检索结果-内蒙古大学图书馆

Vehicle re-identification with location and time stamps 32

学校读者我要写书评

暂无评论

Vehicle re-identification with location and time stamps

32nd IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops, CVPRW 2019

作者： Lv, Kai Du, Heming Hou, Yunzhong Deng, Weijian Sheng, Hao Jiao, Jianbin Zheng, Liang Beijing Advanced Innovation Center for Big Data and Brain Computing Beihang University State Key Laboratory of Software Development Environment School of Computer Science and Engineering Beihang University University of Chinese Academy of Sciences Australian National University

ISBN: (纸本)9781728125060

This paper focuses on the problem of vehicle re-identification (Re-ID). In our attempt, we propose a re-identification framework by exploiting vehicle location and time stamps. The location and time information have the potential to cover the shortage of appearance-based feature representations. First, we introduce an ensemble technique to combine the informative cues of multiple Re-ID models effectively. To further improve the accuracy, we then build up a system to acquire the vehicle location and time stamps. Specifically, we utilize the detected results to obtain the needed information. With the help of the proposed system, we can remove irrelevant images from a given ranking list. Our system finished 3rd place in the 2019 AI-City challenge for city-scale multi-camera vehicle re-identification. © 2019 IEEE Computer Society. All rights reserved.

关键词： Vehicles

A Hybrid Approach for retinal image super-resolution

学校读者我要写书评

暂无评论

Biomedical Engineering Advances 2023年 6卷

作者： Alnur Alimanov Md Baharul Islam Nirase Fathima Abubacker Department of Computer Engineering Bahcesehir University Yildiz Ciragan Cd. Besiktas Istanbul 34349 Turkey College of Data Science & Engineering American University of Malta Triq Dom Mintoff Bormla BML 1013 Malta School of Computing Asia Pacific University of Technology & Innovation Bukit Jalil Kuala Lumpur 57000 Malaysia

Experts require large high-resolution retinal images to detect tiny abnormalities, such as microaneurysms or issues of vascular branches. However, these images often suffer from low quality (e.g., resolution) due to poor imaging device configuration and misoperations. Many works utilized Convolutional Neural Network-based (CNN) methods for image super-resolution. The authors focused on making these models more complex by adding layers and various blocks. It leads to additional computational expenses and obstructs the application in real-life scenarios. Thus, this paper proposes a novel, lightweight, deep-learning super-resolution method for retinal images. It comprises a Vision Transformer (ViT) encoder and a convolutional neural network decoder. To our best knowledge, this is the first attempt to use a transformer-based network to solve the issue of accurate retinal image super-resolution. A progressively growing super-resolution training technique is applied to increase the resolution of images by factors of 2, 4, and 8. The prominent architecture remains constant thanks to the adaptive patch embedding layer, which does not lead to additional computational expense due to increased up-scaling factors. This patch embedding layer includes 2-dimensional convolution with specific values of kernel size and strides that depend on the input shape. This strategy has removed the need to append additional super-resolution blocks to the model. The proposed method has been evaluated through quantitative and qualitative measures. The qualitative analysis also includes vessel segmentation of super-resolved and ground truth images. Experimental results indicate that the proposed method outperforms the current state-of-the-art methods.

关键词： Retinal images Single image super-Resolution Adaptive patch embedding layer Locality self-Attention Vision transformer Convolutional neural network

A novel facial expression recognition method based on cross direction attention network

学校读者我要写书评

暂无评论

Engineering Applications of Artificial Intelligence 2025年 157卷

作者： Cheng Peng Guodong Li Likang Lin Bowen Zhang Kun Zou Sio Long Lo Ah Chung Tsoi School of Computer Science University of Electronic Science and Technology of China Zhongshan Institute No. 1 Xueyuan Road Zhongshan 528402 Guangdong China School of Computer Science and Engineering University of Electronic Science and Technology of China Xiyuan Avenue High-tech Zone Chengdu 610000 Sichuan China College of Mathematics and Informatics South China Agricultural University 483 Wushan Road GuangZhou 510642 Guangdong China College of Big Data and Internet Shenzhen Technology University 3002 Lantian Road Shenzhen 510642 Guangdong China Faculty of Innovation Engineering Macau University of Science and Technology Avenida Wai Long Taipa Macau 999078 Macao Special Administrative Region of China School of Computing and Information Technology University of Wollongong Northfields Ave Wollongong NSW 2522 New South Wales Australia

