检索结果-内蒙古大学图书馆

arXiv 2023年

作者： Li, Huantong Wu, Xiangmiao Lv, Fanbing Liao, Daihai Li, Thomas H. Zhang, Yonggang Han, Bo Tan, Mingkui South China University of Technology China Changsha Hisense Intelligent System Research Institute Co. Ltd China Hong Kong Baptist University Hong Kong Key Laboratory of Big Data and Intelligent Robot Ministry of Education China PengCheng Laboratory China Information Technology R&D Innovation Center of Peking University China School of Electronic and Computer Engineering Peking University Shenzhen Graduate School Shenzhen China

Zero-shot quantization (ZSQ) is promising for compressing and accelerating deep neural networks when the data for training full-precision models are inaccessible. In ZSQ, network quantization is performed using synthetic samples, thus, the performance of quantized models depends heavily on the quality of synthetic samples. Nonetheless, we find that the synthetic samples constructed in existing ZSQ methods can be easily fitted by models. Accordingly, quantized models obtained by these methods suffer from significant performance degradation on hard samples. To address this issue, we propose HArd sample Synthesizing and Training (HAST). Specifically, HAST pays more attention to hard samples when synthesizing samples and makes synthetic samples hard to fit when training quantized models. HAST aligns features extracted by full-precision and quantized models to ensure the similarity between features extracted by these two models. Extensive experiments show that HAST significantly outperforms existing ZSQ methods, achieving performance comparable to models that are quantized with real data. Copyright © 2023, The Authors. All rights reserved.

关键词： Deep neural networks

来源：评论

学校读者我要写书评

暂无评论

Robust Low-rank Deep Feature Recovery in CNNs: Toward Low Information Loss and Fast Convergence

Robust Low-rank Deep Feature Recovery in CNNs: Toward Low In...

引用

IEEE International Conference on data Mining (ICDM)

作者： Jiahuan Ren Zhao Zhang Jicong Fan Haijun Zhang Mingliang Xu Meng Wang School of Computer Science and Information Engineering Hefei University of Technology Hefei China Key Laboratory of Knowledge Engineering with Big Data (Ministry of Education) & Intelligent Interconnected Systems Laboratory of Anhui Province Hefei University of Technology Hefei China School of Data Science The Chinese University of Hong Kong (Shenzhen) & Shenzhen Research Institute of Big Data Shenzhen China Harbin Institute of Technology (Shenzhen) Shenzhen China School of Information Engineering Zhengzhou University Zhengzhou China

ISBN: (纸本)9781665423991

Convolutional Neural Networks (CNNs)-guided deep models have obtained impressive performance for image representation, however the representation ability may still be restricted and usually needs more epochs to make the model converge in training, due to the useful information loss during the convolution and pooling operations. We therefore propose a general feature recovery layer, termed Low-rank Deep Feature Recovery (LDFR), to enhance the representation ability of the convolutional features by seamlessly integrating low-rank recovery into CNNs, which can be easily extended to all existing CNNs-based models. To be specific, to recover the lost information during the convolution operation, LDFR aims at learning the low-rank projections to embed the feature maps onto a low-rank subspace based on some selected informative convolutional feature maps. Such low-rank recovery operation can ensure all convolutional feature maps to be reconstructed easily to recover the underlying subspace with more useful and detailed information discovered, e.g., the strokes of characters or the texture information of clothes can be enhanced after LDFR. In addition, to make the learnt low-rank subspaces more powerful for feature recovery, we design a fusion strategy to obtain a generalized subspace, which averages over all learnt sub-spaces in each LDFR layer, so that the convolutional feature maps in test phase can be recovered effectively via low-rank embedding. Extensive results on several image datasets show that existing CNNs-based models equipped with our LDFR layer can obtain better performance.

关键词： Training Image recognition Convolution Conferences Image representation data mining Convolutional neural networks

来源：评论

学校读者我要写书评

暂无评论

Size-invariance matters: rethinking metrics and losses for imbalanced multi-object salient object detection 24

Size-invariance matters: rethinking metrics and losses for i...

