检索结果-内蒙古大学图书馆

arXiv 2022年

作者： Zhang, Dan Zheng, Rui Gadeng, Luosang Yang, Pei School of Information and Engineering Minzu University of China Beijing100081 China Department of Information Science and Technology Tibet University Lhasa850012 China Department of Computer Technology and Application Qinghai University Xining810016 China

This paper addresses the task of semantic segmentation in computer vision, aiming to achieve precise pixel-wise classification. We investigate the joint training of models for semantic edge detection and semantic segmentation, which has shown promise. However, implicit cross-task consistency learning in multi-task networks is limited. To address this, we propose a novel "decoupled cross-task consistency loss" that explicitly enhances cross-task consistency. Our semantic segmentation network, TriangleNet, achieves a substantial 2.88% improvement over the Baseline in mean Intersection over Union (mIoU) on the Cityscapes test set. Notably, TriangleNet operates at 77.4% mIoU/46.2 FPS on Cityscapes, showcasing real-time inference capabilities at full resolution. With multi-scale inference, performance is further enhanced to 77.8%. Furthermore, TriangleNet consistently outperforms the Baseline on the FloodNet dataset, demonstrating its robust generalization capabilities. The proposed method underscores the significance of multi-task learning and explicit cross-task consistency enhancement for advancing semantic segmentation and highlights the potential of multitasking in real-time semantic segmentation. Copyright © 2022, 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

From Few to More: Scribble-based Medical Image Segmentation via Masked Context Modeling and Continuous Pseudo Labels

arXiv

引用

arXiv 2024年

作者： Wang, Zhisong Ye, Yiwen Chen, Ziyang Shu, Minglei Xia, Yong National Engineering Laboratory for Integrated Aero-Space-Ground-Ocean Big Data Application Technology School of Computer Science and Engineering Northwestern Polytechnical University China Shandong Artificial Intelligence Institute Qilu University of Technology Shandong Academy of Sciences China Ningbo Institute of Northwestern Polytechnical University Ningbo315048 China Research & Development Institute of Northwestern Polytechnical University in Shenzhen Shenzhen518057 China

Scribble-based weakly supervised segmentation techniques offer comparable performance to fully supervised methods while significantly reducing annotation costs, making them an appealing alternative. Existing methods often rely on auxiliary tasks to enforce semantic consistency and use hard pseudo labels for supervision. However, these methods often overlook the unique requirements of models trained with sparse annotations. Since the model must predict pixel-wise segmentation maps with limited annotations, the ability to handle varying levels of annotation richness is critical. In this paper, we adopt the principle of ‘from few to more’ and propose MaCo, a weakly supervised framework designed for medical image segmentation. MaCo employs masked context modeling (MCM) and continuous pseudo labels (CPL). MCM uses an attention-based masking strategy to disrupt the input image, compelling the model’s predictions to remain consistent with those of the original image. CPL converts scribble annotations into continuous pixel-wise labels by applying an exponential decay function to distance maps, resulting in continuous maps that represent the confidence of each pixel belonging to a specific category, rather than using hard pseudo labels. We evaluate MaCo against other weakly supervised methods using three public datasets. The results indicate that MaCo outperforms competing methods across all datasets, setting a new record in weakly supervised medical image segmentation. Copyright © 2024, The Authors. All rights reserved.

关键词： Pixels

来源：评论

学校读者我要写书评

暂无评论

Enhancing Visible-Infrared Person Re-identification with Modality- and Instance-aware Visual Prompt Learning

arXiv

引用

arXiv 2024年

作者： Wu, Ruiqi Jiao, Bingliang Wang, Wenxuan Liu, Meng Wang, Peng School of Computer Science Northwestern Polytechnical University Shaanxi Xi’an China Ningbo Institute Northwestern Polytechnical University Zhejiang Ningbo China National Engineering Laboratory Integrated Aero-Space-Ground-Ocean Big Data Application Technology Shaanxi Xi’an China Honors College Northwestern Polytechnical University Shaanxi Xi’an China School of Electronics and Information Northwestern Polytechnical University Shaanxi Xi’an China