Facial expression recognition (FER) is an area of growing interest in computer vision research. This paper extends the framework provided by the ‘Distract your Attention Network’ (DAN) which consists of multiple parallel branches, each branch composes of a spatial attention (SA) module followed by a channel attention (CA) module, and then these multiple branches are fused together before being passed into a classifier module. The spatial attention module of DAN has an internal channel dimension of 1, while our proposed Cross Directional Attention Network (CDAN)-I and CDAN-II contain respectively an internal channel dimension of 512 (same as the channel dimension of the input), and internal channel dimension of 1024 (double that of the channel dimension of the input). These increases in internal channel dimension allow extraction of more features, before they are being made to conform with the input channel dimension. Despite these seemingly simple modifications from that of DAN, both CDAN-I and CDAN-II are found to outperform those of DAN, a state-of-the-art FER method, on four popular FER benchmark datasets: RAF-DB (Real world Affective Face-database), AffectNet-7 (AffectNet with Seven Categories) AffectNet-8 ( AffectNet with Eight Categories), and CK+ (Cohn–Kanada Extended). Moreover, we make use of three statistical indexes for clustering analysis, and verified that the CDAN-I and CDAN-II modules have been able to increase the inter-cluster distances, and decrease the intra-cluster distances, when compared with those obtained by the backbone ResNet-18 network (Residual Network with 18 Layers) , thus providing a quantitative analysis technique in this area.

关键词：

Relation-Guided Representation Learning

学校读者我要写书评

暂无评论

arXiv 2020年

作者： Kang, Zhao Lu, Xiao Liang, Jian Bai, Kun Xu, Zenglin School of Computer Science and Engineering University of Electronic Science and Technology of China Sichuan China Trusted Cloud Computing and Big Data Key Laboratory of Sichuan Province Cloud and Smart Industries Group Tencent Beijing China School of Computer Science and Technology Harbin Institute of Technology Shenzhen China Center for Artificial Intelligence Peng Cheng Lab Shenzhen China

Deep auto-encoders (DAEs) have achieved great success in learning data representations via the powerful representability of neural networks. But most DAEs only focus on the most dominant structures which are able to reconstruct the data from a latent space and neglect rich latent structural information. In this work, we propose a new representation learning method that explicitly models and leverages sample relations, which in turn is used as supervision to guide the representation learning. Different from previous work, our framework well preserves the relations between samples. Since the prediction of pairwise relations themselves is a fundamental problem, our model adaptively learns them from data. This provides much flexibility to encode real data manifold. The important role of relation and representation learning is evaluated on the clustering task. Extensive experiments on benchmark data sets demonstrate the superiority of our approach. By seeking to embed samples into subspace, we further show that our method can address the large-scale and out-of-sample problem. Our source code is publicly available at: https://***/nbShawnLu/RGRL. Copyright © 2020, The Authors. All rights reserved.

关键词： Clustering algorithms

Insights, opportunities and challenges provided by large cell atlases

学校读者我要写书评

暂无评论

arXiv 2024年

作者： Hemberg, Martin Marini, Federico Ghazanfar, Shila Ajami, Ahmad Al Abassi, Najla Anchang, Benedict Benayoun, Bérénice A. Cao, Yue Chen, Ken Cuesta-Astroz, Yesid DeBruine, Zach Dendrou, Calliope A. De Vlaminck, Iwijn Imkeller, Katharina Korsunsky, Ilya Lederer, Alex R. Meysman, Pieter Miller, Clint Mullan, Kerry Ohler, Uwe Patikas, Nikolaos Schuck, Jonas Siu, Jacqueline H.Y. Triche, Timothy J. Tsankov, Alex van der Laan, Sander W. Yajima, Masanao Yang, Jean Zanini, Fabio Jelic, Ivana The Gene Lay Institute of Immunology and Inflammation Brigham and Women's Hospital Massachusetts General Hospital United States Harvard Medical School BostonMA United States University Medical Center Mainz Mainz Germany Mainz Germany School of Mathematics and Statistics Faculty of Science University of Sydney NSW2006 Australia Sydney Precision Data Science Centre University of Sydney SydneyNSW2006 Australia Charles Perkins Centre University of Sydney SydneyNSW2006 Australia Goethe University Neurological Institute Edinger Institute University Hospital Frankfurt Frankfurt am Main Germany Goethe University Frankfurt Cancer Institute Frankfurt am Main Germany Frankfurt am Main Germany National Institute of Environmental Health Sciences United States Leonard Davis School of Gerontology University of Southern California Los AngelesCA90089 United States Molecular and Computational Biology Department USC Dornsife College of Letters Arts and Sciences Los AngelesCA90089 United States Biochemistry and Molecular Medicine Department USC Keck School of Medicine Los AngelesCA90089 United States Science Park Hong Kong The University of Texas MD Anderson Cancer Center United States Escuela de Microbiología Universidad de Antioquia Ciudad Universitaria Calle 67 No 12 53-108 Medellín Colombia Instituto Colombiano de Medicina Tropical Universidad CES Sabaneta055413 Colombia School of Computing Grand Valley State University AllendaleMI49401 United States Kennedy Institute of Rheumatology Nuffield Department of Orthopaedics Rheumatology and Musculoskeletal Sciences University of Oxford Oxford United Kingdom Cornell University United States Brigham and Women’s Hospital Divisions of Genetics and Rheumatology BostonMA United States and Harvard CambridgeMA United States Lausanne1015 Switzerland Adrem data lab Department of Computer Science University of Antwerp Antwerp Belgium The Rector and Visitors The University of Virginia United States M

