检索结果-内蒙古大学图书馆

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

Time-sensitive Learning for Heterogeneous Federated Edge intelligence

arXiv

引用

arXiv 2023年

作者： Xiao, Yong Zhang, Xiaohan Li, Yingyu Shi, Guangming Krunz, Marwan Nguyen, Diep N. Hoang, Dinh Thai The School of Electronic Information and Communications The Huazhong University of Science and Technology Wuhan430074 China The Peng Cheng Laboratory Guangdong Shenzhen518055 China Guangdong Guangzhou510555 China The School of Mechanical Engineering and Electronic Information China University of Geosciences Wuhan430074 China The School of Artificial Intelligence The Xidian University Shaanxi Xi'An710071 China The Department of Electrical and Computer Engineering The University of Arizona TucsonAZ85721 United States The School of Electrical and Data Engineering University of Technology Sydney Faculty of Engineering and Information Technology SydneyNSW120558 Australia

Real-time machine learning (ML) has recently attracted significant interest due to its potential to support instantaneous learning, adaptation, and decision making in a wide range of application domains, including self-driving vehicles, intelligent transportation, and industry automation. In this paper, we investigate real-time ML in a federated edge intelligence (FEI) system, an edge computing system that implements federated learning (FL) solutions based on data samples collected and uploaded from decentralized data networks, e.g., Internet-of-Things (IoT) and/or wireless sensor networks. FEI systems often exhibit heterogenous communication and computational resource distribution, as well as non-i.i.d. data samples arrived at different edge servers, resulting in long model training time and inefficient resource utilization. Motivated by this fact, we propose a time-sensitive federated learning (TS-FL) framework to minimize the overall run-time for collaboratively training a shared ML model with desirable accuracy. Training acceleration solutions for both TS-FL with synchronous coordination (TS-FL-SC) and asynchronous coordination (TS-FL-ASC) are investigated. To address the straggler effect in TS-FL-SC, we develop an analytical solution to characterize the impact of selecting different subsets of edge servers on the overall model training time. A server dropping-based solution is proposed to allow some slow-performance edge servers to be removed from participating in the model training if their impact on the resulting model accuracy is limited. A joint optimization algorithm is proposed to minimize the overall time consumption of model training by selecting participating edge servers, the local epoch number (the number of model training iterations per coordination), and the data batch size (the number of data samples for each model training iteration). Motivated by the fact that data samples at the slowest edge server may exhibit special characteristics that canno

关键词： Machine learning

来源：评论

学校读者我要写书评

暂无评论

NER- RoBERTa: Fine-Tuning RoBERTa for Named Entity Recognition (NER) within low-resource languages

arXiv

引用

arXiv 2024年

作者： Abdullah, Abdulhady Abas Abdulla, Srwa Hasan Toufiq, Dalia Mohammad Maghdid, Halgurd S. Rashid, Tarik A. Farho, Pakshan F. Sabr, Shadan Sh. Taher, Akar H. Hamad, Darya S. Veisi, Hadi Asaad, Aras T. Artificial Intelligence and Innovation Centre University of Kurdistan Hewler Erbil Iraq Computer Science and Engineering Department University of Kurdistan Hewler KR Erbil Iraq Department of Horticulture College of Agricultural Engineering Sciences University of Sulaimani- Kurdistan Region Iraq Branch of Basic Medical Science College of medicine University of Sulaimani- Kurdistan Region Iraq Department of Engineering Research Center Deanship of R&D Centers Koya University Kurdistan Region Iraq Department of Kurdish Language Faculty of Education Koya University Kurdistan Region Iraq Department of Kurdish Faculty of Education Koya University Kurdistan Region Iraq Department of Software Engineering Faculty of Engineering Koya University Kurdistan Region Iraq School of Intelligent Systems College of Interdisciplinary Science and Technologies University of Tehran Iran

Nowadays natural Language Processing (NLP) is an important tool for most people’s daily life routines, ranging from understating speech, translation, name entity recognition (ENR), and text categorizing, to the generative text models such as ChatGPT. Due to existing big data and consequently big corpora for the most usable languages including English, Spanish, Turkish, Persia, and many more, these applications have been utilized accurately. However, the Kurdish language still needs more corpora and big datasets to be included in the NLP applications. This is because the Kurdish language has a rich linguistic structure, varied dialects, and a poor dataset, which poses unique challenges for Kurdish NLP (KNLP) application development. While several types of research have been conducted in KNLP for various applications, the Kurdish ENR (KNER) remained a challenge for most of the KNLP applications including text analysis and text classification. In this work, we address this limitation by proposing a methodology for fine-tuning the pre-trained RoBERTa model for KNER1. To this end, first, a Kurdish corpus is created, followed by designing a modified model architecture, and the training procedures are implemented. To evaluate the trained model, a set of experiments is conducted to show the performance of the KNER model using different tokenization methods and trained models. The experimental results showed that fine-tuned RoBERTa with sentence-piece tokenization method substantially improves KNER performance by 12.8% (F1-score improvement) in comparison to traditional models and consequently establishes a new benchmark for KNLP. © 2024, CC BY.

