检索结果-内蒙古大学图书馆

IEEE Symposium on High-Performance Computer Architecture

作者： Chencheng Ye Yuanchao Xu Xipeng Shen Yan Sha Xiaofei Liao Hai Jin Yan Solihin National Engineering Research Center for Big Data Technology and System/Services Computing Technology and System Lab/Cluster and Grid Computing Lab School of Computer Science and Technology Huazhong University of Science and Technology Wuhan China North Carolina State University Raleigh North Carolina USA University of Central Florida Florida USA

Log creation, maintenance, and its persist ordering are known to be performance bottlenecks for durable transactions on persistent memory. Existing hardware persistent memory transactions overlook an important opportunity for improving performance: some persistent data is algorithmically redundant such that it can be recovered from other data, removing the need for logging such data. The paper presents an ISA extension that enables selective logging for hardware persistent memory transactions for the first time. The ISA extension features two novel components: fine-grain logging and lazy persistency. Fine-grain logging allows hardware to log updates on data in the granularity of words without lengthening the critical path of data accesses. Lazy persistency allows updated data to remain in the cache after the transaction commits. Together, the new hardware persistent memory transaction outperforms the state-of-the-art hardware counterpart by 1.8× on average.

关键词： Computer architecture Maintenance engineering Hardware Optimization IEEE transactions

来源：评论

学校读者我要写书评

暂无评论

Boosting Fine-Grained Visual Anomaly Detection with Coarse-Knowledge-Aware Adversarial Learning 39

Boosting Fine-Grained Visual Anomaly Detection with Coarse-K...

引用

39th Annual AAAI Conference on Artificial Intelligence, AAAI 2025

作者： Fang, Qingqing Su, Qinliang Lv, Wenxi Xu, Wenchao Yu, Jianxing School of Computer Science and Engineering Sun Yat-sen University Guangzhou China Guangdong Key Laboratory of Big Data Analysis and Processing Guangzhou China Department of Computing The Hong Kong Polytechnic University Hong Kong School of Artificial Intelligence Sun Yat-sen University Guangdong China Pazhou Lab Guangzhou 510330 China

ISBN: (纸本)157735897X

Many unsupervised visual anomaly detection methods train an auto-encoder to reconstruct normal samples and then leverage the reconstruction error map to detect and localize the anomalies. However, due to the powerful modeling and generalization ability of neural networks, some anomalies can also be well reconstructed, resulting in unsatisfactory detection and localization accuracy. In this paper, a small coarsely-labeled anomaly dataset is first collected. Then, a coarse-knowledge-aware adversarial learning method is developed to align the distribution of reconstructed features with that of normal features. The alignment can effectively suppress the auto-encoder’s reconstruction ability on anomalies and thus improve the detection accuracy. Considering that anomalies often only occupy very small areas in anomalous images, a patch-level adversarial learning strategy is further developed. Although no patch-level anomalous information is available, we rigorously prove that by simply viewing any patch features from anomalous images as anomalies, the proposed knowledge-aware method can also align the distribution of reconstructed patch features with the normal ones. Experimental results on four medical datasets and two industrial datasets demonstrate the effectiveness of our method in improving the detection and localization performance. Copyright © 2025, Association for the Advancement of Artificial Intelligence (***). 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

A Rational Delegating Computation Protocol Based on Smart Contract 14th

A Rational Delegating Computation Protocol Based on Smart Co...

引用

14th EAI International Conference on Mobile Multimedia Communications, Mobimedia 2021

作者： Ma, Juan Chen, Yuling Liu, Guoxu Zhu, Hongliang Peng, Changgen State Key Laboratory of Public Big Data College of Computer Science and Technology Guizhou University Guiyang China Blockchain Laboratory of Agricultural Vegetables Weifang University of Science and Technology Shouguang China Engineering Lab for Cloud Security and Information Security Center of BUPT Beijing China

ISBN: (纸本)9783030898137

The delegating computation has become an irreversible trend, together comes the pressing need for fairness and efficiency issues. To solve this problem, we leverage game theory to propose a smart contract-based solution. Firstly, according to the behavioral preferences of the participants, we design an incentive contract to describe the motivation of the participants. Secondly, to satisfy the fairness of the rational delegating computation, we propose a delegating computation protocol based on the smart contract. Specifically, rational participants are to gain the maximum utility and reach the Nash equilibrium in the protocol. Besides, we design a reputation mechanism with a reputation certificate, which measures the reputation from multiple dimensions. And the reputation is used to assure the client’s trust in the computing party to improve the efficiency of the protocol. Finally, the analysis results show that the proposed protocol solves the complex traditional verification problem. Meanwhile, we prove the fairness and correctness of the protocol. © 2021, ICST Institute for Computer sciences, Social Informatics and Telecommunications Engineering.

