检索结果-内蒙古大学图书馆

arXiv 2022年

作者： Li, Jiangmeng Qiang, Wenwen Zheng, Changwen Su, Bing Xiong, Hui Science & Technology on Integrated Information System Laboratory Institute of Software Chinese Academy of Sciences Beijing China University of Chinese Academy of Sciences Beijing China Guangdong China Gaoling School of Artificial Intelligence Renmin University of China Beijing China Beijing Key Laboratory of Big Data Management and Analysis Methods Beijing China Guangzhou China Department of Computer Science Engineering The Hong Kong University of Science and Technology Hong Kong

What matters for contrastive learning? We argue that contrastive learning heavily relies on informative features, or "hard" (positive or negative) features. Early works include more informative features by applying complex data augmentations and large batch size or memory bank, and recent works design elaborate sampling approaches to explore informative features. The key challenge toward exploring such features is that the source multi-view data is generated by applying random data augmentations, making it infeasible to always add useful information in the augmented data. Consequently, the informativeness of features learned from such augmented data is limited. In response, we propose to directly augment the features in latent space, thereby learning discriminative representations without a large amount of input data. We perform a meta learning technique to build the augmentation generator that updates its network parameters by considering the performance of the encoder. However, insufficient input data may lead the encoder to learn collapsed features and therefore malfunction the augmentation generator. A new margin-injected regularization is further added in the objective function to avoid the encoder learning a degenerate mapping. To contrast all features in one gradient back-propagation step, we adopt the proposed optimization-driven unified contrastive loss instead of the conventional contrastive loss. Empirically, our method achieves state-of-the-art results on several benchmark datasets. Copyright © 2022, The Authors. All rights reserved.

关键词： Backpropagation

来源：评论

学校读者我要写书评

暂无评论

ScalaBFS: A scalable BFS accelerator on HBM-enhanced FPGAs

arXiv

引用

arXiv 2021年

作者： Li, Kexin Liu, Chenhao Shao, Zhiyuan Wang, Zeke Wu, Minkang Chen, Jiajie Liao, Xiaofei Jin, Hai 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 Wuhan30074 China Collaborative Innovation Center of Artificial Intelligence Zhejiang University China

High Bandwidth Memory (HBM) provides massive aggregated memory bandwidth by exposing multiple memory channels to the processing units. To achieve high performance, an accelerator built on top of an FPGA configured with HBM (i.e., FPGA-HBM platform) needs to scale its performance according to the available memory channels. In this paper, we propose an accelerator for BFS (Breadth-First Search) algorithm, named as ScalaBFS, that builds multiple processing elements to sufficiently exploit the high bandwidth of HBM to improve efficiency. We implement the prototype system of ScalaBFS and conduct BFS in both real-world and synthetic scale-free graphs on Xilinx Alveo U280 FPGA card real hardware. The experimental results show that ScalaBFS scales its performance almost linearly according to the available memory pseudo channels (PCs) from the HBM2 subsystem of U280. By fully using the 32 PCs and building 64 processing elements (PEs) on U280, ScalaBFS achieves a performance up to 19.7 GTEPS (Giga Traversed Edges Per Second). When conducting BFS in sparse real-world graphs, ScalaBFS achieves equivalent GTEPS to Gunrock running on the state-of-art Nvidia V100 GPU that features 64-PC HBM2 (twice memory bandwidth than U280). Copyright © 2021, The Authors. All rights reserved.

关键词： Field programmable gate arrays (FPGA)

来源：评论

学校读者我要写书评

暂无评论

Interventional Contrastive Learning with Meta Semantic Regularizer

arXiv

引用

arXiv 2022年

作者： Qiang, Wenwen Li, Jiangmeng Zheng, Changwen Su, Bing Xiong, Hui Science & Technology on Integrated Information System Laboratory Institute of Software Chinese Academy of Sciences Beijing China University of Chinese Academy of Sciences Beijing China Guangdong China Gaoling School of Artificial Intelligence Renmin University of China Beijing China Beijing Key Laboratory of Big Data Management and Analysis Methods Beijing China Guangzhou China Department of Computer Science & Engineering The Hong Kong University of Science and Technology Hong Kong

