检索结果-内蒙古大学图书馆

SODU2-NET: a novel deep learning-based approach for salient object detection utilizing U-NET

PeerJ Computer Science 2025年 11卷

作者： Abbas, Hyder Ren, Shen Bing Asim, Muhammad Hassan, Syeda Iqra El-Latif, Ahmed A. Abd State Key Laboratory of Public Big Data College of Computer Science and Technology Institute for Artificial Intelligence Guizhou University Guizhou Guiyang China School of Computer Science and Engineering Central South University Changsha China EIAS Data Science and Blockchain Laboratory College of Computer and Information Sciences Prince Sultan University Riyadh Saudi Arabia School of Computer Science and Technology Guangdong University of Technology Guangzhou China Department of Electrical and Electronic Engineering British Malaysian Institute Universiti of Kuala Lumpur Kuala Lumpur Malaysia Software Engineering Department Sir Syed University of Engineering and Technology Karachi Pakistan Department of Mathematics and Computer Science Faculty of Science Menoufia University Shebin El-Koom Egypt

Detecting and segmenting salient objects from natural scenes, often referred to as salient object detection, has attracted great interest in computer vision. To address this challenge posed by complex backgrounds in salient object detection is crucial for advancing the field. This article proposes a novel deep learning-based architecture called SODU2-NET (Salient object detection U2-Net) for salient object detection that utilizes the U-NET base structure. This model addresses a gap in previous work that focused primarily on complex backgrounds by employing a densely supervised encoder-decoder network. The proposed SODU2-NET employs sophisticated background subtraction techniques and utilizes advanced deep learning architectures that can discern relevant foreground information when dealing with complex backgrounds. Firstly, an enriched encoder block with full feature fusion (FFF) with atrous spatial pyramid pooling (ASPP) varying dilation rates to efficiently capture multi-scale contextual information, improving salient object detection in complex backgrounds and reducing the loss of information during down-sampling. Secondly the block includes an attention module that refines the decoder, is constructed to enhances the detection of salient objects in complex backgrounds by selectively focusing attention on relevant features. This allows the model to reconstruct detailed and contextually relevant information, which is essential to determining salient objects accurately. Finally, the architecture has been improved by adding a residual block at the encoder end, which is responsible for both saliency prediction and map refinement. The proposed network is designed to learn the transformation between input images and ground truth, enabling accurate segmentation of salient object regions with clear borders and accurate prediction of fine structures. SODU2-NET is demonstrated to have superior performance in five public datasets, including DUTS, SOD, DUT OMRON, HKU-IS, PASCA

关键词： Object detection

来源：评论

学校读者我要写书评

暂无评论

Towards artificial general intelligence via a multimodal foundation model

arXiv

引用

arXiv 2021年

作者： Fei, Nanyi Lu, Zhiwu Gao, Yizhao Yang, Guoxing Huo, Yuqi Wen, Jingyuan Lu, Haoyu Song, Ruihua Gao, Xin Xiang, Tao Sun, Hao Wen, Ji-Rong Gaoling School of Artificial Intelligence Renmin University of China Beijing China Beijing Key Laboratory of Big Data Management and Analysis Methods Beijing China School of Information Renmin University of China Beijing China Computer Electrical and Mathematical Sciences and Engineering Division King Abdullah University of Science and Technology Thuwal Saudi Arabia Department of Electrical and Electronic Engineering University of Surrey Guildford United Kingdom

The fundamental goal of artificial intelligence (AI) is to mimic the core cognitive activities of human. Despite tremendous success in the AI research, most of existing methods have only single-cognitive ability. To overcome this limitation and take a solid step towards artificial general intelligence (AGI), we develop a foundation model pre-trained with huge multimodal data, which can be quickly adapted for various downstream cognitive tasks. To achieve this goal, we propose to pre-train our foundation model by self-supervised learning with weak semantic correlation data crawled from the Internet and show that promising results can be obtained on a wide range of downstream tasks. Particularly, with the developed model-interpretability tools, we demonstrate that strong imagination ability is now possessed by our foundation model. We believe that our work makes a transformative stride towards AGI, from our common practice of "weak or narrow AI" to that of "strong or generalized AI". © 2021, CC BY.