关键词： Smart contract

来源：评论

学校读者我要写书评

暂无评论

Stereovision-based Noncooperative Spacecraft Pose Measurement via Circle and Planar Points 33

Stereovision-based Noncooperative Spacecraft Pose Measuremen...

引用

第33届中国控制与决策会议

作者： Cuicui Jiang Yizhong Fang Guopeng Ding Xin Chen Qingyun Mao Qinglei Hu School of Automation Science and Electrical Engineering Beihang University Beijing Institute of Space Long March Vehicle Key Lab of Microsatellite Chinese Academy of Sciences Innovation Academy for Microsatellites of CAS Beijing Advanced Innovation Center for Big-Data Based Precision Medicine Beihang University

ISBN: (纸本)9781665431293

In this paper,a novel approach based on the feature circle and planar points is proposed for the relative pose measurement of the noncooperative ***,the approach uses information from the stereovision-based navigation system to provide multiple perspective projections of the circle and planar points on the noncooperative *** the circle center position is recovered and the normal direction is determined by duality ***,a point depth of recovery from the stereovision is used to define the direction from the circle center to the point,which is regarded as the initial attitude for the stereovision-based orthogonal iteration pose estimation to avoid the local minimal value of the iteration ***,by utilizing the initial attitude and the orthogonal iteration algorithm based on planar points,the pose ambiguity from the planar points is eliminated and the roll angle around the circle normal direction is ***,numerical simulations are conducted to validate the effectiveness of the proposed algorithm.

关键词： Noncooperative spacecraft Stereovision Planar points Orthogonal iteration

来源：评论

学校读者我要写书评

暂无评论

A Generative Adversarial Active Learning Method for Effective Outlier Detection

A Generative Adversarial Active Learning Method for Effectiv...

引用

International Conference on Tools for Artificial Intelligence (ICTAI)

作者： Mohamed Jaward Bah Ji Zhang Ting Yu Feng Xia Zhao Li Shuigeng Zhou Hongzhi Wang Big Data Intelligence Research Center Zhejiang Lab Hangzhou China University of Southern Queensland School of Sciences Toowoomba Australia Institute of Innovation Science and Sustainability Federation University Australia Ballarat Australia Zhejiang University China Fudan University School of Computer Science Shanghai China Harbin Institute of Technology Massive Data Computing Lab China

Outlier detection is an important data mining task, and developing effective methods to detect outliers is challenging in cases where there is insufficient labeled data. Manually labeling the data is labor-intensive and time-consuming. Because of a limited number of labeled samples, the classes are unbalanced, resulting in a class-imbalance problem. Existing methods fail to address these aforementioned issues holistically and fall short in generating quality outlier samples for effective outlier detection accuracy. In this paper, we propose a new solution that tackles these problems. We propose a. Generative Adversarial Active Learning method (DIR-GAAL), which generates Diverse, Informative, and Representative outlier samples through active learning, and employs the mini-max game between the generator and discriminator in a generative adversarial network. We conducted extensive experiments on several benchmark datasets to evaluate the performance of our method. When compared to other benchmark methods, our method consistently demon-strates better outlier detection accuracy without being negatively affected by the class-imbalance problem.

关键词： Learning systems Games Benchmark testing Generative adversarial networks Generators labeling Task analysis

来源：评论

学校读者我要写书评

暂无评论

Semi-supervised Multi-label Learning with Missing labels via Correlation Information

Semi-supervised Multi-Label Learning with Missing Labels via...