关键词： Natural language processing systems

来源：评论

学校读者我要写书评

暂无评论

Parallel Distance: A New Paradigm of Measurement for Parallel Driving

引用

IEEE/CAA Journal of Automatica Sinica 2020年第4期7卷 1169-1178页

作者： Teng Liu Hong Wang Bin Tian Yunfeng Ai Long Chen the Vehicle Intelligence Pioneers Inc. Qingdao 266109 the Department of Automotive Engineering Chongqing UniversityChongqing 400044China the Mechanical and Mechatronics Engineering Department Waterloo UniversityN2L 3G1Canada the State Key Laboratory of Management and Control for Complex Systems Institute of AutomationChinese Academy of SciencesBeijing 100190China the School of Artificial Intelligence University of Chinese Academy of SciencesBeijing 100049China the School of Data and Computer Science Sun Yat-sen UniversityGuangzhou 510006China

In this paper, a new paradigm named parallel distance is presented to measure the data information in parallel driving system. As an example, the core variables in the parallel driving system are measured and evaluated in the parallel distance framework. First, the parallel driving 3.0 system included control and management platform, intelligent vehicle platform and remote-control platform is introduced. Then,Markov chain(MC) is utilized to model the transition probability matrix of control commands in these systems. Furthermore, to distinguish the control variables in artificial and physical driving conditions, different distance calculation methods are enumerated to specify the differences between the virtual and real signals. By doing this, the real system can be guided and the virtual system can be im-proved. Finally, simulation results exhibit the merits and multiple applications of the proposed parallel distance framework.

关键词： artificial and physical system parallel distance parallel driving 3.0 parallel system rotational and accelerator signal

来源：评论

学校读者我要写书评

暂无评论

Semi-Cycled Generative Adversarial Networks for Real-World Face Super-Resolution

arXiv

引用

arXiv 2022年

作者： Hou, Hao Xu, Jun Hou, Yingkun Hu, Xiaotao Wei, Benzheng Shen, Dinggang College of Intelligence and Information Engineering Shandong University of Traditional Chinese Medicine Ji'nan250355 China School of Statistics and Data Science KLMDASR LEBPS LPMC Nankai University Tianjin300071 China School of Biomedical Engineering ShanghaiTech University Shanghai China The School of Information Science and Technology Taishan University Tai’an271000 China College of Computer Science Nankai University Tianjin300071 China The Center for Medical Artificial Intelligence Shandong University of Traditional Chinese Medicine Ji’nan250355 China School of Biomedical Engineering ShanghaiTech University United Imaging Co. Shanghai China

Real-world face super-resolution (SR) is a highly ill-posed image restoration task. The fully-cycled Cycle-GAN architecture is widely employed to achieve promising performance on face SR, but is prone to produce artifacts upon challenging cases in real-world scenarios, since joint participation in the same degradation branch will impact final performance due to huge domain gap between real-world and synthetic LR ones obtained by generators. To better exploit the powerful generative capability of GAN for real-world face SR, in this paper, we establish two independent degradation branches in the forward and backward cycle-consistent reconstruction processes, respectively, while the two processes share the same restoration branch. Our Semi-Cycled Generative Adversarial Networks (SCGAN) is able to alleviate the adverse effects of the domain gap between the real-world LR face images and the synthetic LR ones, and to achieve accurate and robust face SR performance by the shared restoration branch regularized by both the forward and backward cycle-consistent learning processes. Experiments on two synthetic and two real-world datasets demonstrate that, our SCGAN outperforms the state-of-the-art methods on recovering the face structures/details and quantitative metrics for real-world face SR. The code will be publicly released at https: //***/HaoHou-98/SCGAN. Copyright © 2022, 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

COLLABORATIVE AUTO-ENCODING FOR BLIND IMAGE QUALITY ASSESSMENT

arXiv

引用

arXiv 2023年

作者： Zhou, Zehong Zhou, Fei Qiu, Guoping College of Electronic and Information Engineering Shenzhen University Shenzhen China Peng Cheng Laboratory Shenzhen China Guangdong Key Laboratory of Intelligent Information Processing Shenzhen China Shenzhen Institute for Artificial Intelligence and Robotics for Society Shenzhen China School of Computer Science University of Nottingham Nottingham United Kingdom Guangdong-Hong Kong Joint Laboratory for Big Data Imaging and Communication Shenzhen China

