检索结果-内蒙古大学图书馆

Fusion of Super-Resolution and Semantic Segmentation Deep Models for Building Footprint Extraction From Aerial Images

引用

The Photogrammetric Record 2025年第190期40卷

作者： Ziyi Chen Yuhua Luo Jiaying Zhang Ronggang Guo Liai Deng Jinghua Liu Dilong Li Yongtao Yu Ammar Abulibdeh Cheng Wang Department of Computer Science and Technology Fujian Key Laboratory of big Data Intelligence and Security Xiamen Key Laboratory of Computer Vision and Pattern Recognition Huaqiao University Xiamen FJ China Guojiao Spatial Information Technology (Beijing) co. Ltd Beijing China Faculty of Computer and Software Engineering Huaiyin Institute of Technology Huaian JS China Department of Humanities College of Arts and Sciences Qatar University Doha Qatar School of Informatics Xiamen University Xiamen FJ China

The spatial resolution of remotely sensed images has seen significant improvements; higher resolution facilitates the understanding of remote sensing images and improves the accuracy of building footprint extraction. Thus, this paper introduces a novel approach that combines super-resolution reconstruction with semantic segmentation deep models for building footprint extraction. To begin, a super-resolution reconstruction deep model is employed to enhance the resolution of the target images. Subsequently, training samples are generated using various data augmentation techniques based on the reconstructed images. Finally, a semantic segmentation deep model is trained to perform the final building footprint extraction. For validation, our proposed framework was tested on two publicly available aerial image datasets: the WHU building dataset and the Massachusetts building dataset. The results obtained from these datasets demonstrated the effectiveness of our method, achieving high Intersection over Union (IoU) scores of 90.57% and 75.02%, respectively. Furthermore, our approach outperformed seven other competing methods, showcasing its superior performance.

关键词： aerial image building footprint extraction deep learning semantic segmentation super-resolution

来源：评论

学校读者我要写书评

暂无评论

Attention in Attention: Modeling Context Correlation for Efficient Video Classification

arXiv

引用

arXiv 2022年

作者： Hao, Yanbin Wang, Shuo Cao, Pei Gao, Xinjian Xu, Tong Wu, Jinmeng He, Xiangnan The CCCD Key Lab of Ministry of Culture and Tourism School of Data Science School of Information Science and Technology University of Science and Technology of China Anhui 230026 China The Wuhan Research Institute of Posts and Telecommunications Hubei Wuhan430205 China The School of Computer Science and Information Engineering School of Artificial Intelligence Hefei University of Technology Anhui 230009 China The School of Data Science School of Computer Science and Technology University of Science and Technology of China Anhui 230026 China The Hubei Key Laboratory of Optical Information and Pattern Recognition Wuhan Institute of Technology Hubei Wuhan430070 China

Attention mechanisms have significantly boosted the performance of video classification neural networks thanks to the utilization of perspective contexts. However, the current research on video attention generally focuses on adopting a specific aspect of contexts (e.g., channel, spatial/temporal, or global context) to refine the features and neglects their underlying correlation when computing attentions. This leads to incomplete context utilization and hence bears the weakness of limited performance improvement. To tackle the problem, this paper proposes an efficient attention-in-attention (AIA) method for element-wise feature refinement, which investigates the feasibility of inserting the channel context into the spatio-temporal attention learning module, referred to as CinST, and also its reverse variant, referred to as STinC. Specifically, we instantiate the video feature contexts as dynamics aggregated along a specific axis with global average and max pooling operations. The workflow of an AIA module is that the first attention block uses one kind of context information to guide the gating weights calculation of the second attention that targets at the other context. Moreover, all the computational operations in attention units act on the pooled dimension, which results in quite few computational cost increase ( Copyright © 2022, The Authors. All rights reserved.

关键词： Machine learning

来源：评论

学校读者我要写书评

暂无评论

An intelligent clustering scheme based on whale optimization algorithm in flying ad hoc networks

引用

Vehicular Communications 2024年 49卷

作者： Hosseinzadeh, Mehdi Tanveer, Jawad Alanazi, Faisal Aurangzeb, Khursheed Yousefpoor, Mohammad Sadegh Yousefpoor, Efat Darwesh, Aso Lee, Sang-Woong Rahmani, Amir Masoud Institute of Research and Development Duy Tan University Da Nang Viet Nam School of Medicine and Pharmacy Duy Tan University Da Nang Viet Nam Department of Computer Science and Engineering Sejong University Seoul 05006 South Korea Department of Electrical Engineering College of Engineering Prince Sattam bin Abdulaziz University Al-Kharj 11942 Saudi Arabia Department of Computer Engineering College of Computer and Information Sciences King Saud University P. O. Box 51178 Riyadh 11543 Saudi Arabia Center of Research and Strategic Studies Lebanese French University Kurdistan Region Iraq Department of Information Technology University of Human Development Kurdistan Region Sulaymaniyah Iraq Pattern Recognition and Machine Learning Lab Gachon University 1342 Seongnamdaero Sujeonggu Seongnam 13120 South Korea Future Technology Research Center National Yunlin University of Science and Technology Yunlin Taiwan

