively studied for image classification tasks to alleviate catastrophic forgetting, a phenomenon that earlier learned knowledge is forgotten when learning new concepts. For class incremental semantic segmentation, such a phenomenon often becomes much worse due to the background shift, i.e., some concepts learned at previous stages are assigned to the background class at the current training stage, therefore, significantly reducing the performance of these old concepts. To address this issue, we propose a simple yet effective method in this paper, named Mining unseen Classes via Regional Objectness for Segmentation (MicroSeg). Our MicroSeg is based on the assumption that background regions with strong objectness possibly belong to those concepts in the historical or future stages. Therefore, to avoid forgetting old knowledge at the current training stage, our MicroSeg first splits the given image into hundreds of segment proposals with a proposal generator. Those segment proposals with strong objectness from the background are then clustered and assigned newly-defined labels during the optimization. In this way, the distribution characterizes of old concepts in the feature space could be better perceived, relieving the catastrophic forgetting caused by the background shift accordingly. Extensive experiments on Pascal VOC and ADE20K datasets show competitive results with state-of-the-art, well validating the effectiveness of the proposed MicroSeg. Code is available at https://***/zkzhang98/MicroSeg. © 2022, CC BY.

关键词： Semantics

来源：评论

学校读者我要写书评

暂无评论

Dynamic Power Distribution Controlling for Directional Chargers

Dynamic Power Distribution Controlling for Directional Charg...

引用

IEEE Annual Joint Conference: INFOCOM, IEEE computer and Communications Societies

作者： Yuzhuo Ma Dié Wu Jing Gao Wen Sun Jilin Yang Tang Liu College of Computer Science Sichuan Normal University Chengdu China Visual Computing and Virtual Reality Key Lab Sichuan Normal University Chengdu China School of Information and Software Engineering University of Electronic Science and Technology of China Chengdu China School of Cyberspace Security Northwestern Polytechnical University Xi’an China

ISBN: (数字)9798350383508

ISBN: (纸本)9798350383515

Recently, deploying static chargers to construct timely and robust Wireless Rechargeable Sensor networks (WRSNs) has become an important research issue for solving the limited energy problem of wireless sensor networks. However, the established fixed power distribution lacks flexibility in response to dynamic charging requests from sensors and may render some sensors to be continuously impacted by destructive wave interference. This results in a gap between energy supply and practical demand, making the charging process less efficient. In this paper, we focus on the real-time sensor charging requests and formulate a dynamic power disTributIon controlling for Directional chargErs (TIDE) problem to maximize the overall charging utility. To solve the problem, we first build a charging model for directional chargers while considering wave interference and extract the candidate charging orientations from the continuous search space. Then we propose the neighbor set division method to narrow the scope of calculation. Finally, we design a dynamic power distribution controlling algorithm to update the neighbor sets timely and select optimal orientations for chargers. Our experimental results demonstrate the effectiveness and efficiency of the proposed scheme, it outperforms the comparison algorithms by 142.62% on average.

关键词： Wireless communication Wireless sensor networks Heuristic algorithms Computational modeling Power distribution Interference Search problems

来源：评论

学校读者我要写书评

暂无评论

A Secure key-Aggregate keyword Retrieval Scheme Over Encrypted Data in Cloud Computing

引用

IEEE Access 2024年 1-1页

作者： Lou, Chunwei Cao, Mingsheng Luo, Yaohua Xu, Hua Gao, Yuan Wang, Weiwei Wang, Dong University of Electronic Science and Technology of China Chengdu 611731 China Network and Data Security Key Laboratory of Sichuan Province University of Electronic Science and Technology of China Chengdu 611731 China School of Information Science and Technology Chengdu University of Technology Chengdu 610059 China School of Physics and Electronic Engineering Yancheng Teachers University Yancheng 224007 China China Academy of Railway Sciences Beijing 100081 China School of Computer Science and Engineering and the Center for Cyber Security University of Electronic Science and Technology of China Chengdu 611731 China

key-aggregate keyword retrieval primitive enables a cloud server on behalf of delegated users to securely perform a keyword search over the data encrypted with various public keys. However, existing key-aggregate searchable encryption schemes are insecure against keyword guessing attacks, which result in the privacy leakage of keyword ciphertext and trapdoor. In this paper, we for the first time formulate a secure and efficient key-aggregate searchable encryption for cloud-assisted IoT applications, which not only enables a data owner to securely share the selected documents to multiple users, but also supports data users in delegating the capability of keyword search to a cloud server for searching the desired documents without leaking any privacy of keyword ciphertext and trapdoor. Then, the security of the proposed scheme is formally defined and proven to be secure against the indistinguishable selective-file chosen keyword attacks. The flexibility and practicability of the formulated scheme is also demonstrated by theoretical evaluations and experimental simulations. Author