Blind image quality assessment (BIQA) is a challenging problem with important real-world applications. Recent efforts attempting to exploit powerful representations by deep neural networks (DNN) are hindered by the lack of subjectively annotated data. This paper presents a novel BIQA method which overcomes this fundamental obstacle. Specifically, we design a pair of collaborative autoencoders (COAE) consisting of a content autoencoder (CAE) and a distortion autoencoder (DAE) that work together to extract content and distortion representations, which are shown to be highly descriptive of image quality. While the CAE follows a standard codec procedure, we introduce the CAE-encoded feature as an extra input to the DAE’s decoder for reconstructing distorted images, thus effectively forcing DAE’s encoder to extract distortion representations. The self-supervised learning framework allows the COAE including two feature extractors to be trained by almost unlimited amount of data, thus leaving limited samples with annotations to finetune a BIQA model. We will show that the proposed BIQA method achieves state-of-the-art performance and has superior generalization capability over other learning based models. The codes are available at: https://***/Macro-Zhou/NRIQA-VISOR/. © 2023, CC BY.

关键词： Supervised learning

来源：评论

学校读者我要写书评

暂无评论

MedBench: A Comprehensive, Standardized, and Reliable Benchmarking System for Evaluating Chinese Medical Large Language Models

arXiv

引用

arXiv 2024年

作者： Liu, Mianxin Ding, Jinru Xu, Jie Hu, Weiguo Li, Xiaoyang Zhu, Lifeng Bai, Zhian Shi, Xiaoming Wang, Benyou Song, Haitao Liu, Pengfei Zhang, Xiaofan Wang, Shanshan Li, Kang Wang, Haofen Ruan, Tong Huang, Xuanjing Sun, Xin Zhang, Shaoting Shanghai Artificial Intelligence Laboratory Shanghai200232 China Ruijin Hospital Affiliated to Shanghai Jiaotong University School of Medicine Shanghai200025 China Shenzhen Research Institute of Big Data The Chinese University of Hong Kong Shenzhen518172 China The Shanghai Artificial Intelligence Research Institute Shanghai Jiao Tong University Shanghai200240 China The School of Electronic Information and Electrical Engineering Shanghai Jiao Tong University Shanghai200240 China Qing Yuan Research Institute Shanghai Jiao Tong University Shanghai200240 China Shenzhen Institutes of Advanced Technology Chinese Academy of Sciences Shenzhen518055 China Sichuan University West China Hospital Chengdu610041 China The College of Design and Innovation Tongji University Shanghai200092 China The Department of Computer Science and Technology East China University of Science and Technology Shanghai200237 China The School of Computer Science Fudan University Shanghai200433 China Xinhua Hospital Affiliated to Shanghai Jiaotong University School of Medicine Shanghai200092 China

Ensuring the general efficacy and goodness for human beings from medical large language models (LLM) before real-world deployment is crucial. However, a widely accepted and accessible evaluation process for medical LLM, especially in the Chinese context, remains to be established. In this work, we introduce "MedBench", a comprehensive, standardized, and reliable benchmarking system for Chinese medical LLM. First, MedBench assembles the currently largest evaluation dataset (300,901 questions) to cover 43 clinical specialties and performs multi-facet evaluation on medical LLM. Second, MedBench provides a standardized and fully automatic cloud-based evaluation infrastructure, with physical separations for question and ground truth. Third, MedBench implements dynamic evaluation mechanisms to prevent shortcut learning and answer remembering. Applying MedBench to popular general and medical LLMs, we observe unbiased, reproducible evaluation results largely aligning with medical professionals' perspectives. This study establishes a significant foundation for preparing the practical applications of Chinese medical LLMs. MedBench is publicly accessible at https://***. © 2024, CC BY.

关键词： Benchmarking

来源：评论

学校读者我要写书评

暂无评论

Attention mechanism meets with hybrid dense network for Hyperspectral Image Classification

arXiv

引用

arXiv 2022年

作者： Ahmad, Muhammad Mehmood Khan, Adil Mazzara, Manuel Distefano, Salvatore Roy, Swalpa Kumar Wu, Xin Department of Computer Science National University of Computer and Emerging Sciences Islamabad Chiniot-Faisalabad Campus Chiniot35400 Pakistan Institute of Data Science and Artificial Intelligence Innopolis University Innopolis420500 Russia Institute of Software Development and Engineering Innopolis University Innopolis420500 Russia Dipartimento di Matematica e Informatica MIFT University of Messina Messina98121 Italy Department of Computer Science and Engineering Jalpaiguri Government Engineering College West Bengal 735102 India School of Information and Electronics Beijing Institute of Technology Beijing100081 China

