检索结果-内蒙古大学图书馆

arXiv 2024年

作者： Yu, Wentao Chen, Shuo Tong, Yongxin Gu, Tianlong Gong, Chen School of Computer Science and Engineering Nanjing University of Science and Technology China Center for Advanced Intelligence Project RIKEN Japan State Key Laboratory of Complex & Critical Software Environment Beihang University China Jinan University China Department of Automation Institute of Image Processing and Pattern Recognition Shanghai Jiao Tong University China

Heterogeneity is a fundamental and challenging issue in federated learning, especially for the graph data due to the complex relationships among the graph nodes. To deal with the heterogeneity, lots of existing methods perform the weighted federation based on their calculated similarities between pairwise clients (i.e., subgraphs). However, their inter-subgraph similarities estimated with the outputs of local models are less reliable, because the final outputs of local models may not comprehensively represent the real distribution of subgraph data. In addition, they ignore the critical intra-heterogeneity which usually exists within each subgraph itself. To address these issues, we propose a novel Federated learning method by integrally modeling the Inter-Intra Heterogeneity (FedIIH). For the inter-subgraph relationship, we propose a novel hierarchical variational model to infer the whole distribution of subgraph data in a multi-level form, so that we can accurately characterize the inter-subgraph similarities with the global perspective. For the intra-heterogeneity, we disentangle the subgraph into multiple latent factors and partition the model parameters into multiple parts, where each part corresponds to a single latent factor. Our FedIIH not only properly computes the distribution similarities between subgraphs, but also learns disentangled representations that are robust to irrelevant factors within subgraphs, so that it successfully considers the inter- and intra- heterogeneity simultaneously. Extensive experiments on six homophilic and five heterophilic graph datasets in both non-overlapping and overlapping settings demonstrate the effectiveness of our method when compared with nine state-of-the-art methods. Specifically, FedIIH averagely outperforms the second-best method by a large margin of 5.79% on all heterophilic datasets. Code is available at https://***/blgpb/FedIIH. Copyright © 2024, The Authors. All rights reserved.

关键词： Federated learning

来源：评论

学校读者我要写书评

暂无评论

Leveraging Image Captions for Selective Whole Slide Image Annotation

arXiv

引用

arXiv 2024年

作者： Qiu, Jingna Aubreville, Marc Wilm, Frauke Öttl, Mathias Utz, Jonas Schlereth, Maja Breininger, Katharina Department Artificial Intelligence in Biomedical Engineering FAU Erlangen-Nürnberg Erlangen Germany Technische Hochschule Ingolstadt Ingolstadt Germany Flensburg University of Applied Sciences Flensburg Germany Pattern Recognition Lab Department of Computer Science FAU Erlangen-Nürnberg Erlangen Germany Center for AI and Data Science Universität Würzburg Würzburg Germany

Acquiring annotations for whole slide images (WSIs)-based deep learning tasks, such as creating tissue segmentation masks or detecting mitotic figures, is a laborious process due to the extensive image size and the significant manual work involved in the annotation. This paper focuses on identifying and annotating specific image regions that optimize model training, given a limited annotation budget. While random sampling helps capture data variance by collecting annotation regions throughout the WSI, insufficient data curation may result in an inadequate representation of minority classes. Recent studies proposed diversity sampling to select a set of regions that maximally represent unique characteristics of the WSIs. This is done by pretraining on unlabeled data through self-supervised learning and then clustering all regions in the latent space. However, establishing the optimal number of clusters can be difficult and not all clusters are task-relevant. This paper presents prototype sampling, a new method for annotation region selection. It discovers regions exhibiting typical characteristics of each task-specific class. The process entails recognizing class prototypes from extensive histopathology image-caption databases and detecting unlabeled image regions that resemble these prototypes. Our results show that prototype sampling is more effective than random and diversity sampling in identifying annotation regions with valuable training information, resulting in improved model performance in semantic segmentation and mitotic figure detection tasks. Code is available at https://***/DeepMicroscopy/Prototype-sampling. Copyright © 2024, The Authors. All rights reserved.

关键词： Image annotation

来源：评论

学校读者我要写书评

暂无评论

PARTICLE MULTI-AXIS TRANSFORMER FOR JET TAGGING

arXiv

引用

arXiv 2024年

作者： Usman, Muhammad Shahid, M. Husnain Ejaz, Maheen Hani, Ummay Fatima, Nayab Khan, Abdul Rehman Khan, Asifullah Mirza, Nasir Majid Pattern Recognition Lab Department of Computer & Information Science Pakistan Institute of Engineering & Applied Sciences Nilore Islamabad45650 Pakistan Pakistan Institute of Engineering & Applied Sciences Nilore Islamabad45650 Pakistan Center for Mathematical Sciences Pakistan Institute of Engineering & Applied Sciences Nilore Islamabad45650 Pakistan Department of Physics & Applied Mathematics Pakistan Institute of Engineering & Applied Sciences Nilore Islamabad45650 Pakistan

