检索结果-内蒙古大学图书馆

3D Neuron Reconstruction in Tangled Neuronal Image With Deep Networks

IEEE TRANSACTIONS ON MEDICAL IMAGING 2020年第2期39卷 425-435页

作者： Li, Qiufu Shen, Linlin Shenzhen Univ Coll Comp Sci & Software Engn Comp Vis Inst Shenzhen 518060 Peoples R China Shenzhen Univ Natl Engn Lab Big Data Syst Comp Technol Shenzhen 518060 Peoples R China Shenzhen Univ Shenzhen Inst Artificial Intelligence & Robot Soc Shenzhen 518060 Peoples R China Shenzhen Univ Guangdong Key Lab Intelligent Informat Proc Shenzhen 518060 Peoples R China

Digital reconstruction or tracing of 3D neuron is essential for understanding the brain functions. While existing automatic tracing algorithms work well for the clean neuronal image with a single neuron, they are not robust to trace the neuron surrounded by nerve fibers. We propose a 3D U-Net-based network, namely 3D U-Net Plus, to segment the neuron from the surrounding fibers before the application of tracing algorithms. All the images in bigNeuron, the biggest available neuronal image dataset, contain clean neurons with no interference of nerve fibers, which are not practical to train the segmentation network. Based upon the bigNeuron images, we synthesize a SYNethic TAngled NEuronal Image dataset (SYNTANEI) to train the proposed network, by fusing the neurons with extracted nerve fibers. Due to the adoption of dropout, convolution and Spatial Pyramid Pooling (ASPP), experimental results on the synthetic and real tangled neuronal images show that the proposed 3D U-Net Plus network achieved very promising segmentation results. The neurons reconstructed by the tracing algorithm using the segmentation result match significantly better with the ground truth than that using the original images.

关键词： Neuron reconstruction image segmentation SYNTANEI 3D U-Net Plus

来源：评论

学校读者我要写书评

暂无评论

Single-path Bit Sharing for Automatic Loss-aware Model Compression

arXiv

引用

arXiv 2021年

作者： Liu, Jing Zhuang, Bohan Chen, Peng Shen, Chunhua Cai, Jianfei Tan, Mingkui The School of Software Engineering South China University of Technology China The Key Laboratory of Big Data and Intelligent Robot South China University of Technology Ministry of Education China The Pazhou Laboratory Guangzhou China The School of Computer Science the University of Adelaide Australia The Faculty of Information Technology Monash University Australia The College of Computer Science and Technology Zhejiang University Hangzhou China

Network pruning and quantization are proven to be effective ways for deep model compression. To obtain a highly compact model, most methods first perform network pruning and then conduct quantization based on the pruned model. However, this strategy may ignore that the pruning and quantization would affect each other and thus performing them separately may lead to sub-optimal performance. To address this, performing pruning and quantization jointly is essential. Nevertheless, how to make a trade-off between pruning and quantization is non-trivial. Moreover, existing compression methods often rely on some pre-defined compression configurations (i.e., pruning rates or bitwidths). Some attempts have been made to search for optimal configurations, which however may take unbearable optimization cost. To address these issues, we devise a simple yet effective method named Single-path Bit Sharing (SBS) for automatic loss-aware model compression. To this end, we consider the network pruning as a special case of quantization and provide a unified view for model pruning and quantization. We then introduce a single-path model to encode all candidate compression configurations, where a high bitwidth value will be decomposed into the sum of a lowest bitwidth value and a series of re-assignment offsets. Relying on the single-path model, we introduce learnable binary gates to encode the choice of configurations and learn the binary gates and model parameters jointly. More importantly, the configuration search problem can be transformed into a subset selection problem, which helps to significantly reduce the optimization difficulty and computation cost. In this way, the compression configurations of each layer and the trade-off between pruning and quantization can be automatically determined. Extensive experiments on CIFAR-100 and ImageNet show that SBS significantly reduces computation cost while achieving promising performance. For example, our SBS compressed MobileNetV2 achieves

关键词： Encoding (symbols)

来源：评论

学校读者我要写书评

暂无评论

An intelligent Resource Scheduling Method with Edge Channel Deployment for BPM

An Intelligent Resource Scheduling Method with Edge Channel ...