引用

International Joint Conference on Neural Networks (IJCNN)

作者： Zexian Xie Peipei Li Jinling Jiang Xindong Wu Key Laboratory of Knowledge Engineering with Big Data (the Ministry of Education of China) Hefei University of Technology School of Computer Science and Information Engineering Hefei University of Technology Hefei Anhui China Knowledge Engineering Research Center Zhejiang Lab Hangzhou Zhejiang China

In multi-label learning, each instance is associated with a set of labels simultaneously. Most existing studies assume that the set of labels for each instance is complete. However, it is generally difficult to obtain all the relevant labels of each instance, and only a partial or even empty set of relevant labels is available, which is called semi-supervised multi-label learning with missing labels. To tackle this problem, we propose a novel framework that considers label correlations and instance correlations to recover the missing labels and utilizes a large amount of unlabeled data simultaneously to improve the classification performance. Specifically, a new supplementary label matrix is firstly obtained by learning the label correlation. Secondly, considering each class label may be decided by some specific characteristics of its own, a label-specific data representation is hence learned for each class label. Thirdly, instance correlations are utilized not only to recover the missing labels, but also to propagate the supervision information from labeled instances to unlabeled ones. In addition, a united objective function is designed to facilitate the above processing and an accelerated proximal gradient method is adopted to solve the optimization problem. Finally, extensive experimental results conducted on several benchmark datasets demonstrate the effectiveness of the proposed method compared to competing ones.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Towards open-world text-guided face image generation and manipulation

arXiv

引用

arXiv 2021年

作者： Xia, Weihao Yang, Yujiu Xue, Jing-Hao Wu, Baoyuan Tsinghua Shenzhen International Graduate School Tsinghua University China Department of Statistical Science University College London United Kingdom School of Data Science Chinese University of Hongkong Shenzhen China and Secure Computing Lab of Big Data Shenzhen Research Institute of Big Data Shenzhen China

—The existing text-guided image synthesis methods can only produce limited quality results with at most 2562 resolution and the textual instructions are constrained in a small Corpus. In this work, we propose a unified framework for both face image generation and manipulation that produces diverse and high-quality images with an unprecedented resolution at 10242 from multimodal inputs. More importantly, our method supports open-world scenarios, including both image and text, without any re-training, fine-tuning, or post-processing. To be specific, we propose a brand new paradigm of text-guided image generation and manipulation based on the superior characteristics of a pretrained GAN model. Our proposed paradigm includes two novel strategies. The first strategy is to train a text encoder to obtain latent codes that align with the hierarchically semantic of the aforementioned pretrained GAN model. The second strategy is to directly optimize the latent codes in the latent space of the pretrained GAN model with guidance from a pretrained language model. The latent codes can be randomly sampled from a prior distribution or inverted from a given image, which provides inherent supports for both image generation and manipulation from multi-modal inputs, such as sketches or semantic labels, with textual guidance. To facilitate text-guided multi-modal synthesis, we propose the MULTI-MODAL CELEBA-HQ, a large-scale dataset consisting of real face images and corresponding semantic segmentation map, sketch, and textual descriptions. Extensive experiments on the introduced dataset demonstrate the superior performance of our proposed method. Copyright © 2021, 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

An Improved Honey Badger Algorithm for Electric Vehicle Charge Orderly Planning

Journal of Network Intelligence

引用

Journal of Network Intelligence 2022年第2期7卷 332-346页

作者： Chen, Ran-Fan Luo, Hao Huang, Kuan-Chun Nguyen, Trong-The Pan, Jeng-Shyang College of Computer Science and Mathematics Fujian University of Technology Fuzhou350118 China School of Aeronautics and Astronautics Zhejiang University HangZhou310000 China Department of Industrial and Systems Engineering Chung Yuan University Taoyuan320-33 Taiwan Multimedia Communications Lab VNUHCM-University of Information Technology Ho Chi Minh City700000 Viet Nam Vietnam National University Ho Chi Minh City700000 Viet Nam Fujian Provincial Key Laboratory of Big Data Mining and Applications Fujian University of Technology Fuzhou350118 China College of Computer Science and Engineering Shandong University of Science and Technology Qingdao266590 China

Multiple electric vehicles simultaneously connected to a distribution load network will significantly impact the stability of the power grid. This paper proposes an improved Honey-badger algorithm (IHBA) through elite reverse learning, spiral update, and wild dog survival strategies to optimize the orderly charging of electric vehicles (EV). Objective functions of EV charge orderly planning are taken by using load fluctuation satisfaction, user cost satisfaction, and user convenience satisfaction to achieve the high efficiency of orderly charging. The benchmark test function and the electric vehicle se-quential charging problem were employed to evaluate the proposed IHBA approach. The obtained results are compared with the other algorithms in the literature, which indicate that the IHBA algorithm does not only provides more accurate outcome but better con-vergence speed than the other competitors. © 2022;Taiwan Ubiquitous Information CO LTD. All rights reserved.