The Visible-Infrared Person Re-identification (VI ReID) aims to match visible and infrared images of the same pedestrians across non-overlapped camera views. These two input modalities contain both invariant information, such as shape, and modality-specific details, such as color. An ideal model should utilize valuable information from both modalities during training for enhanced representational capability. However, the gap caused by modality-specific information poses substantial challenges for the VI ReID model to handle distinct modality inputs simultaneously. To address this, we introduce the Modality-aware and Instance-aware Visual Prompts (MIP) network in our work, designed to effectively utilize both invariant and specific information for identification. Specifically, our MIP model is built on the transformer architecture. In this model, we have designed a series of modality-specific prompts, which could enable our model to adapt to and make use of the specific information inherent in different modality inputs, thereby reducing the interference caused by the modality gap and achieving better identification. Besides, we also employ each pedestrian feature to construct a group of instance-specific prompts. These customized prompts are responsible for guiding our model to adapt to each pedestrian instance dynamically, thereby capturing identity-level discriminative clues for identification. Through extensive experiments on SYSU-MM01 and RegDB datasets, the effectiveness of both our designed modules is evaluated. Additionally, our proposed MIP performs better than most state-of-the-art methods. Copyright © 2024, The Authors. All rights reserved.

关键词： Infrared imaging

来源：评论

学校读者我要写书评

暂无评论

Utilizing Anomaly Detection Methods for Identifying Fraudulent Activities in Credit Card Transactions

Utilizing Anomaly Detection Methods for Identifying Fraudule...

引用

Advances in Computing, Communication and Networking (ICAC2N), International Conference on

作者： N. Siva Rama Krishna Prasad Amit Gangopadhyay R. Prabakaran Nilamadhab Mishra D. Shyam Prasad Sneha Kapoor Dept. of CSE Saveetha School of Engineering Chennai India Dept. of ECE Mohan Babu University Tirupati India Dept. of Computer Application Arignar Anna Institute of Science and Technology India Dept. of CSE VIT Bhopal University Bhopal India Dept. of Electronics & Instrumentation Engineering CVR College of Engineering Hyderabad India Dept of CSE Swami Vivekanand Subharti University Meerut India

ISBN: (数字)9798350356816

ISBN: (纸本)9798350356823

Anomaly detection involves identifying unusual occurrences that could signal potential issues, such as security breaches, system failures, financial fraud, structural defects, or medical errors. In the context of digital finance, credit card fraud has become a significant concern, with fraudulent transactions often designed to appear legitimate. To address this, we employ the Synthetic Minority Oversampling Technique (SMOTE) to balance the dataset during sampling, and use the ARIMA model for time series forecasting to ensure accurate results. This research explores various fraud detection techniques and models, including K-Nearest Neighbors (KNN), Random Forest, Support Vector Classifier (SVC), and Decision Trees. We evaluate and compare the performance of these models to determine which offers the highest accuracy in detecting fraud.

关键词： Machine learning algorithms Time series analysis Static VAr compensators Nearest neighbor methods Credit cards Vectors Fraud Decision trees Security Random forests

来源：评论

学校读者我要写书评

暂无评论

Stream Attention Based U-Net for L3DAS23 Challenge

Stream Attention Based U-Net for L3DAS23 Challenge

引用

International Conference on Acoustics, Speech, and Signal Processing (ICASSP)

作者： Honglong Wang Yanjie Fu Junjie Li Meng Ge Longbiao Wang Xinyuan Qian Tianjin Key Laboratory of Cognitive Computing and Application College of Intelligence and Computing Tianjin University Tianjin China The Chinese University of Hong Kong Shenzhen China Huiyan Technology (Tianjin) Co. Ltd Tianjin China School of Computer and Communication Engineering University of Science and Technology Beijing Beijing China

Machine learning applications of 3D audio are gaining increasing interest in recent years. In this paper, we propose a stream attention based U-Net to remove background noise and reverberation based on ICASSP Signal Processing Grand Challenge 2023: L3DAS23 Challenge 1 Audio-only track task1 3D Speech Enhancement. Results show that proposed method achieves superior performance than the official baseline model.