引用

Symposia and Workshops on Ubiquitous, Autonomic and Trusted Computing, UIC-ATC

作者： Bowen Liu Wanchun Dou Xiaokang Zhou Xuyun Zhang Lianyong Qi Fei Dai Chaochao Chen State Key Laboratory for Novel Software Technology Nanjing University Nanjing China Faculty of Data Science Shiga University Hikone Japan Department of Computing Macquarie University Sydney Australia College of Computer and Software China University of Petroleum (East China) Qingdao China College of Big Data and Intelligent Engineering Southwest Forestry University Kunming China College of Computer Science and Technology Zhejiang University Hangzhou China

Edge computing is a novel computing paradigm that offers kinds of resources at the network edge. In edge computing, terminal users are connected to edge servers via the wireless network and there are various channels in each wireless link. These wireless channels are limited resource while different channel has different cost and service ability. The dynamic changes of users’ status make it harder to find an appropriate method to satisfy the BPM requirements of channel deployment. With this observation, it is a tricky challenge to make a trade-off between the system cost(rental price) and the service ability(number of users). In view of this challenge, an intelligent resource scheduling method, named EdgeIRS, is proposed in this paper. In the technical sense, the EdgeIRS method can accommodate most users at the edge with a minimum cost of deploying channel resources in an online way. Its performance is analyzed theoretically and the experiments verify the superiority of the method.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Meet Changes with Constancy: Learning Invariance in Multi-Source Translation 28

Meet Changes with Constancy: Learning Invariance in Multi-So...

引用

28th International Conference on Computational Linguistics, COLING 2020

作者： Liu, Jianfeng Luo, Ling Ao, Xiang Song, Yan Xu, Haoran Ye, Jian Institute of Computing Technology Chinese Academy of Sciences Beijing China University of Chinese Academy of Sciences China Beijing Key Laboratory of Mobile Computing and Pervasive Device China Key Laboratory of Intelligent Information Processing Chinese Academy of Sciences China The Chinese University of HongKong Shenzhen China Shenzhen Research Institute of Big Data China

ISBN: (纸本)9781952148279

Multi-source neural machine translation aims to translate from parallel sources of information (e.g. languages, images, etc.) to a single target language, which has shown better performance than most one-to-one systems. Despite the remarkable success of existing models, they usually neglect the fact that multiple source inputs may have inconsistencies. Such differences might bring noise to the task and limit the performance of existing multi-source NMT approaches due to their indiscriminate usage of input sources for target word predictions. In this paper, we attempt to leverage the potential complementary information among distinct sources and alleviate the occasional conflicts of them. To accomplish that, we propose a source invariance network to learn the invariant information of parallel sources. Such network can be easily integrated with multi-encoder based multi-source NMT methods (e.g. multi-encoder RNN and transformer) to enhance the translation results. Extensive experiments on two multi-source translation tasks demonstrate that the proposed approach not only achieves clear gains in translation quality but also captures implicit invariance between different sources. © 2020 COLING 2020 - 28th International Conference on Computational Linguistics, Proceedings of the Conference. All rights reserved.