Jet tagging is an essential categorization problem in high energy physics. In recent times, Deep Learning has not only risen to the challenge of jet tagging but also significantly improved its performance. In this article, we proposed an idea of a new architecture, Particle Multi-Axis transformer (ParMAT) which is a modified version of Particle transformer (ParT). ParMAT contains local and global spatial interactions within a single unit which improves its ability to handle various input lengths. We trained our model on JETCLASS, a publicly available large dataset that contains 100M jets of 10 different classes of particles. By integrating a parallel attention mechanism and pairwise interactions of particles in the attention mechanism, ParMAT achieves robustness and higher accuracy over the ParT and ParticleNet. The scalability of the model to huge datasets and its ability to automatically extract essential features demonstrate its potential for enhancing jet tagging. © 2024, CC BY.

关键词： Deep learning

来源：评论

学校读者我要写书评

暂无评论

LBAA: A novel load balancing mechanism in cloud environments using ant colony optimization and artificial bee colony algorithms

引用

International Journal of Communication Systems 2023年第9期36卷 e5481-e5481页

作者： Mohammadian, Vahid Navimipour, Nima Jafari Hosseinzadeh, Mehdi Darwesh, Aso Department of Computer Engineering Qeshm Branch Islamic Azad University Qeshm Iran Department of Computer Engineering Tabriz Branch Islamic Azad University Tabriz Iran Future Technology Research Center National Yunlin University of Science and Technology Yunlin Douliou64002 Taiwan Pattern Recognition and Machine Learning Lab Gachon University Seongnam Korea Republic of Information Technology Departments University of Human Development Sulaimaniyah Iraq

Recently, cloud computing has been recognized as an effective paradigm for offering an on-demand platform, software services, and an efficient infrastructure to cloud clients. Due to the exponential growth of cloud tasks and the rapidly increasing number of cloud users, scheduling and balancing these tasks among involved heterogeneous virtual machines becomes an Non-deterministic Polynomial hard (NP-hard) optimization problem considering significant constraints, such as high rate of resource usage, low scheduling time, and low implementation cost. Therefore, various meta-heuristic algorithms have been widely used to tackle the issue. The current paper proposes a novel load balancing mechanism using the ant colony optimization and artificial bee colony algorithms, called LBAA, which aims to balance the load division among systems in data centers. The simulation outcomes confirm that our algorithm outperforms previous works regarding response time, imbalance degree, makespan, and resource utilization up to 25%, 15%, 12%, and 10%, respectively. © 2023 John Wiley & Sons Ltd.

关键词： Ant colony optimization

来源：评论

学校读者我要写书评

暂无评论

Hybrid Data-Free Knowledge Distillation

arXiv

引用

arXiv 2024年

作者： Tang, Jialiang Chen, Shuo Gong, Chen School of Computer Science and Engineering Nanjing University of Science and Technology China Key Laboratory of Intelligent Perception and Systems for High-Dimensional Information of Ministry of Education China Jiangsu Key Laboratory of Image and Video Understanding for Social Security China Center for Advanced Intelligence Project RIKEN Japan Department of Automation Institute of Image Processing and Pattern Recognition Shanghai Jiao Tong University China

Data-free knowledge distillation aims to learn a compact student network from a pre-trained large teacher network without using the original training data of the teacher network. Existing collection-based and generation-based methods train student networks by collecting massive real examples and generating synthetic examples, respectively. However, they inevitably become weak in practical scenarios due to the difficulties in gathering or emulating sufficient real-world data. To solve this problem, we propose a novel method called Hybrid Data-Free Distillation (HiDFD), which leverages only a small amount of collected data as well as generates sufficient examples for training student networks. Our HiDFD comprises two primary modules, i.e., the teacher-guided generation and student distillation. The teacher-guided generation module guides a Generative Adversarial Network (GAN) by the teacher network to produce high-quality synthetic examples from very few real-world collected examples. Specifically, we design a feature integration mechanism to prevent the GAN from overfitting and facilitate the reliable representation learning from the teacher network. Meanwhile, we drive a category frequency smoothing technique via the teacher network to balance the generative training of each category. In the student distillation module, we explore a data inflation strategy to properly utilize a blend of real and synthetic data to train the student network via a classifier-sharing-based feature alignment technique. Intensive experiments across multiple benchmarks demonstrate that our HiDFD can achieve state-of-the-art performance using 120 times less collected data than existing methods. Code is available at https://***/tangjialiang97/HiDFD. Copyright © 2024, The Authors. All rights reserved.