Due to the progress of unmanned aerial vehicles (UAVs), this new technology is widely applied in military and civilian areas. Multi-UAV networks are often known as flying ad hoc networks (FANETs). Due to these applications, FANET must ensure communication stability and have high scalability. These goals are achieved by presenting clustering techniques in FANETs. However, the characteristics of these networks, like high-mobility nodes, limited energy, and dynamic topology, have created great challenges in two important processes of clustering protocols, namely cluster construction and the selection of cluster heads. In this paper, an intelligent clustering scheme based on the whale optimization algorithm called ICW is suggested in flying ad hoc networks. Firstly, each UAV specifies its hello interval based on the lifespan of adjacent links to guarantee the adaptability of ICW to FANET. Then, a centralized clustering process is done using a whale optimization algorithm (WOA) to find the best cluster centers on the network. To determine the membership of each UAV in a cluster, ICW employs a new criterion, i.e. closeness ratio, so that each UAV joins a cluster with the best closeness ratio. In addition, the evaluation of each whale is carried out based on a fitness function, consisting of three components, namely the number of isolated clusters, the ratio of inter-cluster distance to intra-cluster distance, and cluster size. Then, a cluster head is selected for each cluster based on a score value. This score is dependent on the weighted sum of four metrics, namely remaining energy, the average link lifespan between each UAV and its neighbors, neighbor degree, and the average distance between each UAV and its neighbors. In the last step, two routing processes, namely intra-cluster routing and inter-cluster routing, are introduced in FANET. Then, the evaluation and implementation of ICW is performed through the NS2 simulator. After completing the simulation process, ICW i

关键词： Artificial Intelligence (AI) Clustering Flying ad hoc networks (FANETs) Nature-inspired algorithms Unmanned aerial vehicles (UAVs)

来源：评论

学校读者我要写书评

暂无评论

ELLE: Efficient Lifelong Pre-training for Emerging Data

arXiv

引用

arXiv 2022年

作者： Qin, Yujia Zhang, Jiajie Lin, Yankai Liu, Zhiyuan Li, Peng Sun, Maosong Zhou, Jie Department of Computer Science and Technology Tsinghua University Beijing China Beijing National Research Center for Information Science and Technology China Institute for Artificial Intelligence Tsinghua University Beijing China Pattern Recognition Center WeChat AI Tencent Inc China International Innovation Center of Tsinghua University Shanghai China Beijing Academy of Artificial Intelligence China Tsinghua University China Jiangsu Collaborative Innovation Center for Language Ability Xuzhou China

Current pre-trained language models (PLM) are typically trained with static data, ignoring that in real-world scenarios, streaming data of various sources may continuously grow. This requires PLMs to integrate the information from all the sources in a lifelong manner. Although this goal could be achieved by exhaustive pre-training on all the existing data, such a process is known to be computationally expensive. To this end, we propose ELLE, aiming at efficient lifelong pretraining for emerging data. Specifically, ELLE consists of (1) function preserved model expansion, which flexibly expands an existing PLM's width and depth to improve the efficiency of knowledge acquisition;and (2) pretrained domain prompts, which disentangle the versatile knowledge learned during pretraining and stimulate the proper knowledge for downstream tasks. We experiment ELLE with streaming data from 5 domains on BERT and GPT. The results show the superiority of ELLE over various lifelong learning baselines in both pre-training efficiency and downstream performances. The codes are publicly available at https://***/thunlp/ELLE. Copyright © 2022, The Authors. All rights reserved.

关键词： Efficiency

来源：评论

学校读者我要写书评

暂无评论

Attentive Part-aware Networks for Partial Person Re- identification

Attentive Part-aware Networks for Partial Person Re- identif...