Contrastive learning (CL)-based self-supervised learning models learn visual representations in a pairwise manner. Although the prevailing CL model has achieved great progress, in this paper, we uncover an ever-overlooked phenomenon: When the CL model is trained with full images, the performance tested in full images is better than that in foreground areas;when the CL model is trained with foreground areas, the performance tested in full images is worse than that in foreground areas. This observation reveals that backgrounds in images may interfere with the model learning semantic information and their influence has not been fully eliminated. To tackle this issue, we build a Structural Causal Model (SCM) to model the background as a confounder. We propose a backdoor adjustment-based regularization method, namely Interventional Contrastive Learning with Meta Semantic Regularizer (ICL-MSR), to perform causal intervention towards the proposed SCM. ICL-MSR can be incorporated into any existing CL methods to alleviate background distractions from representation learning. Theoretically, we prove that ICL-MSR achieves a tighter error bound. Empirically, our experiments on multiple benchmark datasets demonstrate that ICL-MSR is able to improve the performances of different state-of-the-art CL methods. Copyright © 2022, The Authors. All rights reserved.

关键词： Semantics

来源：评论

学校读者我要写书评

暂无评论

Argumentation Based Ontology Alignment Extraction 6th

Argumentation Based Ontology Alignment Extraction

引用

6th International Conference on Advanced Machine Learning Technologies and Applications, AMLTA 2021

作者： Wu, Xiaojing Xue, Xingsi Hu, Wenyu Fujian Provincial Key Laboratory of Big Data Mining and Applications Fujian University of Technology 33 Xuefu South Road Fuzhou Fujian350118 China Intelligent Information Processing Research Center Fujian University of Technology Fuzhou Fujian350118 China Institute of Artificial Intelligence Fujian University of Technology Fuzhou Fujian350118 China Fujian Key Lab for Automotive Electronics and Electric Drive Fujian University of Technology Fuzhou Fujian350118 China School of Information Science and Engineering Fujian University of Technology Fuzhou Fujian350118 China

ISBN: (纸本)9783030697167

The ontology matching technique aims at establishing the correspondence between two ontologies’ entities to solve their heterogeneity problem. In the matching process, the quality of the single matcher’s alignment can not be ensured. Usually, multiple matches are required to work together to increase the evidence of potential matches or mismatches. Selecting, combining, and adjusting these ontology matches to obtain high-quality ontology comparisons is one of the main challenges in ontology matching. This paper proposes an Argumentation Framework (A.F.) based on the ontology extracting technique to address this challenge. First, the proposed approach obtains the alignments obtained by different ontology matches. It extracts the final alignment by debating the disputed entity correspondences with A.F. The experiment is conducted on the Bibliographic track provided by Ontology Alignment Evaluation Initiative (OAEI), and the statistical comparison with the state-of-the-art ontology matching techniques shows the effectiveness of the proposed approach. © 2021, The Author(s), under exclusive license to Springer Nature Switzerland AG.

关键词： Extraction

来源：评论

学校读者我要写书评

暂无评论

Holographic Display in Consumer Electronics for Detecting Abnormal IoT Devices Using a Lightweight Security Model

引用

IEEE Transactions on Consumer Electronics 2025年

作者： Aanjankumar, S. Sathyamoorthy, Malathy Dhanaraj, Rajesh Kumar Poonkuntran, S. Khan, Firoz Quasim, Mohammad Tabrez Basheer, Shakila VIT Bhopal University School of Computing Science and Engineering Bhopal-Indore Highway Kothrikalan Madhya Pradesh Sehore 466114 India KPR Institute of Engineering and Technology Department of Information Technology Tamilnadu Coimbatore 641407 India Symbiosis Institute of Computer Studies and Research (SICSR) Symbiosis International (Deemed University) Maharastra Pune 412115 India Faculty in Center for Information and Communication Sciences Ball state University United States University of Bisha College of Computing and Information Technology Department of Computer Science and Artificial Intelligence Bisha Saudi Arabia Princess Nourah bint Abdulrahman University Department of Information Systems College of computer and Information science Riyadh 11671 Saudi Arabia

