检索结果-内蒙古大学图书馆

Attention Guided Enhancement Network for Weakly Supervised Semantic Segmentation

Chinese Journal of Electronics 2023年第4期32卷 896-907页

作者： ZHANG Zhe WANG Bilin YU Zhezhou ZHAO Fengzhi College of Computer Science and Technology Jilin University Key Laboratory for Symbol Computation and Knowledge Engineering of National Education Ministry

Weakly supervised semantic segmentation using only image-level labels is critical since it alleviates the need for expensive pixel-level labels. Most cuttingedge methods adopt two-step solutions that learn to produce pseudo-ground-truth using only image-level labels and then train off-the-shelf fully supervised semantic segmentation network with these pseudo labels. Although these methods have made significant progress, they also increase the complexity of the model and training. In this paper, we propose a one-step approach for weakly supervised image semantic segmentation—attention guided enhancement network(AGEN), which produces pseudopixel-level labels under the supervision of image-level labels and trains the network to generate segmentation masks in an end-to-end manner. Particularly, we employ class activation maps(CAM) produced by different layers of the classification branch to guide the segmentation branch to learn spatial and semantic ***, the CAM produced by the lower layer can capture the complete object region but with many ***, the self-attention module is proposed to enhance object regions adaptively and suppress irrelevant object regions, further boosting the segmentation *** on the Pascal VOC 2012 dataset demonstrate that AGEN outperforms alternative state-of-the-art weakly supervised semantic segmentation methods exclusively relying on image-level labels.

关键词： Training Annotations Semantic segmentation Scalability Semantics Benchmark testing Boosting

来源：评论

学校读者我要写书评

暂无评论

Recognizing event in short text based on decision tree

Recognizing event in short text based on decision tree

引用

作者： Lu, Jing Ya Zuo, Wan Li Zhu, Liang College of Computer Science and Technology Jilin University Changchun 130012 China Key Laboratory of Symbolic Computation and Knowledge Engineering Ministry of Education of China China

ISBN: (纸本)9783038351399

Mining newsworthy events from a large number of microblogging information is not only the primary problem that several big microblogging websites need to solve, but also a new research field in micro-information age. For now, a lot of study about even recognizing has been made at home and abroad, but relatively rarely contrapose short text(microblogging message). The paper considers newsworthy event recognizing in short text as classification problem, utilizes the decision tree classification algorithm in data mining, sufficiently mines features of event in short text, and then recognizes the newsworthy event in microblogging. In the last, we verify the effect of the model. © (2014) Trans Tech Publications, Switzerland.

关键词： Data mining

来源：评论

学校读者我要写书评

暂无评论

A model for representing topological relations between regions with holes

A model for representing topological relations between regio...

引用

1st International Conference on Information Science and engineering, ICISE2009

作者： Huo, Linlin Ouyang, Jihong Liu, Dayou College of Computer Science and Technology Jilin University China Key Laboratory of Symbolic Computation and Knowledge Engineering of Ministry of Education Jilin University Changchun China

ISBN: (纸本)9780769538877

This paper proposes a unified model - D9-intersection model to represent topological relations between regions with holes. D9-intersection model can describe simple regional relations as accurately as 9-intersection model. When holes are allowed, D9-intersection model can distinguish relations that 9 - intersection could not and then be more expressive than 9-intersection model. In addition, we present the reasoning method based on D9-intersection model restricting to regions with at most one hole. ©2009 IEEE.

关键词： Topology

来源：评论

学校读者我要写书评

暂无评论

A FAST AND SCALABLE SUPERVISED TOPIC MODEL USING STOCHASTIC VARIATIONAL INFERENCE AND MAPREDUCE 5

A FAST AND SCALABLE SUPERVISED TOPIC MODEL USING STOCHASTIC ...

引用

2016 5th IEEE International Conference on Network Infrastructure and Digital Content(IC-NIDC 2016)

作者： Wenzhuo Song Bo Yang Xuehua Zhao Fei Li Jilin University Key Laboratory of Symbolic Computation and Knowledge Engineering of Ministry of Education Jilin University School of Digital Media Shenzhen Institute of Information Technology George Mason University

ISBN: (纸本)9781509012473

An important and widespread topic in cloud computing is text *** often use topic model which is a popular and effective technology to deal with related *** all the topic models,sLDA is acknowledged as a popular supervised topic model,which adds a response variable or category label with each document,so that the model can uncover the latent structure of a text dataset as well as retains the predictive power for supervised ***,sLDA needs to process all the documents at each iteration in the training *** the size of dataset increases to the volume that one node cannot deal with,sLDA will no longer be *** this paper we propose a novel model named *** which extends sLDA with stochastic variational inference(SVI) and *** can reduce the computational burden of sLDA and MapReduce extends the algorithm with *** makes the training become more efficient and the training method can be easily implemented in a large computer cluster or cloud *** results show that our approach has an efficient training process,and similar accuracy with sLDA.