关键词： Students

来源：评论

学校读者我要写书评

暂无评论

A survey of the Vision Transformers and their CNN-Transformer based Variants

arXiv

引用

arXiv 2023年

作者： Khan, Asifullah Rauf, Zunaira Sohail, Anabia Khan, Abdul Rehman Asif, Hifsa Asif, Aqsa Farooq, Umair Pattern Recognition Lab Department of Computer & Information Sciences Pakistan Institute of Engineering & Applied Sciences Nilore Islamabad45650 Pakistan Pakistan Institute of Engineering & Applied Sciences Nilore Islamabad45650 Pakistan Center for Mathematical Sciences Pakistan Institute of Engineering & Applied Sciences Nilore Islamabad45650 Pakistan Department of Electrical Engineering and Computer Science Khalifa University of Science and Technology Abu Dhabi United Arab Emirates Air University E-9 Islamabad44230 Pakistan

Vision transformers have become popular as a possible substitute to convolutional neural networks (CNNs) for a variety of computer vision applications. These transformers, with their ability to focus on global relationships in images, offer large learning capacity. However, they may suffer from limited generalization as they do not tend to model local correlation in images. Recently, in vision transformers hybridization of both the convolution operation and self-attention mechanism has emerged, to exploit both the local and global image representations. These hybrid vision transformers, also referred to as CNN-Transformer architectures, have demonstrated remarkable results in vision applications. Given the rapidly growing number of hybrid vision transformers, it has become necessary to provide a taxonomy and explanation of these hybrid architectures. This survey presents a taxonomy of the recent vision transformer architectures and more specifically that of the hybrid vision transformers. Additionally, the key features of these architectures such as the attention mechanisms, positional embeddings, multi-scale processing, and convolution are also discussed. In contrast to the previous survey papers that are primarily focused on individual vision transformer architectures or CNNs, this survey uniquely emphasizes the emerging trend of hybrid vision transformers. By showcasing the potential of hybrid vision transformers to deliver exceptional performance across a range of computer vision tasks, this survey sheds light on the future directions of this rapidly evolving architecture. Copyright © 2023, The Authors. All rights reserved.

关键词： Taxonomies

来源：评论

学校读者我要写书评

暂无评论

A fire hawk optimizer-based energy-efficient clustering scheme in underwater acoustic sensor networks (UASNs)

引用

Ad Hoc Networks 2025年 176卷

作者： Lee, Sang-Woong Alhussein, Musaed Aurangzeb, Khursheed Yousefpoor, Mohammad Sadegh Yousefpoor, Efat Hosseinzadeh, Mehdi Pattern Recognition and Machine Learning Lab School of Computing Gachon University Seongnam13120 Korea Republic of Department of Computer Engineering College of Computer and Information Sciences King Saud University P.O. Box 51178 Riyadh11543 Saudi Arabia Center of Research and Strategic Studies Lebanese French University Kurdistan Region Iraq School of Computer Science Duy Tan University Da Nang Viet Nam Jadara Research Center Jadara University Irbid21110 Jordan

An underwater acoustic sensor network (UASN) is suitable for gathering data from aquatic environments, including lakes, rivers, seas, and oceans. This network faces several issues due to the distinct features of underwater environments and the limitations of acoustic channels. These challenges include energy limitations, unreliable communication links, and dynamic network topologies. Additionally, the difficulty of recharging or replacing batteries in underwater conditions makes energy optimization essential for prolonging the network lifespan. Currently, many energy-efficient approaches in UASNs emphasize node clustering and multi-hop communication, but most of these methods rely on distributed algorithms. This paper introduces a novel energy-efficient clustering framework called FHOEEC (Fire Hawk Optimization-based Energy-Efficient Clustering), which integrates both distributed and centralized strategies. The clustering process is divided into three stages: (1) cluster formation, (2) selection of cluster heads, and (3) cluster maintenance. During the periodic neighbor discovery phase, FHOEEC examines two key aspects: the format of the hello packet and its propagation process. FHOEEC aims to create an energy-efficient, cluster-based network structure. To achieve this, the sink node utilizes the fire hawk optimization (FHO) algorithm to decide on the optimal range and number of clusters. To establish these clusters, a fitness function considers a weighted combination of three sub-functions: intra-cluster and inter-cluster distances, the proportion of isolated clusters compared to others, and cluster density. In the final stage, intra-cluster and inter-cluster communication paths are established by focusing on energy balance. This ensures that nodes with energy levels below a specified threshold are excluded from serving as intermediate nodes. Simulation results and performance evaluations show that FHOEEC outperforms three existing clustering methods–CCCS, GTC, and

关键词： Clustering algorithms

来源：评论

学校读者我要写书评

暂无评论

Hybrid Multi-Task Learning for End-To-End Multimodal Emotion recognition

Hybrid Multi-Task Learning for End-To-End Multimodal Emotion...