The field of single-cell biology is growing rapidly and is generating large amounts of data from a variety of species, disease conditions, tissues, and organs. Coordinated efforts such as CZI CELLxGENE, HuBMAP, Broad Institute Single Cell Portal, and DISCO, allow researchers to access large volumes of curated datasets. Although the majority of the data is from scRNAseq experiments, a wide range of other modalities are represented as well. These resources have created an opportunity to build and expand the computational biology ecosystem to develop tools necessary for data reuse, and for extracting novel biological insights. Here, we highlight achievements made so far, areas where further development is needed, and specific challenges that need to be overcome. © 2024, CC BY-NC-ND.

关键词： Biotic

IDEA: Integrating Divisive and Ensemble-Agglomerate hierarchical clustering framework for arbitrary shape data

学校读者我要写书评

暂无评论

IDEA: Integrating Divisive and Ensemble-Agglomerate hierarch...

IEEE International Conference on Big data

作者： Hongryul Ahn Inuk Jung Heejoon Chae Minsik Oh Inyoung Kim Sun Kim Division of Data Science DS&ML Center The University of Suwon Hwaseong Republic of Korea School of Computer Science and Engineering Kyungpook National University Daegu Republic of Korea Division of Computer Science Sookmyung Women's University Seoul Republic of Korea BK21 Four Intelligence Computing Seoul National University Seoul Republic of Korea Artificial Intelligence Institute Seoul National University Seoul Republic of Korea Interdisciplinary Program in Bioinformatics and Bioinformatics Institute Seoul National University Seoul Republic of Korea

ISBN: (纸本)9781665445993

Hierarchical clustering, a traditional clustering method, has been getting attention again. Among several reasons, a credit goes to a recent paper by Dasgupta in 2016 that proposed a cost function that quantitatively evaluates hierarchical clustering trees. An important question is how to combine this recent advance with existing successful clustering methods. In this paper, we propose a hierarchical clustering method to minimize the cost function of clustering tree by incorporating existing clustering techniques. First, we developed an ensemble tree-search method that finds an integrated tree with reduced cost by integrating multiple existing hierarchical clustering methods. Second, to operate on large and arbitrary shape data, we designed an efficient hierarchical clustering framework, called integrating divisive and ensemble-agglomerate (IDEA) by combining it with advanced clustering techniques such as nearest neighbor graph construction, divisive-agglomerate hybridization, and dynamic cut tree. The IDEA clustering method showed better performance in minimizing Dasgupta's cost and improving accuracy (adjusted rand index) over existing cost-minimization-based, and density-based hierarchical clustering methods in experiments using arbitrary shape datasets and complex biology-domain datasets.

关键词： Costs Shape Clustering methods Conferences Big data Cost function Minimization

Poisoning attack against estimating from pairwise comparisons

学校读者我要写书评

暂无评论

arXiv 2021年

作者： Ma, Ke Xu, Qianqian Zeng, Jinshan Cao, Xiaochun Huang, Qingming The School of Computer Science and Technology University of Chinese Academy of Sciences Beijing100049 China The Artificial Intelligence Research Center Peng Cheng Laboratory Shenzhen518055 China The Key Laboratory of Intelligent Information Processing Institute of Computing Technology Chinese Academy of Sciences Beijing100190 China The School of Computer and Information Engineering Jiangxi Normal University Jiangxi Nanchang330022 China Institute of Information Engineering Chinese Academy of Sciences Beijing100093 China The School of Cyber Security University of Chinese Academy of Sciences Beijing100049 China The Key Laboratory of Intelligent Information Processing Institute of Computing Technology Chinese Academy of Sciences Beijing100190 China The School of Computer Science and Technology University of Chinese Academy of Sciences Beijing100049 China The Key Laboratory of Big Data Mining and Knowledge Management The School of Economics and Management University of Chinese Academy of Sciences Beijing100049 China