关键词： Aggregates

来源：评论

学校读者我要写书评

暂无评论

Direct Participant Recruitment Strategy in Sparse Mobile Crowdsensing

引用

Jisuanji Xuebao/Chinese Journal of computers 2022年第7期45卷 1539-1556页

作者： Tu, Chun-Yu Yu, Zhi-Yong Han, Lei Zhu, Wei-Ping Huang, Fang-Wan Guo, Wen-Zhong Wang, Le-Ye College of Mathematics and Computer Science Fuzhou University Fuzhou350108 China Department of Fujian Key Laboratory of Network Computing and Intelligent Information Processing Fuzhou University Fuzhou350108 China School of Computer Science Northwestern Polytechnical University Xi'an710072 China Key Lab of High Confidence Software Technologies Peking University Beijing100871 China School of Computer Science Peking University Beijing100871 China

Sparse Mobile Crowdsensing (Sparse MCS) selects a small part of sub-areas for data collection and infers the data of other sub-areas from the collected data. Compared with Mobile Crowdsensing (MCS) that does not use data inference methods, Sparse MCS saves sensing costs while ensuring the quality of global data. However, the existing research works on Sparse MCS only focus on selecting a small part of sub-areas with higher value. It does not consider whether the recruited participants can collect the data of the required sub-areas, and also ignores the value of other data collected by the participants. In order to solve the limitations of traditional methods in sub-areas selection, this paper starts from the perspective of participants and concentrates on the contribution of the data collected by each participant to the entire collection task. All the data contributions collected by each participant will become the basis for decision-making for the participant's choice. And correspondingly, a new idea to deal with the problem of participant selection under Sparse MCS is proposed. In view of the fact that each person's daily movement trajectory is basically stable, and the data collected by different people on their respective trajectories have different values, this paper uses this regularity and difference to study how to directly recruit participants who can collect high-value data. Furthermore, the participant selection problem considered in this paper is not limited to the data collection in the next cycle, but directly recruits some participants to continue the data collection task in the next multiple cycles. The participant selection problem that spans multiple cycles can be modeled as a dynamic decision-making problem. Since heuristic strategies may fall into a local optimal solution, this paper uses reinforcement learning to solve the participant selection problem: We use the participant selection system as an agent of reinforcement learning, and design the

关键词： Compressed sensing

来源：评论

学校读者我要写书评

暂无评论

Location Privacy-Preserving Method Based on Degree of Semantic Distribution Similarity 6th

Location Privacy-Preserving Method Based on Degree of Semant...

引用

6th International Conference of Pioneering computer Scientists, Engineers and Educators, ICPCSEE 2020

作者： Liu, Rui Zuo, Kaizhong Wang, Yonglu Zhao, Jun College of Computer and Information Anhui Normal University WuhuAnhui241002 China Anhui Provincial Key Laboratory of Network and Information Security Anhui Normal University WuhuAnhui241002 China

ISBN: (纸本)9789811579806

While enjoying the convenience brought by location-based services, mobile users also face the risk of leakage of location privacy. Therefore, it is necessary to protect location privacy. Most existing privacy-preserving methods are based on K-anonymous and L-segment diversity to construct an anonymous set, but lack consideration of the distribution of semantic location on the road segments. Thus, the number of various semantic location types in the anonymous set varies greatly, which leads to semantic inference attack and privacy disclosure. To solve this problem, a privacy-preserving method is proposed based on degree of semantic distribution similarity on the road segment, ensuring the privacy of the anonymous set. Finally, the feasibility and effectiveness of the method are proved by extensive experiments evaluations based on dataset of real road network. © 2020, Springer Nature Singapore Pte Ltd.

关键词： Location based services

来源：评论

学校读者我要写书评

暂无评论

A Drug Box Recognition System Based on Deep Learning and Cloud-Edge Collaboration for Pharmacy Automation

A Drug Box Recognition System Based on Deep Learning and Clo...