IoT (Internet of Things) devices are becoming more popular because they can be connected to mobile phones and communicate with various types of devices (e.g., smart homes, automation, and monitoring applications), which provides a high-quality service with the flexibility of performing operations from anywhere at any time. This research proposes a holographic display in consumer electronics to provide a more interactive experience for the user by providing significant security and privacy framework to the IoT devices which are prone to vulnerabilities. A simple Post-Quantum Cryptography Algorithm (PQCA) is used in this study to find flaws in a quantum lattice that is based on a 3x3 matrix in pre-processing. Also, an edge-based anomaly detection framework is created to work with consumer devices to show holographic data streams and IoT device activity in real time for devices with limited resources and less computational overhead than traditional machine learning models. The suggested method conducts testing on a set of unsupervised IoT devices, which contain data and metrics on user behaviour. The dataset contains 8000 service requests in an IoT environment. It finds security anomalies in 70% of the cases in training phases and 30% of the cases in testing phases, respectively. The proposed system detects vulnerable IoT devices by projecting them in a holographic projection graph, which in turn enhances privacy. The test results showed that the minimum encryption time overhead is 0.00085, and the accuracy achieved is about 97.44%. © 1975-2011 IEEE.

关键词： Consumer Electronics Holographic Display Internet of Things (IoT) lightweight post-quantum cryptography Lightweight Security model

来源：评论

学校读者我要写书评

暂无评论

HIPA: Hierarchical Patch Transformer for Single Image Super Resolution

arXiv

引用

arXiv 2022年

作者： Cai, Qing Qian, Yiming Li, Jinxing Lyu, Jun Yang, Yee-Hong Wu, Feng Zhang, David The Faculty of Information Science and Engineering Ocean University of China Shandong Qingdao266100 China The Department of Computer Science University of Manitoba WinnipegMBR3T 2N2 Canada The School of Computer Science and Technology Harbin Institute of Technology Guangdong Shenzhen518055 China The School of Nursing The Hong Kong Polytechnic University Hong Kong The Department of Computing Science University of Alberta EdmontonABT6G 2E9 Canada The School of Information Science and Technology University of Science and Technology of China Anhui Hefei230026 China The School of Data Science The Chinese University of Hong Kong Guangdong Shenzhen518172 China The Shenzhen Institute of Artificial Intelligence and Robotics for Society Guangdong Shenzhen518000 China Linklogis Joint Laboratory of Computer Vision and Artificial Intelligence Guangdong Shenzhen518172 China

Transformer-based architectures start to emerge in single image super resolution (SISR) and have achieved promising performance. However, most existing vision Transformer-based SISR methods still have two shortcomings: (1) they divide images into the same number of patches with a fixed size, which may not be optimal for restoring patches with different levels of texture richness;and (2) their position encodings treat all input tokens equally and hence, neglect the dependencies among them. This paper presents a HIPA, which stands for a novel Transformer architecture that progressively recovers the high resolution image using a hierarchical patch partition. Specifically, we build a cascaded model that processes an input image in multiple stages, where we start with tokens with small patch sizes and gradually merge them to form the full resolution. Such a hierarchical patch mechanism not only explicitly enables feature aggregation at multiple resolutions but also adaptively learns patch-aware features for different image regions, e.g., using a smaller patch for areas with fine details and a larger patch for textureless regions. Meanwhile, a new attention-based position encoding scheme for Transformer is proposed to let the network focus on which tokens should be paid more attention by assigning different weights to different tokens, which is the first time to our best knowledge. Furthermore, we also propose a multi-receptive field attention module to enlarge the convolution receptive field from different branches. The experimental results on several public datasets demonstrate the superior performance of the proposed HIPA over previous methods quantitatively and qualitatively. We will share our code and models when the paper is accepted. Copyright © 2022, The Authors. All rights reserved.