引用

Asia-Pacific Signal and Information Processing Association Annual Summit and Conference (APSIPA)

作者： Junjie Chen Yongwei Li Ziping Zhao Xuefei Liu Zhengqi Wen Jianhua Tao College of Computer and Information Engineering Tianjin Normal University Tianjin China National Laboratory of Pattern Recognition Institute of Automation Chinese Academy of Sciences Beijing China Department of Automation Tsinghua University Beijing China Beijing National Research Center for Information Science and Technology Tsinghua University Beijing China

Multimodal emotion recognition plays a pivotal role in the advancement of natural human-computer interaction systems. Recent studies have attempted to apply multi-task learning to emotion recognition. However, the multi-task shared feature extractor of traditional methods needs to integrate the feature representations of different tasks, which may lead to the feature extractor failing to focus on the learning of emotion representations. To address this problem, we propose a hybrid multi-task learning framework for end-to-end multimodal emotion recognition, in which the primary task is emotion classification, and the auxiliary tasks are emotion regression and gender classification. This framework consists of two networks specialized in gender and emotion recognition, where the latter transfers knowledge from the former through our proposed Deep Aggregation LSTM (DA-LSTM). The DA-LSTM could more precisely capture emotional information in discourse by aggregating emotion and gender feature extractors. Experimental results on a commonly used dataset IEMOCAP demonstrate the effectiveness of our proposed method.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Retinal blood flow speed quantification at the capillary level using temporal autocorrelation fitting OCTA

arXiv

引用

arXiv 2023年

作者： Hwang, Yunchan Won, Jungeun Yaghy, Antonio Takahashi, Hiroyuki Girgis, Jessica M. Lam, Kenneth Chen, Siyu Moult, Eric M. Ploner, Stefan B. Maier, Andreas Waheed, Nadia K. Fujimoto, James G. Department of Electrical Engineering and Computer Science Research Laboratory of Electronics Massachusetts Institute of Technology CambridgeMA02139 United States New England Eye Center Tufts Medical Center BostonMA02116 United States Pattern Recognition Lab Friedrich-Alexander-Universität Erlangen-Nürnberg Erlangen Germany

Optical coherence tomography angiography (OCTA) can visualize vasculature structures, but provides limited information about the blood flow speeds. Here, we present a second generation variable interscan time analysis (VISTA) OCTA, which evaluates a quantitative surrogate marker for blood flow speed in vasculature. At the capillary level, spatially compiled OCTA and a simple temporal autocorrelation model, ρ(τ) = exp(-ατ), were used to evaluate a temporal autocorrelation decay constant, α, as the blood flow speed marker. A 600 kHz A-scan rate swept-source provides short interscan time OCTA and fine A-scan spacing acquisition, while maintaining multi mm2field of views for human retinal imaging. We demonstrate the cardiac pulsatility and repeatability of α measured with VISTA. We show different α for different retinal capillary plexuses in healthy eyes and present representative VISTA OCTA of eyes with diabetic retinopathy. Copyright © 2023, The Authors. All rights reserved.

关键词： Optical tomography

来源：评论

学校读者我要写书评

暂无评论

Skinscan: 3D Dermatologic Diagnosis and Documentation with Commodity Devices 55

Skinscan: 3D Dermatologic Diagnosis and Documentation with C...

引用

55th Asilomar Conference on Signals, Systems and computers, ACSSC 2021

作者： Nau, Merlin A. Schiffers, Florian Li, Yunhao Xu, Bingjie Maier, Andreas Tumblin, Jack Walton, Marc Katsaggelos, Aggelos K. Willomitzer, Florian Cossairt, Oliver Northwestern University Department of Computer Science Evanston United States Center for Scientific Studies in the Arts Northwestern University Evanston United States Department of Electrical and Computer Engineering Northwestern University Evanston United States Pattern Recognition Lab Friedrich-Alexander-Universität Erlangen-Nürnberg Germany Department of Radiology Northwestern University Chicago United States

ISBN: (纸本)9781665458283

Computational photography has become a valuable field of interest for dermatologists. Current telemedical approaches mainly use two-dimensional (2D) color imagery, which cannot always capture sufficient information for the physician. In clinical practice dedicated imaging systems can acquire valuable three-dimensional (3D) data to improve the patients outcome [1], [2]. The major drawback of clinical imaging systems is the price and the availability to the broad audience. We tackle this problem by providing an open-source software framework. The framework uses a photometric stereo-inspired gradient illumination technique, enabling detailed 3D measurements of fine skin structures, like fingerprints. Especially in vastly populated or underdeveloped areas, our system could show benefits for initial diagnosis and documenting the evolution of skin diseases. © 2021 IEEE.

关键词： Open source software

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：