引用

International Conference on pattern recognition

作者： Lijuan Huo Chunfeng Song Zhengyi Liu Zhaoxiang Zhang Center for Research on Intelligent Perception and Computing (CRIPAC) National Laboratory of Pattern Recognition (NLPR) Institute of Automation Chinese Academy of Sciences (CASIA) Artificial Intelligence ResearchChinese Academy of Sciences Jiaozhou Qingdao China School of Computer Science and Technology Anhui University Hefei China University of Chinese Academy of Sciences (UCAS)

Partial person re-identification (re-ID) refers to re-identify a person through occluded images. It suffers from two major challenges, i.e., insufficient training data and incomplete probe image. In this paper, we introduce a part-aware learning method for partial person re-identification. On the one hand, we adopt data augmentation operation to enrich the training data and improve the robustness of the model. On the other hand, we intuitively find that the partial person images usually have fixed percentages of parts, therefore, in partial person re-ID task, the probe image could be cropped from the pictures and divided into several different partial types following fixed ratios. Based on the cropped images, we propose the Cropping Type Consistency (CTC) loss to classify the cropping types of partial images. Moreover, in order to help the network better fit the generated and cropped data, we incorporate the Block Attention Mechanism (BAM) into the framework for attentive learning. To enhance the retrieval performance in the inference stage, we implement cropping on gallery images according to the predicted types of probe partial images. Through calculating feature distances between the partial image and the cropped holistic gallery images, the model can recognize the right person from the gallery. To validate the effectiveness of our approach, we conduct extensive experiments on the partial re- ID benchmarks and achieve state-of-the-art performance.

关键词： Training Learning systems Image recognition Semantics Training data Robustness Data models

来源：评论

学校读者我要写书评

暂无评论

EfficientFCN: Holistically-guided decoding for semantic segmentation

arXiv

引用

arXiv 2020年

作者： Liu, Jianbo He, Junjun Zhang, Jiawei Ren, Jimmy S. Li, Hongsheng CUHK-SenseTime Joint Laboratory Chinese University of Hong Kong Hong Kong Shenzhen Key Lab of Computer Vision and Pattern Recognition Shenzhen Institutes of Advanced Technology Chinese Academy of Sciences China SenseTime Research China

Both performance and efficiency are important to semantic segmentation. State-of-the-art semantic segmentation algorithms are mostly based on dilated Fully Convolutional Networks (dilatedFCN), which adopt dilated convolutions in the backbone networks to extract high-resolution feature maps for achieving high-performance segmentation performance. However, due to many convolution operations are conducted on the high-resolution feature maps, such dilatedFCN-based methods result in large computational complexity and memory consumption. To balance the performance and efficiency, there also exist encoder-decoder structures that gradually recover the spatial information by combining multi-level feature maps from the encoder. However, the performances of existing encoder-decoder methods are far from comparable with the dilatedFCN-based methods. In this paper, we propose the EfficientFCN, whose backbone is a common ImageNet pretrained network without any dilated convolution. A holistically-guided decoder is introduced to obtain the high-resolution semantic-rich feature maps via the multi-scale features from the encoder. The decoding task is converted to novel codebook generation and codeword assembly task, which takes advantages of the high-level and low-level features from the encoder. Such a framework achieves comparable or even better performance than state-of-the-art methods with only 1/3 of the computational cost. Extensive experiments on PASCAL Context, PASCAL VOC, ADE20K validate the effectiveness of the proposed EfficientFCN. Copyright © 2020, The Authors. All rights reserved.

关键词： Convolution

来源：评论

学校读者我要写书评

暂无评论

COCAS: A Large-Scale Clothes Changing Person Dataset for Re-Identification

COCAS: A Large-Scale Clothes Changing Person Dataset for Re-...

引用

Conference on computer vision and pattern recognition (CVPR)

作者： Shijie Yu Shihua Li Dapeng Chen Rui Zhao Junjie Yan Yu Qiao ShenZhen Key Lab of Computer Vision and Pattern Recognition SIAT-SenseTime Joint Lab Shenzhen Institutes of Advanced Technology Chinese Academy of Science University of Chinese Academy of Sciences China Institute of Microelectronics of the Chinese Academy of Sciences

ISBN: (数字)9781728171685

ISBN: (纸本)9781728171692

Recent years have witnessed great progress in person re-identification (re-id). Several academic benchmarks such as Market1501, CUHK03 and DukeMTMC play important roles to promote the re-id research. To our best knowledge, all the existing benchmarks assume the same person will have the same clothes. While in real-world scenarios, it is very often for a person to change clothes. To address the clothes changing person re-id problem, we construct a novel large-scale re-id benchmark named Clothes Changing Person Set (COCAS), which provides multiple images of the same identity with different clothes. COCAS totally contains 62,382 body images from 5,266 persons. Based on COCAS, we introduce a new person re-id setting for clothes changing problem, where the query includes both a clothes template and a person image taking another clothes. Moreover, we propose a two-branch network named Biometric-Clothes Network (BC-Net) which can effectively integrate biometric and clothes feature for re-id under our setting. Experiments show that it is feasible for clothes changing re-id with clothes templates.