关键词： Signal encoding

来源：评论

学校读者我要写书评

暂无评论

Non-invasive estimation of pulmonary hypertension and clinical deterioration risk in pediatric congenital heart disease:Development and validation of predictive tools

引用

Chinese Medical Journal 2024年第11期137卷 1384-1386页

作者： Ting Wang Dansha Zhou Yuqin Chen Suhua Kuang Yue Xing Qijian Yi Zhengxia Pan Weibin Xu Jiao Rao Yunqi Liu Guoliang Lu Ziying Lin Xiang Li Yi Xie Yulong Wu Peng An Xiaoxiao Deng Jiayue He Jiayi Xie Chenxi Li Gang Geng Daiyin Tian Enmei Liu Jingsi Huang Zhou Fu Jian Wang Department of Respiratory Chongqing Higher Institution Engineering Research Center of Children’s Medical Big Data Intelligent ApplicationNational Clinical Research Center for Child Health and DisordersMinistry of Education Key Laboratory of Child Development and DisordersChildren’s Hospital of Chongqing Medical UniversityChongqing 400014China State Key Laboratory of Respiratory Diseases National Center for Respiratory MedicineGuangdong Key Laboratory of Vascular DiseasesNational Clinical Research Center for Respiratory DiseasesGuangzhou Institute of Respiratory Healththe First Affiliated Hospital of Guangzhou Medical UniversityGuangzhou Medical UniversityGuangzhouGuangdong 510120China Department of Cardiac Surgery The First Affiliated Hospital of Guangzhou Medical UniversityGuangzhou Medical UniversityGuangzhouGuangdong 510120China Department of Cardiovascular Medicine Children’s Hospital of Chongqing Medical University National Clinical Research Center for Child Health and DisordersMinistry of Education Key Laboratory of Child Development and DisordersChildren’s Hospital of Chongqing Medical UniversityChongqing 400014China Department of Thoracic and Cardiac Surgery Children’s Hospital of Chongqing Medical University National Clinical Research Center for Child Health and DisordersMinistry of Education Key Laboratory of Child Development and DisordersChildren’s Hospital of Chongqing Medical UniversityChongqing 400014China Department of Cardiac Center of Guangdong Women and Children Hospital Guangzhou GuangzhouGuangdong 511400China Department of Guangzhou Laboratory Guangzhou International Bio IslandGuangzhouGuangdong 510005China

To the Editor:Owing to the heterogeneity of congenital heart disease-associated pulmonary hypertension(CHDPH)disease and the development of the pulmonary vascular system in pediatric patients,the management of CHD-PH in children is signicantly different from that in adults.[1]Early identication and intervention of CHD-PH are of great signicance for disease management in children with CHD,and non-invasive,accurate clinical tools are urgently needed to predict PH risk in children with ***,the applicability of the current risk-scoring system to pediatric CHD-PH remains ***,there are presently no user-friendly,non-invasive online tools available for predicting CHD-PH,and there is a scarcity of related studies in Asian *** study aimed to develop and validate the prediction tools for estimating the risk of pulmonary hypertension and clinical deterioration in children with congenital heart disease.

关键词： pediatric congenital hypertension

来源：评论

学校读者我要写书评

暂无评论

Stepdown SLOPE for Controlled Feature Selection

arXiv

引用

arXiv 2023年

作者： Liang, Jingxuan Zhang, Xuelin Chen, Hong Li, Weifu Tang, Xin College of Science Huazhong Agricultural University Wuhan430070 China College of Informatics Huazhong Agricultural University Wuhan430070 China Ping An Property & Casualty Insurance Company Shenzhen China Engineering Research Center of Intelligent Technology for Agriculture Ministry of Education Wuhan430070 China Key Laboratory of Smart Farming for Agricultural Animals Wuhan430070 China Hubei Engineering Technology Research Center of Agricultural Big Data Wuhan430070 China

Sorted L-One Penalized Estimation (SLOPE) has shown the nice theoretical property as well as empirical behavior recently on the false discovery rate (FDR) control of high-dimensional feature selection by adaptively imposing the non-increasing sequence of tuning parameters on the sorted 1 penalties. This paper goes beyond the previous concern limited to the FDR control by considering the stepdown-based SLOPE to control the probability of k or more false rejections (k-FWER) and the false discovery proportion (FDP). Two new SLOPEs, called k-SLOPE and F-SLOPE, are proposed to realize k-FWER and FDP control respectively, where the stepdown procedure is injected into the SLOPE scheme. For the proposed stepdown SLOPEs, we establish their theoretical guarantees on controlling k-FWER and FDP under the orthogonal design setting, and also provide an intuitive guideline for the choice of regularization parameter sequence in much general setting. Empirical evaluations on simulated data validate the effectiveness of our approaches on controlled feature selection and support our theoretical findings. Copyright © 2023, The Authors. All rights reserved.

