检索结果-内蒙古大学图书馆

Journal of Geophysical Research: Machine Learning and Computation 2025年第1期2卷

作者： Husnu Baris Baydargil Jose Eduardo Oliveira Silva Yeon Joo Lee Meeyoung Cha Data Science Group Institute for Basic Science (IBS) Daejeon Republic of Korea Planetary Atmospheres Group Institute for Basic Science (IBS) Daejeon Republic of Korea School of Computing Korea Advanced Institute of Science and Technology (KAIST) Daejeon Republic of Korea Max Planck Institute for Security and Privacy (MPI-SP) Bochum Germany

The atmosphere of Venus features stationary waves of planetary scale, which are believed to be caused by wind flowing over elevated terrains. Detecting these waves can provide valuable insight into atmospheric dynamics. However, manual detection is time-consuming, especially with the increasing volume of new images. To address this, we propose a self-supervised anomaly detection model based on a vector-quantized generative adversarial network to identify and localize stationary atmospheric waves in spacecraft images of Venus. Our model is developed over Akatsuki images of Venus and is trained on smaller cropped images containing features other than stationary waves, allowing it to learn the underlying patterns of normal cloud features. We enhance the model with spatial attention modules, skip connections, and latent space transformation to improve image reconstruction and avoid mixing stationary wave features with artifacts. For inference, we use an overlapping sliding window approach, considering the reconstruction loss of each grid slice to identify anomalies. The model records bounding boxes with high reconstruction loss, localizes stationary waves, and draws the final bounding box. Experiments demonstrate that our model outperforms benchmark models using ultraviolet imaging (UVI) and longwave infrared imaging (LIR) acquired by the Akatsuki Venus orbiter, achieving an area under the curve (AUC) score of 94.78% for UVI and 92.84% for LIR images, and an intersection over union score of 66.53% for UVI and 61.49% for LIR images. The ablation study shows consecutive performance improvements with each added module. Propose a self-supervised model for detecting stationary atmospheric waves on Venus through anomaly detection in Akatsuki images Localize stationary waves by analyzing overlapping image patches, identifying regions with significant original-reconstruction deviations Streamline the identification of stationary waves, eliminating the constraints of date and or

关键词： Venus stationary wave deep learning anomaly detection localization

来源：评论

学校读者我要写书评

暂无评论

MaxStyle: Adversarial Style Composition for Robust Medical Image Segmentation

arXiv

引用

arXiv 2022年

作者： Chen, Chen Li, Zeju Ouyang, Cheng Sinclair, Matt Bai, Wenjia Rueckert, Daniel BioMedIA Group Department of Computing Imperial College London United Kingdom HeartFlow United States Data Science Institute Imperial College London United Kingdom Department of Brain Sciences Imperial College London United Kingdom Klinikum Rechts der Isar Technical University of Munich Germany

Convolutional neural networks (CNNs) have achieved remarkable segmentation accuracy on benchmark datasets where training and test sets are from the same domain, yet their performance can degrade significantly on unseen domains, which hinders the deployment of CNNs in many clinical scenarios. Most existing works improve model out-of-domain (OOD) robustness by collecting multi-domain datasets for training, which is expensive and may not always be feasible due to privacy and logistical issues. In this work, we focus on improving model robustness using a single-domain dataset only. We propose a novel data augmentation framework called MaxStyle, which maximizes the effectiveness of style augmentation for model OOD performance. It attaches an auxiliary style-augmented image decoder to a segmentation network for robust feature learning and data augmentation. Importantly, MaxStyle augments data with improved image style diversity and hardness, by expanding the style space with noise and searching for the worst-case style composition of latent features via adversarial training. With extensive experiments on multiple public cardiac and prostate MR datasets, we demonstrate that MaxStyle leads to significantly improved out-of-distribution robustness against unseen corruptions as well as common distribution shifts across multiple, different, unseen sites and unknown image sequences under both low- and high-training data settings. The code can be found at https://***/cherise215/MaxStyle. © 2022, CC BY.