引用

Proceedings of the 41st International Conference on Machine Learning

作者： Feiran Li Qianqian Xu Shilong Bao Zhiyong Yang Runmin Cong Xiaochun Cao Qingming Huang Institute of Information Engineering Chinese Academy of Sciences Beijing China and School of Cyber Security University of Chinese Academy of Sciences Beijing China Key Laboratory of Intelligent Information Processing Institute of Computing Technology Chinese Academy of Sciences Beijing China School of Computer Science and Technology University of Chinese Academy of Sciences Beijing China Institute of Information Science Beijing Jiaotong University Beijing China and School of Control Science and Engineering Shandong University Jinan China and Key Laboratory of Machine Intelligence and System Control Ministry of Education Jinan China School of Cyber Science and Tech. Shenzhen Campus Sun Yat-sen University School of Computer Science and Technology University of Chinese Academy of Sciences Beijing China and Key Laboratory of Intelligent Information Processing Institute of Computing Technology Chinese Academy of Sciences Beijing China and Key Laboratory of Big Data Mining and Knowledge Management Chinese Academy of Sciences Beijing China

This paper explores the size-invariance of evaluation metrics in Salient Object Detection (SOD), especially when multiple targets of diverse sizes co-exist in the same image. We observe that current metrics are size-sensitive, where larger objects are focused, and smaller ones tend to be ignored. We argue that the evaluation should be size-invariant because bias based on size is unjustified without additional semantic information. In pursuit of this, we propose a generic approach that evaluates each salient object separately and then combines the results, effectively alleviating the imbalance. We further develop an optimization framework tailored to this goal, achieving considerable improvements in detecting objects of different sizes. Theoretically, we provide evidence supporting the validity of our new metrics and present the generalization analysis of SOD. Extensive experiments demonstrate the effectiveness of our method. The code is available at https://***/Ferry-Li/SI-SOD.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Large language models illuminate a progressive pathway to artificial intelligent healthcare assistant

Medicine Plus

引用

Medicine Plus 2024年第2期1卷 102-124页

作者： Mingze Yuan Peng Bao Jiajia Yuan Yunhao Shen Zifan Chen Yi Xie Jie Zhao Quanzheng Li Yang Chen Li Zhang Lin Shen Bin Dong Center for Data Science Peking UniversityBeijing 100871China Department of Gastrointestinal Oncology Key Laboratory of Carcinogenesis and Translational Research(Ministry of Education)Peking University Cancer Hospital and Institute Beijing 100142China National Engineering Laboratory for Big Data Analysis and Applications Peking UniversityBeijing 100871China Beijing International Center for Mathematical Research Peking UniversityBeijing 100871China Center for Machine Learning Research Peking University Beijing 100871China National Biomedical Imaging Center Peking UniversityBeijing 100871China Peking University Changsha Institute for Computing and Digital Economy Changsha 410205China Massachusetts General Hospital Boston MA 02114-2696USA Harvard Medical School BostonMA 02115USA

With the rapid development of artificial intelligence,large language models(LLMs)have shown promising capabilities in mimicking human-level language comprehen-sion and *** has sparked significant interest in applying LLMs to enhance various aspects of healthcare,ranging from medical education to clinical decision ***,medicine involves multifaceted data modalities and nuanced reasoning skills,presenting challenges for integrating *** review introduces the fundamental applications of general-purpose and specialized LLMs,demon-strating their utilities in knowledge retrieval,research support,clinical workflow automation,and diagnostic *** the inherent multimodality of medicine,the review emphasizes the multimodal LLMs and discusses their ability to process diverse data types like medical imaging and electronic health records to augment diagnostic *** address LLMs'limitations regarding personalization and complex clinical reasoning,the review further explores the emerging develop-ment of LLM-powered autonomous agents for ***,it summarizes the evaluation methodologies for assessing LLMs'reliability and safety in medical *** have transformative potential in medicine;however,there is a pivotal need for continuous optimizations and ethical oversight before these models can be effectively integrated into clinical practice.

关键词： Large language models Artificial intelligence Medicine Healthcare assistant Prompt engineering In-context learning

来源：评论

学校读者我要写书评

暂无评论

Mobility-aware Seamless Service Migration and Resource Allocation in Multi-edge IoV Systems

arXiv

引用

arXiv 2025年

作者： Chen, Zheyi Huang, Sijin Min, Geyong Ning, Zhaolong Li, Jie Zhang, Yan College of Computer and Data Science Fuzhou University Fuzhou350116 China Engineering Research Center of Big Data Intelligence Ministry of Education Fujian Key Laboratory of Network Fuzhou350002 China Computing and Intelligent Information Processing [Fuzhou University Fuzhou350116 China Department of Computer Science Faculty of Environment Science and Economy University of Exeter ExeterEX4 4QF United Kingdom School of Communications and Information Engineering Chongqing University of Posts and Telecommunications Chongqing400065 China Department of Computer Science and Engineering Shanghai Jiao Tong University Shanghai200240 China Department of Informatics University of Oslo Oslo0316 Norway