关键词： Feature Selection

来源：评论

学校读者我要写书评

暂无评论

Dual attention mechanism object tracking algorithm based on Fully-convolutional Siamese network

Dual attention mechanism object tracking algorithm based on ...

引用

International Conference on Networking and Network Applications (NaNA)

作者： Sugang Ma Zixian Zhang Lei Zhang Yanping Chen Xiaobao Yang Lei Pu Zhiqiang Hou School of Computer Science and Technology Xi’an University of Posts and Telecommunications Xi’an Shaanxi China School of Information Engineering Chang’an University Xi’an Shaanxi China Shaanxi Key Laboratory of Network Data Analysis and Intelligent Processing Xi’an Key Laboratory of Big Data and Intelligent Computing Xi’an University of Posts and Telecommunications Xi’an Shaanxi China School of Information and Navigation Air Force Engineering University Xi’an Shaanxi China

In an effort to the problem of insufficient tracking performance of the Fully-convolutional Siamese network (SiamFC) in complex scenarios, a dual attention mechanism object tracking algorithm based on the Fully-convolutional Siamese network is proposed to improve the generalization capability of the tracker by ameliorating the robustness of the template characteristics. Firstly, a global context attention module is appended after the backbone network of SiamFC to ameliorate the power of original feature extraction from two dimensions of spatial and channel. Then, a coordinate attention module is introduced to augment the capability of feature extraction in the channel dimension. Finally, the model of the proposed algorithm is trained on the Got-10k dataset. Five related algorithms are tested on the OTB2015 dataset, the results of experiments manifest that our algorithm outperforms the baseline trackers, the success and precision rate of the proposed algorithm are improved by 3.3% and 6.3%. The average tracking speed is 145FPS, which can demand the requirement of real-time tracking.

关键词： Target tracking Feature extraction Real-time systems Robustness Object tracking Task analysis

来源：评论

学校读者我要写书评

暂无评论

Improving Incremental Learning: A Closer Look at the Softmax Function

SSRN

引用

SSRN 2024年

作者： Zhai, Zheng Zhang, Jiali Wang, Haiyu Wu, Mingxin Yang, Keshun Qiao, Xiaoyan Sun, Qiang Beijing Normal University No.18 Jinfeng Road Guangdong Zhuhai519087 China Shandong Technology and Business University Shandong Yantai China Yantai Key Laboratory of Big Data Modeling and Intelligent Computing Shandong China Immersion Technology and Evaluation Shandong Engineering Research Center Shandong China School of Mathematics Sichuan University Chengdu China College of Liberal Arts and Sciences University of Illinois Urbana-Champaign IL United States Department of Statistical Sciences University of Toronto ON Canada Department of Computer Science University of Toronto ON Canada Department of Statistics and Data Science MBZUAI Abu Dhabi United Arab Emirates

This paper investigates the limitations of the widely adopted softmax cross-entropy loss in incremental learning problems. Specifically, we highlight how the shift-invariant property of this loss function can lead to multiple optimal solutions and imbalanced weights across different tasks, which exacerbates catastrophic forgetting. To address these issues, we propose two key modifications to the objective function: (1) regularizing or replacing the original joint distillation loss with a summation of task-specific distillation losses, and/or (2) utilizing a shift-sensitive prediction loss function, such as the binary cross-entropy loss. Numerical experiments validate the effectiveness of these proposals, demonstrating improved prediction accuracy and a significant reduction in forgetting. © 2024, The Authors. 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

Debiased visual question answering from feature and sample perspectives 21

Debiased visual question answering from feature and sample p...