关键词： Convolutional neural networks

来源：评论

学校读者我要写书评

暂无评论

A motion-based compression algorithm for resource-constrained video camera traps

arXiv

引用

arXiv 2024年

作者： Ratnayake, Malika Nisal Gallon, Lex Toosi, Adel N. Dorin, Alan Agents and Decision-Making Group Dept. of Data Science and AI Faculty of Information Technology Monash University ClaytonVIC3800 Australia Monash e-Research Centre Monash University ClaytonVIC3800 Australia School of Computing and Information Systems Faculty of Engineering and Information Technology The University of Melbourne ParkvilleVIC3052 Australia Dept. of Software Systems and Cybersecurity Faculty of Information Technology Monash University ClaytonVIC3800 Australia

Field-captured video facilitates detailed studies of spatio-temporal aspects of animal locomotion, decision-making and environmental interactions including predator-prey relationships and habitat utilisation. But even though data capture is cheap with mass-produced hardware, storage, processing and transmission overheads provide a hurdle to acquisition of high resolution video from field-situated edge computing devices. Efficient compression algorithms are therefore essential if monitoring is to be conducted on single-board computers in situations where such hurdles must be overcome. Animal motion tracking in the field has unique characteristics that necessitate the use of novel video compression techniques, which may be underexplored or unsuitable in other contexts. In this article, we therefore introduce a new motion analysis-based video compression algorithm specifically designed for camera traps. We implemented and tested this algorithm using a case study of insect-pollinator motion tracking on three popular edge computing platforms. The algorithm identifies and stores only image regions depicting motion relevant to pollination monitoring, reducing overall data size by an average of 87% across diverse test datasets. Our experiments demonstrate the algorithm’s capability to preserve critical information for insect behaviour analysis through both manual observation and automatic analysis of the compressed footage. The method presented in this paper enhances the applicability of low-powered computer vision edge devices to remote, in situ animal motion monitoring, and improves the efficiency of playback during behavioural analyses. Our new software, EcoMotionZip, is available Open Access. Copyright © 2024, The Authors. All rights reserved.

关键词： Digital storage

来源：评论

学校读者我要写书评

暂无评论

Analysing ecological dynamics with relational event models: the case of biological invasions

arXiv

引用

arXiv 2023年

作者： Juozaitiene, Ruta Seebens, Hanno Latombe, Guillaume Essl, Franz Wit, Ernst C. VU Institute of Data Science and Digital Technologies Vilnius Lithuania Vytautas Magnus University Kaunas Lithuania Senckenberg Biodiversity and Climate Research Centre Frankfurt Germany Institute of Evolutionary Biology University of Edinburgh United Kingdom Bioinvasions. Global Chang. Macroecology Group Department of Botany and Biodiversity Research University of Vienna Austria Institute of Computing Università della Svizzera italiana Lugano Switzerland

Spatio-temporal processes play a key role in ecology, from genes to large-scale macroecological and biogeographical processes. Existing methods studying such spatio-temporally structured data either simplify the dynamic structure or the complex interactions of ecological drivers. The aim of this paper is to present a generic method for ecological research that allows analysing spatio-temporal patterns of biological processes at large spatial scales by including the time-varying variables that drive these dynamics. Location Global analysis at the level of 272 regions. Methods We introduce a method called relational event modelling (REM). REM relies on temporal interaction dynamics, that encode sequences of relational events connecting a sender node to a recipient node at a specific point in time. We apply REM to the spread of alien species around the globe between 1880 and 2005, following accidental or deliberate introductions into geographical regions outside of their native range. In this context, a relational event represents the new occurrence of an alien species given its former distribution. Results The application of relational event models to the first reported invasions of 4835 established alien species outside of their native ranges from four major taxonomic groups enables us to unravel the main drivers of the dynamics of the spread of invasive alien species. Combining the alien species first records data with other spatio-temporal information enables us to discover which factors have been responsible for the spread of species across the globe. Besides the usual drivers of species invasions, such as trade, land use and climatic conditions, we also find evidence for species-interconnectedness in alien species spread. Conclusions Relational event models offer the capacity to account for the temporal sequences of ecological events such as biological invasions and to investigate how relationships between these events and potential drivers change over time. © 20

关键词： Geographical regions

来源：评论

学校读者我要写书评

暂无评论

Learning Embeddings for Image Clustering: An Empirical Study of Triplet Loss Approaches

Learning Embeddings for Image Clustering: An Empirical Study...