关键词： Text classification MapReduce Variational inference Topic modeling

来源：评论

学校读者我要写书评

暂无评论

Hybrid Parameter Update: Alleviating Imbalance Impacts for Distributed Deep Learning 24

Hybrid Parameter Update: Alleviating Imbalance Impacts for D...

引用

24th IEEE International Conference on High Performance Computing and Communications, 8th IEEE International Conference on Data Science and Systems, 20th IEEE International Conference on Smart City and 8th IEEE International Conference on Dependability in Sensor, Cloud and Big Data Systems and Application, HPCC/DSS/SmartCity/DependSys 2022

作者： Li, Hongliang Xu, Dong Xu, Zhewen Li, Xiang College of Computer Science and Technology Jilin University Changchun130012 China Key Laboratory of Symbolic Computation and Knowledge Engineering of the Ministry of Education Changchun China

ISBN: (纸本)9798350319934

Nowadays, data parallelism has been widely applied to train large datasets on distributed deep learning clusters, but it has suffered from costly global parameter updates at batch barriers. Performance imbalance among worker instances, introduced by uneven workload partitioning or biased resource allocation, can cause straggly workers, which can lead to severe impacts on both training speed and result accuracy. This paper studies the issue focusing on the tradeoff between training speed and result accuracy. We propose Cooperate Grouping Parallel (CGP), a hybrid parameter update solution that allows the flexibility of both synchronous and asynchronous update schemes. We introduce a novel Cooperate Worker Grouping Problem (CWGP) that seeks a task grouping configuration that leads to maximum model accuracy and holds customized training speed guarantees. We propose an evolution-based Pareto local searching algorithm to compute efficient worker grouping configurations. Comprehensive evaluation results are presented to demonstrate the effectiveness of CGP under both persistent and fluctuant imbalances. The proposed method alleviates the imbalance impacts without introducing extra adjustment over-heads. © 2022 IEEE.

关键词： Large dataset

来源：评论

学校读者我要写书评

暂无评论

Superpixels Based Interactive Image Segmentation Algorithm

Superpixels Based Interactive Image Segmentation Algorithm

引用

2013 International Conference on Information,Business and Education Technology(ICIBET 2013)

作者： LONG Jian-wu SHEN Xuan-jing ZANG Hui CHEN Hai-peng College of Computer Science and Technology Jilin University Key Laboratory of Symbolic Computation and Knowledge Engineering of Ministry of Education Jilin University

ISBN: (纸本)9781629932101

A superpixels based interactive image segmentation algorithm is proposed in this paper. Firstly the initial segmentation is obtained by MeanShift algorithm, and then a graph is built using pre-segmented regions as nodes, finally min-cut/maxflow algorithm is implemented for global solution. In this process, each region is represented by a color histogram and Bhattacharyya coefficient is chosen to calculate the similarity between any two regions. Extensive experiments are performed and the results show that the presented algorithm obtains much more satisfactory segmentation results with less user interaction and less comsuming time than MSRM algorithm.

关键词： interactive image segmentation graph cut mean shift

来源：评论

学校读者我要写书评

暂无评论

An unmanned aerial vehicle pose estimation system guided by desired shot 2

An unmanned aerial vehicle pose estimation system guided by ...

引用

2nd IEEE International Conference on Automation, Electronics and Electrical engineering, AUTEEE 2019

作者： Dou, Xinglei Ding, Qijian Du, Qiao Yang, Min Huo, Yuzhou Wang, Xin College of Software Engineering Jilin University Changchun China Key Laboratory of Symbolic Computation and Knowledge Engineer Ministry of Education Jilin University Changchun China

ISBN: (纸本)9781728150291

Unmanned aerial vehicles (UAVs) are widely used in aerial photography nowadays for their strong maneuverability, good image quality and high cost performance, while they have limited battery capacity and difficulty in operation. It is difficult to reach the ideal pose and get the desired shot by manual manipulation in a short time. To solve these problems, an UAV pose estimation system guided by desired shot is constructed. Either a sequence of images or a video is taken as input. The user interacts with the system to express the desired shot. The 3D-reconstruction is done by Structure from Motion (SfM). Then the Perspective-n-Point (PnP) problem is solved to estimate the ideal pose of the UAV. The experimental results proves that the system is effective and valid. © 2019 IEEE.