Mobile Edge Computing (MEC) offers low-latency and high-bandwidth support for Internet-of-Vehicles (IoV) applications. However, due to high vehicle mobility and finite communication coverage of base stations, it is hard to maintain uninterrupted and high-quality services without proper service migration among MEC servers. Existing solutions commonly rely on prior knowledge and rarely consider efficient resource allocation during the service migration process, making it hard to reach optimal performance in dynamic IoV environments. To address these important challenges, we propose SR-CL, a novel mobility-aware seamless Service migration and Resource allocation framework via Convex-optimization-enabled deep reinforcement Learning in multi-edge IoV systems. First, we decouple the Mixed Integer Nonlinear Programming (MINLP) problem of service migration and resource allocation into two sub-problems. Next, we design a new actor-critic-based asynchronous-update deep reinforcement learning method to handle service migration, where the delayed-update actor makes migration decisions and the one-step-update critic evaluates the decisions to guide the policy update. Notably, we theoretically derive the optimal resource allocation with convex optimization for each MEC server, thereby further improving system performance. Using the real-world datasets of vehicle trajectories and testbed, extensive experiments are conducted to verify the effectiveness of the proposed SR-CL. Compared to benchmark methods, the SR-CL achieves superior convergence and delay performance under various scenarios. Copyright © 2025, The Authors. All rights reserved.

关键词： Convex optimization

来源：评论

学校读者我要写书评

暂无评论

Subject Event Extraction from Chinese Court Verdict Case via Frame-filling

Subject Event Extraction from Chinese Court Verdict Case via...

引用

IEEE International Conference on big knowledge (ICBK)

作者： Gongqing Wu Shengjie Hu Yinghuan Wang Zan Zhang Xianyu Bao Key Laboratory of Knowledge Engineering with Big Data of Ministry of Education Hefei University of Technology Hefei China Shenzhen Academy of Inspection and Quarantine Shenzhen China

ISBN: (数字)9781728181561

ISBN: (纸本)9781728181578

At present, the query and acquisition of the fragmented knowledge in Chinese court verdicts mainly adopt the class case retrieval method based on the search engine and the rough extraction method for a part of the data in court verdicts. These traditional methods cannot structurally extract fragmented knowledge in Chinese court verdicts and meet the needs of people for the follow-up analysis of court verdicts. Thus, in this paper, we present a structured subject event extraction method (SEE) for Chinese court verdict cases combining with techniques of event extraction (EE) and attribute-value pair extraction (AVPE). Specifically, we provide a subject event representation frame for organizing fragmented knowledge in Chinese court verdict cases. Then, we extract subject events from the unstructured cases based on the trained sequence labeling models and constructed heuristic rules, and fill them into the subject event representation frame in the form of attribute-value pairs (AVPs). The experimental results show that SEE can efficiently and automatically extract subject events from Chinese court verdict cases and visually display them via frame-filling, which promotes the efficiency of people in searching for legal materials and facilitates further research and analysis.

关键词： Feature extraction data mining Labeling Information retrieval Semantics Machine learning knowledge engineering

来源：评论

学校读者我要写书评

暂无评论

Realization of asymmetric near-field focusing by transmissive janus metasurface

引用

Physics Letters A 2025年 553卷

作者： Jie Wang Le Jiang Na Kou Shixing Yu Key Laboratory of Micro-Nano-Electronics and Software Technology of Guizhou Province Engineering Research Center of Power Semiconductor Device Reliability of the Ministry of Education College of Big Data and Information Engineering Guizhou University Guiyang 550025 China

In this paper, a novel transmission Janus metasurface is proposed to achieve asymmetric near-field electromagnetic (EM) focusing with a focusing efficiency of up to 32.38 %. When the incident wave propagates along the forward direction, the EM wave will be concentrated on two foci. While along the reverse direction, there is a single focus. A polarization conversion unit with high transmission is designed, and its cross-polarization transmission amplitude and polarization conversion rate (PCR) are as high as 96.65 % and 94 %, respectively. In addition, the split ring (SR) structure of the unit can be adjusted to achieve 360° full cross-polarization transmission phase. Both simulation and experimental results show that the proposed Janus metasurface can effectively realize asymmetric near-field EM focusing.

关键词： Light transmission

来源：评论

学校读者我要写书评

暂无评论

A residual attention-based privacy-preserving biometrics model of transcriptome prediction from genome

A residual attention-based privacy-preserving biometrics mod...