引用

International Conference on Pattern Recognition

作者： Kalun Ho Janis Keuper Franz-Josef Pfreundt Margret Keuper Data and Web Science Group University of Mannheim Germany Institute for Machine Learning and Analytics (IMLA) Offenburg University Germany Competence Center High Performance Computing Fraunhofer ITWM Kaiserslautern Germany

In this work, we evaluate two different image clustering objectives, k-means clustering and correlation clustering, in the context of Triplet Loss induced feature space embeddings. Specifically, we train a convolutional neural network to learn discriminative features by optimizing two popular versions of the Triplet Loss in order to study their clustering properties under the assumption of noisy labels. Additionally, we propose a new, simple Triplet Loss formulation, which shows desirable properties with respect to formal clustering objectives and outperforms the existing methods. We evaluate all three Triplet loss formulations for K-means and correlation clustering on the CIFAR-10 image classification dataset.

关键词： Correlation Pattern recognition Noise measurement Convolutional neural networks Image classification

来源：评论

学校读者我要写书评

暂无评论

Efficient Low-Resolution Face Recognition via Bridge Distillation

arXiv

引用

arXiv 2024年

作者： Ge, Shiming Zhao, Shengwei Li, Chenyu Zhang, Yu Li, Jia The Institute of Information Engineering Chinese Academy of Sciences Beijing100095 China School of Cyber Security University of Chinese Academy of Sciences Beijing100049 China SenseTime Group Limited 100084 China The State Key Laboratory of Virtual Reality Technology and Systems School of Computer Science and Engineering Beihang University China The Beijing Advanced Innovation Center for Big Data and Brain Computing Beihang University Beijing100191 China The Peng Cheng Laboratory Shenzhen518055 China

Face recognition in the wild is now advancing towards light-weight models, fast inference speed and resolution-adapted capability. In this paper, we propose a bridge distillation approach to turn a complex face model pretrained on private high-resolution faces into a light-weight one for low-resolution face recognition. In our approach, such a cross-dataset resolution-adapted knowledge transfer problem is solved via two-step distillation. In the first step, we conduct cross-dataset distillation to transfer the prior knowledge from private high-resolution faces to public high-resolution faces and generate compact and discriminative features. In the second step, the resolution-adapted distillation is conducted to further transfer the prior knowledge to synthetic low-resolution faces via multi-task learning. By learning low-resolution face representations and mimicking the adapted high-resolution knowledge, a light-weight student model can be constructed with high efficiency and promising accuracy in recognizing low-resolution faces. Experimental results show that the student model performs impressively in recognizing low-resolution faces with only 0.21M parameters and 0.057MB memory. Meanwhile, its speed reaches up to 14,705, 934 and 763 faces per second on GPU, CPU and mobile phone, respectively. Copyright © 2024, The Authors. All rights reserved.

关键词： Multi-task learning

来源：评论

学校读者我要写书评

暂无评论

FedLGMatch: Federated semi-supervised learning via joint local and global pseudo labeling

引用

Knowledge-Based Systems 2025年 320卷

作者： Zhao, Qing Chu, Jielei Li, Zhaoyu Huang, Wei Luo, Zhipeng Li, Tianrui School of Computing and Artificial Intelligence Southwest Jiaotong University Chengdu611756 China Engineering Research Center of Sustainable Urban Intelligent Transportation Ministry of Education Chengdu611756 China National Engineering Laboratory of Integrated Transportation Big Data Application Technology Southwest Jiaotong University Chengdu611756 China Manufacturing Industry Chains Collaboration and Information Support Technology Key Laboratory of Sichuan Province Southwest Jiaotong University Chengdu611756 China China Railway Engineering Group Limited Beijing100039 China China Railway Eryuan Engineering Group Co. Ltd. Sichuan Chengdu610031 China College of Computer and Data Science Fuzhou University China