关键词： Aerial photography

来源：评论

学校读者我要写书评

暂无评论

A Novel Method for Prediction of Protein Domain Using Distance-Based Maximal Entropy

引用

Journal of Bionic engineering 2008年第3期5卷 215-223页

作者： Shu-xue Zou Yan-xin Huang Yan Wang Chun-guang Zhou Key Laboratory of Symbol Computation and Knowledge Engineering of Ministry of Education College of Computer Science and Technology Jilin University Changchun 130012 P. R. China

Detecting the boundaries of protein domains is an important and challenging task in both experimental and computational structural biology. In this paper, a promising method for detecting the domain structure of a protein from sequence information alone is presented. The method is based on analyzing multiple sequence alignments derived from a database search. Multiple measures are defined to quantify the domain information content of each position along the sequence. Then they are combined into a single predictor using support vector machine. What is more important, the domain detection is first taken as an imbal- anced data learning problem. A novel undersampling method is proposed on distance-based maximal entropy in the feature space of Support Vector Machine （SVM）. The overall precision is about 80%. Simulation results demonstrate that the method can help not only in predicting the complete 3D structure of a protein but also in the machine learning system on general im- balanced datasets.

关键词： protein domain boundary SVM imbalanced data learning distance-based maximal entropy

来源：评论

学校读者我要写书评

暂无评论

Adaptive Image Thresholding by Background Subtraction

Adaptive Image Thresholding by Background Subtraction

引用

2013 International Conference on Information,Business and Education Technology(ICIBET 2013)

ISBN: (纸本)9781629932101

In this paper, an adaptive image thresholding algorithm is proposed for thresholding images with uneven illumination. Firstly, a Gaussian scale space, which is produced from the convolution of a two-dimensional Gaussian function with an input image, is used to estimate the background image. Followed by background subtraction, the objective image can be easily obtained to eliminate interference of uneven illumination. Thirdly, to highlight those darker objects, gamma correction is employed to enhance the objective image. Finally, the thresholding result is extracted easily using the global valley-emphasis Otsu method. The experimental results show that the introduced method yields satisfactory visual quality.

关键词： thresholding background estimation background subtraction

来源：评论

学校读者我要写书评

暂无评论

SMRI: A New Method for siRNA Design for COVID-19 Therapy

引用

Journal of Computer Science & Technology 2022年第4期37卷 991-1002页

作者： Meng-Xin Chen Xiao-Dong Zhu Hao Zhang Zhen Liu Yuan-Ning Liu College of Software Jilin UniversityChangchun 130012China Key Laboratory of Symbolic Computation and Knowledge Engineering of the Ministry of Education Jilin UniversityChangchun 130012China College of Computer Science and Technology Jilin UniversityChangchun 130012China Graduate School of Engineering Nagasaki Institute of Applied ScienceNagasaki 851-0193Japan

First discovered in Wuhan, China, SARS-CoV-2 is a highly pathogenic novel coronavirus, which rapidly spreads globally and becomes a pandemic with no vaccine and limited distinctive clinical drugs available till March 13th, 2020. Ribonucleic Acid interference (RNAi) technology, a gene-silencing technology that targets mRNA, can cause damage to RNA viruses effectively. Here, we report a new efficient small interfering RNA (siRNA) design method named Simple Multiple Rules Intelligent Method (SMRI) to propose a new solution of the treatment of COVID-19. To be specific, this study proposes a new model named Base Preference and Thermodynamic Characteristic model (BPTC model) indicating the siRNA silencing efficiency and a new index named siRNA Extended Rules index (SER index) based on the BPTC model to screen high-efficiency siRNAs and filter out the siRNAs that are difficult to take effect or synthesize as a part of the SMRI method, which is more robust and efficient than the traditional statistical indicators under the same circumstances. Besides, to silence the spike protein of SARS-CoV-2 to invade cells, this study further puts forward the SMRI method to search candidate high-efficiency siRNAs on SARS-CoV-2's S gene. This study is one of the early studies applying RNAi therapy to the COVID-19 treatment. According to the analysis, the average value of predicted interference efficiency of the candidate siRNAs designed by the SMRI method is comparable to that of the mainstream siRNA design algorithms. Moreover, the SMRI method ensures that the designed siRNAs have more than three base mismatches with human genes, thus avoiding silencing normal human genes. This is not considered by other mainstream methods, thereby the five candidate high-efficiency siRNAs which are easy to take effect or synthesize and much safer for human body are obtained by our SMRI method, which provide a new safer, small dosage and long efficacy solution for the treatment of COVID-19.

关键词： COVID-19 SARS-CoV-2 RibonucleicAcid interference

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：