关键词： Semantics

来源：评论

学校读者我要写书评

暂无评论

QuesNet: A unified representation for heterogeneous test questions

arXiv

引用

arXiv 2019年

作者： Yin, Yu Liu, Qi Huang, Zhenya Chen, Enhong Tong, Wei Wang, Shijin Su, Yu Anhui Province Key Laboratory of Big Data Analysis and Application School of Computer Science and Technology School of Data Science University of Science and Technology of China IFLYTEK Research IFLYTEK CO. LTD. State Key Laboratory of Cognitive Intelligence

Understanding learning materials (e.g. test questions) is a crucial issue in online learning systems, which can promote many applications in education domain. Unfortunately, many supervised approaches suffer from the problem of scarce human labeled data, whereas abundant unlabeled resources are highly underutilized. To alleviate this problem, an effective solution is to use pre-trained representations for question understanding. However, existing pretraining methods in NLP area are infeasible to learn test question representations due to several domain-specific characteristics in education. First, questions usually comprise of heterogeneous data including content text, images and side information. Second, there exists both basic linguistic information as well as domain logic and knowledge. To this end, in this paper, we propose a novel pre-training method, namely QuesNet, for comprehensively learning question representations. Specifically, we first design a unified framework to aggregate question information with its heterogeneous inputs into a comprehensive vector. Then we propose a two-level hierarchical pre-training algorithm to learn better understanding of test questions in an unsupervised way. Here, a novel holed language model objective is developed to extract low-level linguistic features, and a domain-oriented objective is proposed to learn high-level logic and knowledge. Moreover,we showthat Ques- Net has good capability of being fine-tuned in many question-based tasks. We conduct extensive experiments on large-scale real-world question data, where the experimental results clearly demonstrate the effectiveness of QuesNet for question understanding as well as its superior applicability. Copyright © 2019, The Authors. All rights reserved.

关键词： Learning systems

来源：评论

学校读者我要写书评

暂无评论

Weakly supervised learning for textbook question answering

TechRxiv

引用

TechRxiv 2021年

作者： Ma, Jie Chai, Qi Huang, Jingyue Liu, Jun You, Yang Zheng, Qinghua National Engineering Lab for Big Data Analytics School of Computer Science and Technology Xi’an Jiaotong University Shaanxi Xi’an710049 China Shaanxi Province Key Laboratory of Satellite and Terrestrial Network Tech. R&D School of Computer Science and Technology Xi’an Jiaotong University Shaanxi Xi’an710049 China The High Performance Computing for Artificial intelligence Lab Department of Computer Science National University of Singapore 117417 Singapore

Textbook Question Answering (TQA) is the task of answering diagram and non-diagram questions given large multimodal contexts consisting of abundant text and diagrams. Deep text understandings and effective learning of diagram semantics are important for this task due to its specificity. In this paper, we propose a Weakly Supervised learning method for TQA (WSTQ), which regards the incompletely accurate results of essential intermediate procedures for this task as supervision to develop Text Matching (TM) and Relation Detection (RD) tasks and then employs the tasks to motivate itself to learn strong text comprehension and excellent diagram semantics respectively. Specifically, we apply the result of text retrieval to build positive as well as negative text pairs. In order to learn deep text understandings, we first pre-train the text understanding module of WSTQ on TM and then fine-tune it on TQA. We build positive as well as negative relation pairs by checking whether there is any overlap between the items/regions detected from diagrams using object detection. The RD task forces our method to learn the relationships between regions, which are crucial to express the diagram semantics. We train WSTQ on RD and TQA simultaneously, i.e., multitask learning, to obtain effective diagram semantics and then improve the TQA performance. Extensive experiments are carried out on CK12-QA and AI2D to verify the effectiveness of WSTQ. Experimental results show that our method achieves significant accuracy improvements of 5.02% and 4.12% on test splits of the above datasets respectively than the current state-of-the-art baseline. We have released our code on https://***/dr-majie/WSTQ. © 2021, CC BY.