引用

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

作者： Cheng Tian Song Liu Jinbao Li Guangchen Wang Luyue Kong Key Laboratory of Computing Power Network and Information Security Ministry of Education Shandong Computer Science Center Qilu University of Technology (Shandong Academy of Sciences) Jinan China Shandong Engineering Research Center of Big Data Applied Technology Faculty of Computer Science and Technology 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 Department of Medicine Shandong Medical College Jinan China

ISBN: (数字)9798350381993

ISBN: (纸本)9798350382006

Transcriptome prediction from genetic variation data is an important task in the privacy-preserving and biometrics field, which can better protect genomic data and achieve biometric recognition through transcriptome. Many transcriptome prediction methods have achieved good accuracy from genetic variation data. However, these traditional transcriptome prediction methods have the problems of linear assumption, overfitting, expose personal privacy, and extensive manual optimization. To solve these shortcomings, we propose an attention-based transcriptome prediction model from genetic variation named RATPM that improves the accuracy of transcriptome prediction and protects participant genomic data. In RATPM, we introduce and improve the deep learning model with multi-head self-attention into the transcriptome prediction stage of Predixcan, which uncovers the non-linear relationship between genetic variation and transcriptome. Moreover, we introduce a residual attention module to generate attention-aware features and extract more accurate features at different levels from genetic variation. Furthermore, we introduce the BERT pre-training module to encode genetic variation fully utilizing their contextual information. Our research enables scientific institutions to publish only predicted transcriptomic data for biometric purposes, thus protecting the genomic information of the subjects. Finally, we evaluated our model on the 1000 Genomes and Geuvadis projects datasets to compare with other baseline models.

关键词： Privacy Biometrics (access control) Biological system modeling Genomics Predictive models Feature extraction Gene expression

来源：评论

学校读者我要写书评

暂无评论

Tcgfusion: A Network for Pet-Mri Fusion Based on Gan and Transformer

SSRN

引用

SSRN 2022年

作者： Fan, Chao Chen, Zhixiang Lin, Hao Wang, Xiao School of Artificial Intelligence and Big Data Henan University of Technology Henan Province Zhengzhou City China School of Information Science and Engineering Henan University of Technology Henan Province Zhengzhou City China Key Laboratory of Grain Information Processing and Control Ministry of Education Henan Province Zhengzhou City China

We provide an end-to-end unsupervised training model called TCGFusion: a network for PET-MRI fusion based on GAN and transformer. We set the generator to a dual-path layout to assure the gathering of both global and detailed image information. To guarantee the coarse scale picture extraction and prevent the high computational cost, the global path T-Path utilizes Grid-former (a residual grid transformer structure). The detailed path C-Path is DenseNet, and its multi-cascade structure captures image details well. Additionally, we set up a dual adversarial mechanism between the fused image and the source image, creating a dual discriminator to determine the distribution of structural similarity between the fused result and the source image, and using patch-SSIM to reinforce the semantic constraints between them and promote the image details. According to our extensive studies on public datasets, medical image fusion demonstrate the superiority of our TCGFusion compared to the state-of-the-art image fusion algorithms. © 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

Relation extraction with proactive domain adaptation strategy 11

Relation extraction with proactive domain adaptation strateg...

引用

11th IEEE International Conference on knowledge Graph, ICKG 2020

作者： Zhong, Lingfeng Zhu, Yi Key Laboratory of Knowledge Engineering with Big Data (Heifei Unversity of Technology) Ministry of Education Heifei China School of Computer Science and Information Engineering Heifei University of Technology Heifei China Yangzhou University School of Computer Science and Technology Yangzhou China

ISBN: (数字)9781728181561

ISBN: (纸本)9781728181578

Relation extraction is an important information extraction task in many Natural Language Processing (NLP) applications, such as automatic knowledge graph construction, question answering, sentiment analysis, etc. However, relation extraction suffers from inappropriate associations between entities when the background knowledge of corpus is insufficiency. Despite the preprocessed external word vector bases can ease this problem, how to find a single word vector base as domain knowledge that contains all the required knowledge features is a huge challenge, and relation extraction with background knowledge is still open to further optimization. To address this problem, in this paper, we propose Relation Extraction method with Proactive Domain Adaptation Strategy (REPDAS for short) to introduce more knowledge features from different knowledge bases. More specifically, firstly, a convolutional network with a parameter-sharing layer is introduced for relation extraction, and word seeds that are important to relational feature exploitation are proactively picked by an attention mechanism during training. Secondly, the proactively-chosen word seeds and the previous parameter-sharing layer are utilized to establish a map between different domains. Our proposed method selectively avails both background knowledge and contextual features for relation extraction by incorporating the convolutional neural network with the proactively domain adaptation strategy. Experiments show that our method effectively enhances the performance of relation extraction compared with other baselines. © 2020 IEEE.

关键词： Domain Adaptation knowledge Graph Relation Extraction

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：