关键词： Image reconstruction

来源：评论

学校读者我要写书评

暂无评论

Multi-instance curriculum learning for histopathology image classification with bias reduction

引用

Medical image analysis 2025年 105卷 103647页

作者： Zihao Mi Jianan Zhang Xueyu Liu Guanghui Yue Junhong Yue Mingqiang Wei Yidi Li Yongfei Wu College of Computer Science and Technology (College of Data Science) Taiyuan University of Technology Taiyuan Shanxi 030024 China. National-Regional Key Technology Engineering Laboratory for Medical Ultrasound Guangdong Key Laboratory for Biomedical Measurements and Ultrasound Imaging School of Biomedical Engineering Health Science Center Shenzhen University Shenzhen China. College of Artificial Intelligence Taiyuan University of Technology Taiyuan Shanxi 030024 China. College of Computer Science and Technology (College of Data Science) Taiyuan University of Technology Taiyuan Shanxi 030024 China College of Artificial Intelligence Taiyuan University of Technology Taiyuan Shanxi 030024 China. Electronic address: wuyongfei@***.

Multi-instance learning (MIL) exhibits advanced and surpassed capabilities in understanding and recognizing complex patterns within gigapixel histopathological images. However, current MIL methods for the analysis of the histopathological images still give rise to two main concerns. On one hand, vanilla MIL methods intuitively focus on identifying salient instances (easy-to-classify instances) without considering hard-to-classify instances, which is biased and prone to produce false positive instances. On the other hand, since the positive tissue occupies only a small fraction of histopathological images, it is commonly suffer from class imbalance between positive and negative instances, causing the MIL model to overly focus on the majority class in training instances classifier. In light of these issues of bias learning, we propose a multi-instance curriculum learning method that collaboratively incorporates hard negative instance mining and positive instance augmentation to improve classification performance of the model. Specifically, we first initialize the MIL model using easy-to-classify instances, then we mine the hard negative instances (hard-to-classify instances) and augment the positive instances via the diffusion model. Finally, the MIL model is retrained with memory rehearsal method by combining the mined negative instances and the augmented positive instances. Technically, the diffusion model is first designed to generate lesion instances, which optimally augment diverse features to reflect realistic positive samples with post screening scenario. Extensive experimental results show that the proposed method alleviates model bias in MIL and improves model interpretability.

关键词： Curriculum learning Diffusion model Hard negative instance mining Histopathology image Multi-instance learning Positive instance augmentation

来源：评论

学校读者我要写书评

暂无评论

Fast Coding Mode Prediction for Intra Prediction in VVC SCC

Fast Coding Mode Prediction for Intra Prediction in VVC SCC

引用

IEEE International Conference on Image Processing

作者： Dayong Wang Junyi Yu Xin Lu Frederic Dufaux Hongwei Guo Hui Guo Ce Zhu Chongqing Key Laboratory on Big Data for Bio Intelligence Chongqing University of Posts and Telecommunications Guangxi Key Laboratory of Machine Vision and Intelligent Control Wuzhou University Chongqing Key Laboratory of Image Cognition Chongqing University of Posts and Telecommunications Faculty of Computing Engineering and Media (CEM) De Montfort University Université Paris-Saclay CNRS CentraleSupélec Laboratoire des signaux et systèmes School of Engineering Honghe University Mengzi Yunnan China University of Electronic Science and Technology of China

ISBN: (数字)9798350349399

ISBN: (纸本)9798350349405

Currently, screen content video applications are increasingly widespread in our daily lives. The latest Screen Content Coding (SCC) standard, known as Versatile Video Coding (VVC) SCC, employs screen content Coding Modes (CMs) selection. While VVC SCC achieves high coding efficiency, its coding complexity poses a significant obstacle to the further widespread adoption of screen content video. Hence, it is crucial to enhance the coding speed of VVC SCC. In this paper, we propose a fast mode and splitting decision for Intra prediction in VVC SCC. Specifically, we initially exploit deep learning techniques to predict content types for all CUs. Subsequently, we examine CM distributions of different content types to predict candidate CMs for CUs. We then introduce early skip and early terminate CM decisions for different content types of CUs to further eliminate unlikely CMs. Finally, we develop Block-based Differential Pulse-Code Modulation (BDPCM) early termination to improve coding speed. Experimental results demonstrate that the proposed algorithm can improve coding speed by $34.95 \%$ on average while maintaining almost the same coding efficiency.