关键词： Semantics

来源：评论

学校读者我要写书评

暂无评论

NDRIDC: NMF-based deep representation algorithm for incomplete data clustering

引用

Knowledge-Based Systems 2025年 324卷

作者： Dexian Wang Zonglin Li Sha Yang Tianrui Ren Pengfei Zhang Ping Deng Tianrui Li Chengdu University of Traditional Chinese Medicine Chengdu 611137 China Chinese Academy of Medical Sciences & Peking Union Medical College Beijing 100730 China School of Computer and Software Engineering Xihua University Chengdu 610039 China School of Computing and Artificial Intelligence Southwest Jiaotong University Chengdu 611756 China National Engineering Laboratory of Integrated Transportation Big Data Application Technology Southwest Jiaotong University Chengdu 611756 China Manufacturing Industry Chains Collaboration and Information Support Technology Key Laboratory of Sichuan Province Chengdu 611756 China

Incomplete data clustering is a hot research topic in the field of data mining. Many methods based on incomplete clustering have two issues: (1) their models do not have non-negative constraints; (2) their model building strategies do not consider combining traditional machine learning and deep learning. To address these issues, we proposed the NMF-based deep representation algorithm for incomplete data clustering (NDRIDC). First, the element-based objective function is constructed based on the known elements in the incomplete data matrix with matrix factorization principle. Then the NDRIDC deep network is constructed based on the element update gradient and nonlinear function with non-negative value domain. The learning of the NDRIDC network enables the optimization of the objective function and the filling of missing values. Further, based on the same learning framework, the NDRIDC network is employed to perform low-dimensional representation of the filled matrix. Finally, extensive experiments on regular and large-scale datasets show that our proposed algorithm has good performance.

关键词： Clustering Deep learning Incomplete data Non-negative matrix factorization

来源：评论

学校读者我要写书评

暂无评论

Erratum to: CA-DTS: A Distributed and Collaborative Task Scheduling Algorithm for Edge Computing Enabled Intelligent Road Network

引用

Journal of Computer Science and technology 2023年第6期38卷 1451-1451页

作者： Hu, Shi-Hong Luo, Qu-Yuan Li, Guang-Hui Shi, Weisong Ye, Bao-Liu Key Laboratory of Water Big Data Technology of Ministry of Water Resources Hohai University Nanjing China School of Computer and Information Hohai University Nanjing China School of Information Science and Technology Southwest Jiaotong University Chengdu China School of Artificial Intelligence and Computer Science Jiangnan University Wuxi China Department of Computer and Information Sciences University of Delaware Newark USA National Key Laboratory for Novel Software Technology Nanjing University Nanjing China

来源：评论

学校读者我要写书评

暂无评论

Study of Star/Galaxy Classification Based on the XGBoost Algorithm

引用

Chinese Astronomy and Astrophysics 2019年第4期43卷 539-548页

作者： Chao, Li Wen-hui, Zhang Ji-ming, Lin College of Information and Communication Engineering Guilin University of Electronic Technology Guilin 541004 Key Laboratory of Cognitive Radio and Information Processing the Ministry of Education Guilin University of Electronic Technology Guilin 541004 Guangxi Cooperative Innovation Center of Cloud Computing and Big Data Guilin University of Electronic Technology Guilin 541004 Guangxi Colleges and Universities Key Laboratory of Cloud Computing and Complex Systems Guilin University of Electronic Technology Guilin 541004

Machine learning has achieved great success in many areas today. The lifting algorithm has a strong ability to adapt to various scenarios with a high accuracy, and has played a great role in many fields. But in astronomy, the application of lifting algorithms is still rare. In response to the low classification accuracy of the dark star/galaxy source set in the Sloan Digital Sky Survey (SDSS), a new research result of machine learning, eXtreme Gradient Boosting (XGBoost), has been introduced. The complete photometric data set is obtained from the SDSS-DR7, and divided into a bright source set and a dark source set according to the star magnitude. Firstly, the ten-fold cross-validation method is used for the bright source set and the dark source set respectively, and the XGBoost algorithm is used to establish the star/galaxy classification model. Then, the grid search and other methods are used to adjust the XGBoost parameters. Finally, based on the galaxy classification accuracy and other indicators, the classification results are analyzed, by comparing with the models of function tree (FT), Adaptive boosting (Adaboost), Random Forest (RF), Gradient Boosting Decision Tree (GBDT), Stacked Denoising AutoEncoders (SDAE), and Deep Belief Nets (DBN). The experimental results show that, the XGBoost improves the classification accuracy of galaxies in the dark source classification by nearly 10% as compared to the function tree algorithm, and improves the classification accuracy of sources with the darkest magnitudes in the dark source set by nearly 5% as compared to the function tree algorithm. Compared with other traditional machine learning algorithms and deep neural networks, the XGBoost also has different degrees of improvement. © 2019

关键词： Stars: fundamental parameters—galaxies: fundamental parameters—techniques: photometric—methods: data analysis