引用

International Conference on Parallel and Distributed Systems (ICPADS)

作者： Honglei Zhu Anming Dong Jiguo Yu Ministry of Education Shandong Computer Science Center (National Supercomputer Center in Jinan) Key Laboratory of Computing Power Network and Information Security Qilu University of Technology (Shandong Academy of Sciences) Jinan China School of Computer Science and Technology Qilu University of Technology (Shandong Academy of Sciences) Jinan China Big Data Institute Qilu University of Technology (Shandong Academy of Sciences) Jinan China Shandong Provincial Key Laboratory of Computer Networks Shandong Fundamental Research Center for Computer Science Jinan China

Drug box recognition is an integral part of the pharmacy automation system (PAS), which checks for discrepancies between the drugs provided by the system and the doctor’s prescription with the help of modern image recognition techniques. Although deep learning has facilitated the development of pharmacy automation systems, practical applications still face challenges. First, pharmacies update drugs frequently, and many pharmacies across the country are trained independently, which requires consuming massive computational resources. Secondly, the equipment performance of pharmacies is poor, and it’s hard to guarantee the real-time and accuracy of recognition. Therefore, we propose a cloud-side collaborative drug box recognition system. When new drugs are added, the new model is trained in the cloud and uniformly distributed to each edge through this architecture. In terms of real-time recognition, an improved lightweight YOLOv5 model is added to the edge part, and a text recognition module is deployed in the cloud to validate the recognition results at the edge. This cloud-edge collaboration architecture not only ensures the accuracy of recognition, but also reduces the burden on the compute edge, ensures the real-time *** results show that the proposed cloud-edge architecture reduces the recognition latency by 37.18% and achieves a precision of 97.47%. The improved YOLOv5 model reduces GFLOPs by 45% while achieving a 1.6% precision improvement.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Efficient Adaptive label Refinement for label Noise Learning

arXiv

引用

arXiv 2025年

作者： Zhang, Wenzhen Cheng, Debo Lu, Guangquan Zhou, Bo Li, Jiaye Zhang, Shichao School of Computer Science and Engineering Guangxi Normal University Guangxi Guilin541004 China Guangxi Key Lab of Multi-Source Information Mining & Security Guangxi Normal University Guangxi Guilin541004 China Key Lab of Education Blockchain and Intelligent Technology Ministry of Education Guangxi Normal University Guangxi Guilin541004 China UniSA STEM University of South Australia AdelaideSA5095 Australia Guangxi Collaborative Innovation Center of Modern Sericulture and Silk Hechi University Guangxi Hechi546300 China The State Key Laboratory of Blockchain and Data Security Zhejiang University Zhejiang Hangzhou310027 China

Deep neural networks are highly susceptible to overfitting noisy labels, which leads to degraded performance. Existing methods address this issue by employing manually defined criteria, aiming to achieve optimal partitioning in each iteration to avoid fitting noisy labels while thoroughly learning clean samples. However, this often results in overly complex and difficult-to-train models. To address this issue, we decouple the tasks of avoiding fitting incorrect labels and thoroughly learning clean samples and propose a simple yet highly applicable method called Adaptive label Refinement (ALR). First, inspired by label refurbishment techniques, we update the original hard labels to soft labels using the model’s predictions to reduce the risk of fitting incorrect labels. Then, by introducing the entropy loss, we gradually ‘harden’ the high-confidence soft labels, guiding the model to better learn from clean samples. This approach is simple and efficient, requiring no prior knowledge of noise or auxiliary datasets, making it more accessible compared to Copyright © 2025, The Authors. All rights reserved.

关键词： Self-supervised learning

来源：评论

学校读者我要写书评

暂无评论

Robustness and Privacy for Green Learning under Noisy labels

Robustness and Privacy for Green Learning under Noisy Labels

引用

IEEE International Conference on Trust, security and Privacy in Computing and Communications (TrustCom)

作者： De Li Tiange Xia Qiyu Li Xianxian Li Jinyan Wang Key Lab of Education Blockchain and Intelligent Technology Ministry of Education Guangxi Normal University Guilin China Guangxi Key Lab of Multi-Source Information Mining & Security Guangxi Normal University Guilin China School of Computer Science and Engineering Guangxi Normal University Guilin China Faculty of Education Guangxi Normal University Guilin China

ISBN: (数字)9798350381993

ISBN: (纸本)9798350382006

As a new paradigm of machine learning, green learning has achieved performance comparable to deep learning in vision tasks, knowledge graph learning, and modeling graph structures. Compared with deep learning, green learning has the advantages of a low carbon footprint, lightweight model and logical transparency. In this paper, to enhance the robustness of green learning, we study the performance of the green model when the training dataset labels are noisy. Through theoretical analysis and experimental verification, we found that noisy labels will not only reduce the performance of green learning, but also amplify the risk of privacy leaks of training dataset members. Therefore, we propose a robust green learning to approach the above two threats. Specifically, we design a multi-stage label-consistency sample selection method to filter out noisy labels in the training dataset by taking advantage of the characteristics of unsupervised representation learning in green learning. In order to further improve the stable classification performance of the model, we propose a feature-level class-balanced data augmentation method in the feature decision learning stage to solve the class imbalance problem caused by sample selection. Finally, a large number of experiments on multiple noisy datasets show that the robust green learning method proposed in this paper can not only enhance the generalization of the model under noisy training labels, but also alleviate the risk of member privacy information leakage.