关键词： Video coding Deep learning Image coding Modulation Prediction algorithms Complexity theory Copper

来源：评论

学校读者我要写书评

暂无评论

Internal search of the evolution matrix in QUasi-Affine TRansformation Evolution (QUATRE) algorithm

Internal search of the evolution matrix in QUasi-Affine TRan...

引用

作者： Chu, Shu-Chuan Chen, Yuxin Meng, Fanjia Yang, Chen Pan, Jeng-Shyang Meng, Zhenyu College of Computer Science and Engineering Shandong University of Science and Technology Qingdao China Institute of Artificial Intelligence Fujian University of Technology Fuzhou China Guanzhuang Central Primary School of Zhangqiu District Jinan China Fujian Provincial Key Lab of Big Data Mining and Applications Fujian University of Technology Fuzhou China

Optimization demands exist everywhere in the real world especially in science studies and engineering practices, and it is important that the method to deal with intricacy optimization problems should itself be relative simple. Particle Swarm Optimization (PSO) and Differential Evolution (DE) both are simple evolutionary algorithms (EAs) which are proposed for single-objective optimization and both of them have been proved to be efficient methods for optimizing applications, however, there are still some weakness existing within them. A innovative evolutionary method named QUasi-Affine TRansformation Evolutionary (QUATRE) algorithm which is derived from, also tackles some weaknesses of PSO and DE algorithm, and obtains better performance on commonly used test suites. The key characteristic of QUATRE is that an automatically generated matrix named evolution matrix M is implemented in evolutionary process, which is taken as an alternative of employing the crossover rate CR. Here in this paper, we present a novel QUATRE variant, named IS-QUATRE, which can explore the search area in a better way comparison with the previous method, and relatively good optimization ability can be obtained by our proposed IS-QUATRE algorithm under CEC2013 test suit. And the conducted experimental results validate that our proposed IS-QUATRE is competitive with some other famous PSO and DE variants. © 2020 - IOS Press and the authors. All rights reserved.

关键词： Particle swarm optimization (PSO)

来源：评论

学校读者我要写书评

暂无评论

Analysis of Ethical Issues Associated with Wearable Medical Devices

Analysis of Ethical Issues Associated with Wearable Medical ...

引用

International Conference on Smart Systems and Inventive technology (ICSSIT)

作者： S. Venkatachalam T Padmavathi N. Vinodh J. Thilagavathi Garvita Joshi G. Ramachandran B. Rajasekaran Department of Management Karpagam Academy of Higher Education Coimbatore Department of ECE CVR College of Engineering Telangana S.A.Engineering College Thiruvalluvar Artificial intelligence and data science Arjun College of Technology Coimbatore Mahakal Institute of Pharmaceutical Studies Ujjain ECE Vinayaka Mission’s KirupanandaVariyar Engineering College Vinayaka Mission’s Research Foundation (Deemed to be University) Salem Tamil Nadu India Department of Electronics and Communication Engineering Vinayaka Mission’s Kirupananda Variyar Engineering College Vinayaka Mission’s Research Foundation - Deemed to be University Salem India

Medical practice and the delivery of healthcare are changing as a result of the advancement and widespread use of medical wearable technology. The daily vast amount of personal data those results, privacy disclosure, and other ethical difficulties associated with interests are gradually brought to light, though. This paper summarises and analyses the ethical issues that exist in the entire process of health medical wearable equipment serving humans, including the equipment itself, data collection, transmission, management, and data use, from the perspective of medical ethics. It then suggests appropriate solutions and countermeasures from the perspectives of respecting autonomy, informed consent, privacy protection, medical optimization, and beneficial principles. To fully utilize the potential of health care wearables in the field of medical care, advance the development of new intelligent medical care, and contribute to the creation of a healthy India, the concepts of “prevention before disease, disease prevention, and change prevention,” and “medicine.

关键词： Ethics Privacy Medical devices Law Wearable computers Medical services Stakeholders

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：