来源：评论

学校读者我要写书评

暂无评论

Combining dynamic and static analysis for automated grading SQL statements

Journal of Network Intelligence

引用

Journal of Network intelligence 2020年第4期5卷 179-190页

作者： Wang, Jinshui Zhao, Yunpeng Tang, Zhengyi Xing, Zhenchang School of Computer Science and Mathematics Fujian University of Technology Fuzhou350118 China Fujian Provincial Key Laboratory of Big Data Mining and Applications Fujian University of Technology Fuzhou350118 China Key Laboratory of Hunan Province for Mobile Business Intelligence Hunan University of Technology and Business Changsha410205 China Research School of Computer Science Australian National University ACT 2601 Australia

Learning and teaching Structured Query Language (SQL) is a challenge that is widely recognized within the computer science education community. Programming ac-tivities are considered to be the most important aspect of the learning process. Manually grading of SQL statements, however, is often regarded as a tedious and time-consuming ordeal. In this paper we propose an automated grading approach for SQL statements, which combines dynamic and static analysis. The proposed approach first identified the correct statements from the student SQL statements, and then grades the incorrect statements based on the similarity between the statements and the correct statements. Empir-ical evaluation of the proposal was carried out on a dataset consisting of 255 manually graded pairs of statements. Experimental results show that our approach is superior to three state-of-the-art grading approaches. Our study found that each grading approach has its particular advantages and disadvantages, and the combination of different grading approaches can help to improve the quality of grading results. © 2020, Taiwan Ubiquitous Information. All rights reserved.

关键词： Grading

来源：评论

学校读者我要写书评

暂无评论

Corrigendum to Intrusion detection based on improved density peak clustering for imbalanced data on sensor-cloud systems Journal of Systems Architecture volume 118 (2021) 102212

引用

Journal of Systems Architecture 2021年 119卷

作者： Ming Yan Yewang Chen Xiaoliang Hu Dongdong Cheng Yi Chen Jixiang Du The College of Computer Science and Technology Huaqiao University Xiamen China Beijing Key Laboratory of Big Data Technology for Food Safety Beijing Technology and Business University Beijing China Provincial Key Laboratory for Computer Information Processing Technology Soochow University Soochow China Xiamen Key Laboratory of Computer Vision and Pattern Recognition Huaqiao University Fujian Key Laboratory of Big Data Intelligence and Security Huaqiao University Xiamen China College of Big Data and Intelligent Engineering Yangtze Normal University Chongqing China

来源：评论

学校读者我要写书评

暂无评论

Real-time Semantic Segmentation via Spatial-detail Guided Context Propagation

arXiv

引用

arXiv 2020年

作者： Hao, Shijie Zhou, Yuan Guo, Yanrong Hong, Richang Cheng, Jun Wang, Meng Key Laboratory of Knowledge Engineering with Big Data Hefei University of Technology Ministry of Education School of Computer Science and Information Engineering Hefei University of Technology Hefei230009 China CAS Key Laboratory of Human-Machine Intelligence-Synergy Systems Shenzhen Institutes of Advanced Technology Chinese Academy of Sciences Chinese University of Hong Kong Hong Kong

Nowadays, vision-based computing tasks play an important role in various real-world applications. However, many vision computing tasks, e.g. semantic segmentation, are usually computationally expensive, posing a challenge to the computing systems that are resource-constrained but require fast response speed. Therefore, it is valuable to develop accurate and real-time vision processing models that only require limited computational resources. To this end, we propose the Spatial-detail Guided Context Propagation Network (SGCPNet) for achieving real-time semantic segmentation. In SGCPNet, we propose the strategy of spatial-detail guided context propagation. It uses the spatial details of shallow layers to guide the propagation of the low-resolution global contexts, in which the lost spatial information can be effectively reconstructed. In this way, the need for maintaining high-resolution features along the network is freed, therefore largely improving the model efficiency. On the other hand, due to the effective reconstruction of spatial details, the segmentation accuracy can be still preserved. In the experiments, we validate the effectiveness and efficiency of the proposed SGCPNet model. On the Citysacpes dataset, for example, our SGCPNet achieves 69.5% mIoU segmentation accuracy, while its speed reaches 178.5 FPS on 768×1536 images on a GeForce GTX 1080 Ti GPU card. In addition, SGCPNet is very lightweight and only contains 0.61 M parameters. The code will be released at https://***/zhouyuan888888/SGCPNet. Copyright © 2020, The Authors. All rights reserved.

关键词： Semantic Segmentation

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：