关键词： Training Deep learning Representation learning Data privacy Privacy Robustness Data models

来源：评论

学校读者我要写书评

暂无评论

A Trajectory Tracking System for Zebrafish Based on Embedded Edge Artificial Intelligence

A Trajectory Tracking System for Zebrafish Based on Embedded...

引用

International Conference on Parallel and Distributed Systems (ICPADS)

作者： Chuanhao Zang Anming Dong Jiguo Yu Key Laboratory of Computing Power Network and Information Security Ministry of Education Shandong Computer Science Center (National Supercomputer Center in Jinan) Qilu University of Technology (Shandong Academy of Sciences) Jinan China School of Computer Science and Technology Qilu University of Technology (Shandong Academy of Sciences) Jinan China Big Data Institute Qilu University of Technology (Shandong Academy of Sciences) Jinan China Shandong Provincial Key Laboratory of Computer Networks Shandong Fundamental Research Center for Computer Science Jinan China

Trajectory tracking of zebrafish is an important requirement in studying neurological disorders and developing new psychoactive drug. However, many challenges emerge for stable tracking, since zebrafish are similar in appearance, occlusion, agile, non-linear in moving and easy to swarm, all of which will lead to mistrack for multiple fish. And there is no precedent for tracking zebrafish through embedded edge artificial intelligence device. To overcome these difficulties, we present a tracking system for zebrafish based on RK3588-S. First, We construct an embedded edge AI hardware system consisting of two cameras driven by the RK3588-S, one for the front view and the other for top view of the fish. Then, we develop a 2D tracking algorithm based on YOLOv5 and the Observation-Centric Simple online and real-time tracking (OC-SORT) algorithm, which are transplanted to the RK3588-S for tracking the top and front views of the fish at the edge device. Compared with the previous methods, our method has fewer ID exchanges and highly real-time. Moreover, we apply the MQTT mechanism to establish communication links between the edge and the cloud to reliably transmit data to the cloud. The correspondence between cloud server and embedded AI is 1: N. Finally, we design a multi-view data fusion association algorithm to fuse the data of the two views in the cloud, which are further utilized to build the 3D tracklets of the zebrafish.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Frozen-DETR: enhancing DETR with image understanding from frozen foundation models 24

Frozen-DETR: enhancing DETR with image understanding from fr...

引用

Proceedings of the 38th International Conference on Neural information Processing Systems

作者： Shenghao Fu Junkai Yan Qize Yang Xihan Wei Xiaohua Xie Wei-Shi Zheng School of Computer Science and Engineering Sun Yat-sen University China and Tongyi Lab Alibaba Group and Key Laboratory of Machine Intelligence and Advanced Computing Ministry of Education China Tongyi Lab Alibaba Group School of Computer Science and Engineering Sun Yat-sen University China and Key Laboratory of Machine Intelligence and Advanced Computing Ministry of Education China and Guangdong Province Key Laboratory of Information Security Technology China School of Computer Science and Engineering Sun Yat-sen University China and Peng Cheng Laboratory Shenzhen China and Key Laboratory of Machine Intelligence and Advanced Computing Ministry of Education China and Pazhou Laboratory (Huangpu) Guangzhou Guangdong China

ISBN: (纸本)9798331314385

Recent vision foundation models can extract universal representations and show impressive abilities in various tasks. However, their application on object detection is largely overlooked, especially without fine-tuning them. In this work, we show that frozen foundation models can be a versatile feature enhancer, even though they are not pre-trained for object detection. Specifically, we explore directly transferring the high-level image understanding of foundation models to detectors in the following two ways. First, the class token in foundation models provides an in-depth understanding of the complex scene, which facilitates decoding object queries in the detector's decoder by providing a compact context. Additionally, the patch tokens in foundation models can enrich the features in the detector's encoder by providing semantic details. Utilizing frozen foundation models as plug-and-play modules rather than the commonly used backbone can significantly enhance the detector's performance while preventing the problems caused by the architecture discrepancy between the detector's backbone and the foundation model. With such a novel paradigm, we boost the SOTA query-based detector DINO from 49.0% AP to 51.9% AP (+2.9% AP) and further to 53.8% AP (+4.8% AP) by integrating one or two foundation models respectively, on the COCO validation set after training for 12 epochs with R50 as the detector's backbone.

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：