As pairwise ranking becomes broadly employed for elections, sports competitions, recommendation, information retrieval and so on, attackers have strong motivation and incentives to manipulate or disrupt the ranking list. They could inject malicious comparisons into the training data to fool the target ranking algorithm. Such a technique is called "poisoning attack" in regression and classification tasks. In this paper, to the best of our knowledge, we initiate the first systematic investigation of data poisoning attack on the pairwise ranking algorithms, which can be generally formalized as the dynamic and static games between the ranker and the attacker, and can be modeled as certain kinds of integer programming problems mathematically. To break the computational hurdle of the underlying integer programming problems, we reformulate them into the distributionally robust optimization (DRO) problems, which are computational tractable. Based on such DRO formulations, we propose two efficient poisoning attack algorithms and establish the associated theoretical guarantees including the existence of Nash equilibrium and the generalization ability bounds. The effectiveness of the suggested poisoning attack strategies is demonstrated by a series of toy simulations and several real data experiments. These experimental results show that the proposed methods can significantly reduce the performance of the ranker in the sense that the correlation between the true ranking list and the aggregated results with toxic data can be decreased dramatically. © 2021, CC BY-NC-ND.

关键词： Toys

Generalization bound of gradient descent for non-convex metric learning 20

学校读者我要写书评

暂无评论

Generalization bound of gradient descent for non-convex metr...

Proceedings of the 34th International Conference on Neural Information Processing Systems

作者： Mingzhi Dong Xiaochen Yang Rui Zhu Yujiang Wang Jing-Hao Xue School of Computer Science Fudan University Shanghai China and Shanghai Key Laboratory of Data Science Fudan University Shanghai China and Department of Statistical Science University College London London UK Department of Statistical Science University College London London UK The Business School (formerly Cass) City University of London London UK Department of Computing Imperial College London London UK

ISBN: (纸本)9781713829546

Metric learning aims to learn a distance measure that can benefit distance-based methods such as the nearest neighbor (NN) classifier. While considerable efforts have been made to improve its empirical performance and analyze its generalization ability by focusing on the data structure and model complexity, an unresolved question is how choices of algorithmic parameters, such as the number of training iterations, affect metric learning as it is typically formulated as an optimization problem and nowadays more often as a non-convex problem. In this paper, we theoretically address this question and prove the agnostic Probably Approximately Correct (PAC) learnability for metric learning algorithms with non-convex objective functions optimized via gradient descent (GD); in particular, our theoretical guarantee takes the iteration number into account. We first show that the generalization PAC bound is a sufficient condition for agnostic PAC learnability and this bound can be obtained by ensuring the uniform convergence on a densely concentrated subset of the parameter space. We then show that, for classifiers optimized via GD, their generalizability can be guaranteed if the classifier and loss function are both Lipschitz smooth, and further improved by using fewer iterations. To illustrate and exploit the theoretical findings, we finally propose a novel metric learning method called Smooth Metric and representative Instance LEarning (SMILE), designed to satisfy the Lipschitz smoothness property and learned via GD with an early stopping mechanism for better discriminability and less computational cost of NN.

关键词：

Federated learning for 6G communications: Challenges, methods, and future directions

学校读者我要写书评

暂无评论

arXiv 2020年

作者： Liu, Yi Yuan, Xingliang Xiong, Zehui Kang, Jiawen Wang, Xiaofei Niyato, Dusit School of Data Science of Technology Heilongjiang University Harbin China Faculty of Information Technology Monash University ClaytonVIC3800 Australia School of Computer Science and Engineering Nanyang Technological University Singapore Singapore College of Intelligence and Computing Tianjin University Tianjin China Energy Research Institute Nanyang Technological University Singapore

—As the 5G communication networks are being widely deployed worldwide, both industry and academia have started to move beyond 5G and explore 6G communications. It is generally believed that 6G will be established on ubiquitous Artificial Intelligence (AI) to achieve data-driven Machine Learning (ML) solutions in heterogeneous and massive-scale networks. However, traditional ML techniques require centralized data collection and processing by a central server, which is becoming a bottleneck of large-scale implementation in daily life due to significantly increasing privacy concerns. Federated learning, as an emerging distributed AI approach with privacy preservation nature, is particularly attractive for various wireless applications, especially being treated as one of the vital solutions to achieve ubiquitous AI in 6G. In this article, we first introduce the integration of 6G and federated learning and provide potential federated learning applications for 6G. We then describe key technical challenges, the corresponding federated learning methods, and open problems for future research on federated learning in the context of 6G communications. Copyright © 2020, The Authors. All rights reserved.

关键词： 5G mobile communication systems