The nonlinear relation between the spectral information and the corresponding objects (complex physiognomies) makes pixel-wise classification challenging for conventional methods. To deal with nonlinearity issues in Hyperspectral Image Classification (HISC), Convolutional Neural Networks (CNN) are more suitable, indeed. However, fixed kernel sizes make traditional CNN too specific, neither flexible nor conducive to feature learning, thus impacting on the classification accuracy. The convolution of different kernel size networks may overcome this problem by capturing more discriminating and relevant information. In light of this, the proposed solution aims at combining the core idea of 3D and 2D Inception net with the Attention mechanism to boost the HSIC CNN performance in a hybrid scenario. The resulting attention-fused hybrid network (AfNet) is based on three attention-fused parallel hybrid subnets with different kernels in each block repeatedly using highlevel features to enhance the final ground-truth maps. In short, AfNet is able to selectively filter out the discriminative features critical for classification. Several tests on HSI datasets provided competitive results for AfNet compared to state-of-the-art models. The proposed pipeline achieved, indeed, an overall accuracy of 97% for the Indian Pines, 100% for Botswana, 99% for Pavia University, Pavia Center, and Salinas datasets. © 2022, CC BY.

关键词： Convolution

来源：评论

学校读者我要写书评

暂无评论

Collaborative Auto-encoding for Blind Image Quality Assessment

Collaborative Auto-encoding for Blind Image Quality Assessme...

引用

IEEE International Conference on Multimedia and Expo (ICME)

作者： Zehong Zhou Fei Zhou Guoping Qiu College of Electronic and Information Engineering Shenzhen University Shenzhen China Guangdong Key Laboratory of Intelligent Information Processing Shenzhen China Shenzhen Institute for Artificial Intelligence and Robotics for Society Shenzhen China Peng Cheng Laboratory Shenzhen China Guangdong-Hong Kong Joint Laboratory for Big Data Imaging and Communication Shenzhen China School of Computer Science University of Nottingham Nottingham U.K

Blind image quality assessment (BIQA) is a challenging problem with important real-world applications. Recent efforts attempting to exploit powerful representations by deep neural networks (DNN) are hindered by the lack of subjectively annotated data. This paper presents a novel BIQA method which overcomes this fundamental obstacle. Specifically, we design a pair of collaborative autoencoders (COAE) consisting of a content autoencoder (CAE) and a distortion autoencoder (DAE) that work together to extract content and distortion representations, which are shown to be highly descriptive of image quality. While the CAE follows a standard codec procedure, we introduce the CAE-encoded feature as an extra input to the DAE's decoder for reconstructing distorted images, thus effectively forcing DAE's encoder to extract distortion representations. The self-supervised learning framework allows the COAE including two feature extractors to be trained by almost unlimited amount of data, thus leaving limited samples with annotations to finetune a BIQA model. We will show that the proposed BIQA method achieves state-of-the-art performance and has superior generalization capability over other learning based models. All the related codes, trained models, and the supplementary material are available at: https://***/Macro-Zhou/NRIQA-VISOR/.

关键词：

来源：评论

学校读者我要写书评

暂无评论

When Vision Meets Touch: A Contemporary Review for Visuotactile Sensors from the Signal Processing Perspective

arXiv

引用

arXiv 2024年

作者： Li, Shoujie Wang, Zihan Wu, Changsheng Li, Xiang Luo, Shan Fang, Bin Sun, Fuchun Zhang, Xiao-Ping Ding, Wenbo Tsinghua Shenzhen International Graduate School Shenzhen518055 China RISC-V International Open Source Laboratory Shenzhen518055 China Department of Materials Science and Engineering National University of Singapore Singapore117575 Singapore Centre for Robotics Research King’s College London LondonWC2R 2LS United Kingdom Department of Automation Tsinghua University Beijing100084 China School of Artificial Intelligence Beijing University of Posts and Telecommunications Beijing100876 China Department of Computer Science and Technology Tsinghua University Beijing100084 China

Tactile sensors, which provide information about the physical properties of objects, are an essential component of robotic systems. The visuotactile sensing technology with the merits of high resolution and low cost has facilitated the development of robotics from environment exploration to dexterous operation. Over the years, several reviews on visuotactile sensors for robots have been presented, but few of them discussed the significance of signal processing methods to visuotactile sensors. Apart from ingenious hardware design, the full potential of the sensory system toward designated tasks can only be released with the appropriate signal processing methods. Therefore, this paper provides a comprehensive review of visuotactile sensors from the perspective of signal processing methods and outlooks possible future research directions for visuotactile sensors. Copyright © 2024, The Authors. All rights reserved.

关键词： Signal processing

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：