The bulk of existing Federated Learning (FL) algorithms pay attention to supervised setting and assume that clients have fully labeled data. However, it may be impractical for all clients to obtain plenty of labels due to high annotation costs. Hence, the Federated Semi-Supervised Learning (FSSL) as a promising paradigm has better prospect in many realistic applications (e.g. medical scenario). Under Labels-at-Server scenario, most pseudo labeling based FSSL approaches use only the global model to generate pseudo-labels for unlabeled data, while the local models are ignored. When the local data distribution is much more different from the central server (e.g., Non-IID setting), the generated pseudo-labels may contain much noise, thus, resulting in more serious confirmation bias. To tackle the crucial issue, a novel Federated Semi-Supervised Learning via Joint Local and Global Pseudo Labeling (FedLGMatch) framework is proposed in this paper. The prominent advantage of the proposed FedLGMatch is that it allows local models trained in the last communication round to assist global model in generating pseudo-labels, which successfully emphasizes more clean pseudo-label learning at each client. Experimental results also show that FedLGMatch achieves significant performance improvements than other state-of-the-art models on the standard benchmark datasets. © 2025 Elsevier B.V.

关键词： Semi-supervised learning

来源：评论

学校读者我要写书评

暂无评论

SemRel2024: A Collection of Semantic Textual Relatedness datasets for 13 Languages

arXiv

引用

arXiv 2024年

作者： Ousidhoum, Nedjma Muhammad, Shamsuddeen Hassan Abdalla, Mohamed Abdulmumin, Idris Ahmad, Ibrahim Said Ahuja, Sanchit Aji, Alham Fikri Araujo, Vladimir Ayele, Abinew Ali Baswani, Pavan Beloucif, Meriem Biemann, Chris Bourhim, Sofia De Kock, Christine Dekebo, Genet Shanko Hourrane, Oumaima Kanumolu, Gopichand Madasu, Lokesh Rutunda, Samuel Shrivastava, Manish Solorio, Thamar Surange, Nirmal Tilaye, Hailegnaw Getaneh Vishnubhotla, Krishnapriya Winata, Genta Yimam, Seid Muhie Mohammad, Saif M. Cardiff University United Kingdom Imperial College London United Kingdom Data Science for Social Impact Research Group University of Pretoria South Africa Institute For Experiential AI Northeastern University United States BITS Pilani India MBZUAI United Arab Emirates KU Leuven Belgium Universität Hamburg Language Technology Group Germany Bahir Dar University Faculty of Computing Ethiopia IIIT Hyderabad India Uppsala University Sweden The University of Melbourne Australia Adama Science and Technology University Ethiopia Digital Umuganda Rwanda Kotebe University of Education Ethiopia University of Toronto Canada HKUST Hong Kong National Research Council Canada

Exploring and quantifying semantic relatedness is central to representing language and holds significant implications across various NLP tasks. While earlier NLP research primarily focused on semantic similarity, often within the English language context, we instead investigate the broader phenomenon of semantic relatedness. In this paper, we present SemRel, a new semantic relatedness dataset collection annotated by native speakers across 13 languages: Afrikaans, Algerian Arabic, Amharic, English, Hausa, Hindi, Indonesian, Kinyarwanda, Marathi, Moroccan Arabic, Modern Standard Arabic, Spanish, and Telugu. These languages originate from five distinct language families and are predominantly spoken in Africa and Asia – regions characterised by a relatively limited availability of NLP resources. Each instance in the SemRel datasets is a sentence pair associated with a score that represents the degree of semantic textual relatedness between the two sentences. The scores are obtained using a comparative annotation framework. We describe the data collection and annotation processes, challenges when building the datasets, baseline experiments, and their impact and utility in NLP. Copyright © 2024, The Authors. All rights reserved.