关键词： Food products

来源：评论

学校读者我要写书评

暂无评论

PGP: Prior-Guided Pretraining for Small-sample Esophageal Cancer Segmentation

PGP: Prior-Guided Pretraining for Small-sample Esophageal Ca...

引用

IEEE International Conference on Bioinformatics and Biomedicine (BIBM)

作者： Qinglei Shi Wenhan Duan Wanyi Chen Haotian Yang Haochen Lu Kecan Wu Junxi Zhu Juefei Yuan Qiyan Ke Andu Zhang Xiang Wan Changmiao Wang Li Ruan Renzhi Wang The Chinese University of Hong Kong (Shenzhen) Shandong University School of Software Jinan P.R. China Sino-French School of Engineering Beihang University Beijing P.R. China School of Data Science the Chinese University of Hong Kong Shenzhen P.R. China School of Computer Science Beihang University Beijing P.R. China School of Medicine Zhengzhou University Zhengzhou P.R. China School of Medicine The Chinese University of Hong Kong Shenzhen Shenzhen P.R. China Hebei Medical University Fourth Afliated Hospital University Hebei P.R. China Shenzhen Research Institute of Big Data The Chinese University of Hong Kong Shenzhen P.R. China Medical Big Data Lab Shenzhen Research Institute of Big Data Shenzhen P.R. China School of Computer Science and Engineering Beihang University Beijing P.R. China School of Medicine The Chinese University of Hong Kong Shenzhen P.R. China

ISBN: (数字)9798350386226

ISBN: (纸本)9798350386233

Transformer-based models have demonstrated substantial potential in medical image segmentation tasks due to their exceptional ability to capture long-range dependencies. To further enhance segmentation performance, various effective methods have been proposed, including pretraining methods (weakly supervised or self-supervised pretraining schemes), contrastive learning schemes, and knowledge distillation methods. However, segmenting esophageal cancer (EC) from CT images remains a significant challenge, partly due to the complex anatomy of EC, such as variable shapes, extensive extents, and often blurred boundaries with adjacent anatomical structures. In this study, we propose a prior-guided pretraining (PGP) regimen based on bounding boxes, which enhances the model’s ability to discern textural differences between EC and the surrounding tissues. Using Swin UNITR as the backbone, our proposed pretraining scheme demonstrates superior performance in EC segmentation compared to other schemes. To further improve the segmentation accuracy of EC, we also addressed the class imbalance and long-tail problems inherent in EC segmentation, thereby further enhancing segmentation performance.

关键词： Image segmentation Heavily-tailed distribution Shape Computed tomography Contrastive learning Streaming media Transformers Cancer Biomedical imaging Tumors

来源：评论

学校读者我要写书评

暂无评论

M2CF-Net: A Multi-Resolution and Multi-Scale Cross Fusion Network for Segmenting Pathology Lesion of the Focal Lymphocytic Sialadenitis

M2CF-Net: A Multi-Resolution and Multi-Scale Cross Fusion Ne...

引用

Medical Artificial Intelligence (MedAI), IEEE International Conference on

作者： Hao Han Feng Lu Yanhan Deng Xiaofang Luo Hai Jin Wei Tu Xia Xie National Engineering Research Center for Big Data Technology and System Services Computing Technology and System Lab Cluster and Grid Computing Lab School of Computer Science and Technology Huazhong University of Science and Technology Wuhan China Tongji Hospital Tongji Medical College Huazhong University of Science and Technology Wuhan China School of Computer Science and Technology Hainan University Haikou China

In the medical realm, the pivotal role of pathological Whole Slide Images (WSIs) in detecting cancer, tracking disease progression, and evaluating treatment efficacy is indisputable. Nevertheless, the identification and quantification of lesion areas in these gigapixel WSIs present a significant challenge due to their substantial size and the intricate details of lesions. To address these issues, we developed a novel multi-resolution and multi-scale cross fusion network (M 2 CF-Net), adept at managing large-scale pathological WSIs and capturing both fine details and context. Our model particularly focuses on segmenting local lymphocyte infiltration lesions in pathological WSIs of patients diagnosed with primary Sjogren's syndrome. By employing a patch-based training approach and combining interconnected elements via a multi-scale fusion technique, we enhance our model's capacity to detect and analyze structures and features in minor salivary gland section WSIs. Extensive experiments and ablation studies conducted on real-world clinical datasets affirm our model's superior accuracy in identifying lymphocyte-infiltrated regions over state-of-the-art models, with a performance improvement of up to 4.32% in terms of the Dice Similarity Coefficient.

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：