关键词： Face Feature extraction Benchmark testing Protocols Biological system modeling Shape

来源：评论

学校读者我要写书评

暂无评论

A simple real-word error detection and correction using local word bigram and trigram 25

A simple real-word error detection and correction using loca...

引用

25th Conference on Computational Linguistics and Speech Processing, ROCLING 2013

作者： Samanta, Pratip Chaudhuri, Bidyut B. Computer Vision and Pattern Recognition Unit Indian Statistical Institute Kolkata India

ISBN: (纸本)9789573079262

Spelling error is broadly classified in two categories namely non word error and real word error. In this paper a localized real word error detection and correction method is proposed where the scores of bigrams generated by immediate left and right neighbour of the candidate word and the trigram of these three words are combined. A single character position error model is assumed so that if a word W is erroneous then the correct word belongs to the set of real words S generated by single character edit operation on W. The above combined score is calculated also on all members of S. These words are ranked in the decreasing order of the score. By observing the rank and using a rule based approach, the error decision and correction candidates are simultaneously selected. The approach gives comparable accuracy with other existing approaches but is computationally attractive. Since only left and right neighbor are involved, multiple errors in a sentence can also be detected (if the error occurs in every alternate words). © ROCLING *** rights reserved.

关键词： Error detection

来源：评论

学校读者我要写书评

暂无评论

Partial Differential Equations is All You Need for Generating Neural Architectures - A Theory for Physical Artificial Intelligence Systems

arXiv

引用

arXiv 2021年

作者： Guo, Ping Huang, Kaizhu Xu, Zenglin Image Processing & Pattern Recognition Lab. Beijing Normal University Beijing100875 China Data Science Research Center Duke Kunshan University Jiangsu Kunshan215316 China School of Computer Science and Technology Harbin Institute of Technology at ShenZhen Peng Cheng National Lab Guangdong Shenzhen510855 China

In this work, we generalize the reaction-diffusion equation in statistical physics, Schrödinger equation in quantum mechanics, and Helmholtz equation in paraxial optics into the neural partial differential equations (NPDE), which can be considered as the fundamental equations in the field of artificial intelligence research. We take the finite difference method to discretize NPDEs for finding the numerical solution. Moreover, the basic building blocks of deep neural network architectures, including multi-layer perceptron, convolutional neural networks, and recurrent neural networks, are generated. The learning strategies, such as Adaptive moment estimation, L-BFGS, pseudoinverse learning algorithms, and partial differential equation constrained optimization, are also developed. This work is of significance in that it presents a clear view of interpretable deep neural networks physically, enables high possibility to be applied to analog computing device design, and paves the road to physical artificial intelligence. © 2021, CC BY-NC-SA.

关键词： Schrodinger equation

来源：评论

学校读者我要写书评

暂无评论

COCAS: A large-scale clothes changing person dataset for re-identification

arXiv

引用

arXiv 2020年

作者： Yu, Shijie Li, Shihua Chen, Dapeng Zhao, Rui Yan, Junjie Qiao, Yu ShenZhen Key Lab of Computer Vision and Pattern Recognition SIAT-SenseTime Joint Lab Shenzhen Institutes of Advanced Technology Chinese Academy of Science University of Chinese Academy of Sciences China Institute of Microelectronics of the Chinese Academy of Sciences

Recent years have witnessed great progress in person re-identification (re-id). Several academic benchmarks such as Market1501, CUHK03 and DukeMTMC play important roles to promote the re-id research. To our best knowledge, all the existing benchmarks assume the same person will have the same clothes. While in real-world scenarios, it is very often for a person to change clothes. To address the clothes changing person re-id problem, we construct a novel large-scale re-id benchmark named ClOthes ChAnging Person Set (COCAS), which provides multiple images of the same identity with different clothes. COCAS totally contains 62,382 body images from 5,266 persons. Based on COCAS, we introduce a new person re-id setting for clothes changing problem, where the query includes both a clothes template and a person image taking another clothes. Moreover, we propose a two-branch network named Biometric-Clothes Network (BC-Net) which can effectively integrate biometric and clothes feature for re-id under our setting. Experiments show that it is feasible for clothes changing re-id with clothes templates. Copyright © 2020, The Authors. All rights reserved.

关键词： Large dataset

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：