关键词： Natural language processing systems

来源：评论

学校读者我要写书评

暂无评论

Swarm Intelligence with Adaptive Neuro-Fuzzy Inference System-Based Routing Protocol for Clustered Wireless Sensor Networks

引用

Computational Intelligence and Neuroscience 2022年第0期2022卷 7940895页

作者： A-Matarneh, Feras Mohammed Alqaralleh, Bassam A. Y. Aldhaban, Fahad Alqaralleh, Esam A. Kumar, Anil Gupta, Deepak Joshi, Gyanendra Prasad Department of Computer Science University College of Duba University of Tabuk Tabuk71491 Saudi Arabia MIS Department College of Business Administration University of Business and Technology Jeddah21448 Saudi Arabia School of Engineering Princess Sumaya University for Technology Amman11941 Jordan Data Science Research Group School of Computing DIT University Dehradun India Department of Computer Science & Engineering Maharaja Agrasen Institute of Technology Delhi India Department of Computer Science and Engineering Sejong University Seoul05006 Korea Republic of

Wireless sensor network (WSN) comprises numerous compact-sized sensor nodes which are linked to one another. Lifetime maximization of WSN is considered a challenging problem in the design of WSN since its energy-limited capacity of the inbuilt batteries exists in the sensor nodes. Earlier works have focused on the design of clustering and routing techniques to accomplish energy efficiency and thereby result in an increased lifetime of the network. The multihop route selection process can be treated as an NP-hard problem and can be solved by the use of computational intelligence techniques such as fuzzy logic and swarm intelligence (SI) algorithms. With this motivation, this article aims to focus on the design of swarm intelligence with an adaptive neuro-fuzzy inference system-based routing (SI-ANFISR) protocol for clustered WSN. The proposed SI-ANFISR technique aims to determine the cluster heads (CHs) and optimal routes for multihop communication in the network. To accomplish this, the SI-ANFISR technique primarily employs a weighted clustering algorithm to elect CHs and construct clusters. Besides, the SI-ANFISR technique involves the design of an ANFIS model for the selection process, which make use of three input parameters, namely, residual energy, node degree, and node history. In order to optimally adjust the membership function (MF) of the ANFIS model, the squirrel search algorithm (SSA) is utilized. None of the earlier works have used ANFIS with SSA for the routing process. The design of SSA to tune the MFs of the ANFIS model for optimal routing process in WSN shows the novelty of the study. The experimental validation of the SI-ANFISR technique takes place, and the results are inspected under different aspects. The simulation results highlighted the significant performance of the SI-ANFISR technique compared to the recent techniques with a maximum throughput of 43838 kbps and residual energy of 0.4800J, respectively. © 2022 Feras Mohammed A-Matarneh et al.

关键词： Routing protocols

来源：评论

学校读者我要写书评

暂无评论

Motor imagery enhances performance beyond the imagined action

引用

Proceedings of the National Academy of sciences of the United States of America 2025年第20期122卷 e2423642122页

作者： Gippert, Magdalena Shih, Pei-Cheng Heed, Tobias Howard, Ian S. Jamshidi Idaji, Mina Villringer, Arno Sehm, Bernhard Nikulin, Vadim V. Department of Neurology Max Planck Institute for Human Cognitive and Brain Sciences Leipzig 04103 Germany Sony Computer Science Laboratories 141-0022 Tokyo Japan Department of Psychology and Centre for Cognitive Neuroscience University of Salzburg 5020 Salzburg Austria School of Engineering Computing and Mathematics Faculty of Science and Engineering University of Plymouth Plymouth PL4 8AA United Kingdom Machine Learning Group Berlin Institute for the Foundations of Learning and Data 10587 Berlin Germany Machine Learning Group Institute of Software Engineering and Theoretical Computer Science Electrical Engineering and Computer Science Faculty Technical University Berlin 10587 Berlin Germany Department of Neurology Martin Luther University of Halle-Wittenberg Halle (Saale) 06120 Germany

Motor imagery is frequently utilized to improve the performance of specific target movements in sports and rehabilitation. In this study, we show that motor imagery can facilitate learning of not only the imagined target movements but also sequentially linked overt movements. Hybrid sequences comprising imagined and physically executed segments allowed participants to learn specific movement characteristics of the executed segments when they were consistently associated with specific imagined segments. Electrophysiological recordings revealed that the degree of event-related synchronization in the alpha and beta bands during a basic motor imagery task was correlated with imagery-evoked motor learning. Thus, both behavioral and neural evidence indicate that motor imagery's benefits extend beyond the imagined movements, improving performance in linked overt movements. This provides decisive evidence for the functional equivalence of imagined and overt movements and suggests applications for imagery in sports and rehabilitation.

关键词： adaptation force field motor imagery motor learning motor sequence

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：