引用

Proceedings of the 35th International Conference on Neural Information Processing Systems

作者： Zhiquan Wen Guanghui Xu Mingkui Tan Qingyao Wu Qi Wu School of Software Engineering South China University of Technology China and PengCheng Laboratory China School of Software Engineering South China University of Technology China School of Software Engineering South China University of Technology China and Key Laboratory of Big Data and Intelligent Robot (South China University of Technology) Ministry of Education School of Computer Science University of Adelaide

ISBN: (纸本)9781713845393

Visual question answering (VQA) is designed to examine the visual-textual reasoning ability of an intelligent agent. However, recent observations show that many VQA models may only capture the biases between questions and answers in a dataset rather than showing real reasoning abilities. For example, given a question, some VQA models tend to output the answer that occurs frequently in the dataset and ignore the images. To reduce this tendency, existing methods focus on weakening the language bias. Meanwhile, only a few works also consider vision bias implicitly. However, these methods introduce additional annotations or show unsatisfactory performance. Moreover, not all biases are harmful to the models. Some "biases" learnt from datasets represent natural rules of the world and can help limit the range of answers. Thus, how to filter and remove the true negative biases in language and vision modalities remain a major challenge. In this paper, we propose a method named D-VQA to alleviate the above challenges from the feature and sample perspectives. Specifically, from the feature perspective, we build a question-to-answer and vision-to-answer branch to capture the language and vision biases, respectively. Next, we apply two unimodal bias detection modules to explicitly recognise and remove the negative biases. From the sample perspective, we construct two types of negative samples to assist the training of the models, without introducing additional annotations. Extensive experiments on the VQA-CP v2 and VQA v2 datasets demonstrate the effectiveness of our D-VQA method.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Distributed Complementary Binary Quantization for Joint Hash Table Learning

引用

IEEE TRANSACTIONS ON NEURAL NETWORKS AND LEARNING SYSTEMS 2020年第12期31卷 5312-5323页

作者： Liu, Xianglong Fu, Qiang Wang, Deqing Bai, Xiao Wu, Xinyu Tao, Dacheng Beihang Univ State Key Lab Software Dev Environm Beijing 100191 Peoples R China Beihang Univ Beijing Adv Innovat Ctr Big Data Based Precis Med Beijing 100191 Peoples R China Chinese Acad Sci Shenzhen Inst Adv Technol Guangdong Prov Key Lab Robot & Intelligent Syst Shenzhen 100864 Peoples R China Chinese Univ Hong Kong Dept Mech & Automat Engn Hong Kong Peoples R China Univ Sydney Darlington NSW 2008 Australia

Building multiple hash tables serves as a very successful technique for gigantic data indexing, which can simultaneously guarantee both the search accuracy and efficiency. However, most of existing multitable indexing solutions, without informative hash codes and strong table complementarity, largely suffer from the table redundancy. To address the problem, we propose a complementary binary quantization (CBQ) method for jointly learning multiple tables and the corresponding informative hash functions in a centralized way. Based on CBQ, we further design a distributed learning algorithm (D-CBQ) to accelerate the training over the large-scale distributed data set. The proposed (D-)CBQ exploits the power of prototype-based incomplete binary coding to well align the data distributions in the original space and the Hamming space and further utilizes the nature of multi-index search to jointly reduce the quantization loss. (D-)CBQ possesses several attractive properties, including the extensibility for generating long hash codes in the product space and the scalability with linear training time. Extensive experiments on two popular large-scale tasks, including the Euclidean and semantic nearest neighbor search, demonstrate that the proposed (D-)CBQ enjoys efficient computation, informative binary quantization, and strong table complementarity, which together help significantly outperform the state of the arts, with up to 57.76% performance gains relatively.

关键词： Binary quantization distributed learning joint indexing nearest neighbor search prototype-based hashing

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：