关键词： Adaptation models Solid modeling Three-dimensional displays Machine learning Speech enhancement Signal processing 3D audio

来源：评论

学校读者我要写书评

暂无评论

Methodology,progress and challenges of geoscience knowledge graph in International Big science Program of Deep-Time Digital Earth

引用

Journal of Geographical sciences 2025年第5期35卷 1132-1156页

作者： ZHU Yunqiang WANG Qiang WANG Shu SUN Kai WANG Xinbing LV Hairong HU Xiumian ZHANG Jie WANG Bin QIU Qinjun YANG Jie ZHOU Chenghu State Key Laboratory of Resources and Environmental Information System Institute of Geographic Sciences and Natural Resources ResearchCASBeijing 100101China Jiangsu Center for Collaborative Innovation in Geographical Information Resource Development and Application Nanjing 210023China University of Chinese Academy of Sciences Beijing 100049China School of Electronic Information and Electrical EngineeringShanghai Jiao Tong UniversityShanghai 200240China Department of Automation Tsinghua UniversityBeijing 100084China State Key Laboratory for Mineral Deposits Research School of Earth Sciences and EngineeringNanjing UniversityNanjing 210023China State Key Laboratory of Information Photonics and Optical Communications Beijing University of Posts and TelecommunicationsBeijing 100876China Command Center of Natural Resources Comprehensive Survey China Geological SurveyBeijing 100055China School of Computer Science China University of GeosciencesWuhan 430074China

Deep-time Earth research plays a pivotal role in deciphering the rates,patterns,and mechanisms of Earth's evolutionary processes throughout geological history,providing essential scientific foundations for climate prediction,natural resource exploration,and sustainable planetary *** advance Deep-time Earth research in the era of big data and artificial intelligence,the International Union of Geological sciences initiated the“Deeptime Digital Earth International Big science Program”(DDE)in *** the core of this ambitious program lies the development of geoscience knowledge graphs,serving as a transformative knowledge infrastructure that enables the integration,sharing,mining,and analysis of heterogeneous geoscience big *** DDE knowledge graph initiative has made significant strides in three critical dimensions:(1)establishing a unified knowledge structure across geoscience disciplines that ensures consistent representation of geological entities and their interrelationships through standardized ontologies and semantic frameworks;(2)developing a robust and scalable software infrastructure capable of supporting both expert-driven and machine-assisted knowledge engineering for large-scale graph construction and management;(3)implementing a comprehensive three-tiered architecture encompassing basic,discipline-specific,and application-oriented knowledge graphs,spanning approximately 20 geoscience *** its open knowledge framework and international collaborative network,this initiative has fostered multinational research collaborations,establishing a robust foundation for next-generation geoscience research while propelling the discipline toward FAIR(Findable,Accessible,Interoperable,Reusable)data practices in deep-time Earth systems research.

关键词： deep-time Earth geoscience knowledge graph Deep-time Digital Earth International Big science Program

来源：评论

学校读者我要写书评

暂无评论

Texture-enhanced Light Field Super-resolution with Spatio-Angular Decomposition Kernels

arXiv

引用

arXiv 2021年

作者： Hu, Zexi Chen, Xiaoming Wing, Henry Yeung, Fung Chung, Yuk Ying Chen, Zhibo School of Computer Science University of Sydney Australia School of Computer Science and Engineering Beijing Technology and Business University China CAS Key Laboratory of Technology in Geo-spatial Information Processing and Application System University of Science and Technology of China China

Despite the recent progress in light field super-resolution (LFSR) achieved by convolutional neural networks, the correlation information of light field (LF) images has not been sufficiently studied and exploited due to the complexity of 4D LF data. To cope with such high-dimensional LF data, most of the existing LFSR methods resorted to decomposing it into lower dimensions and subsequently performing optimization on the decomposed sub-spaces. However, these methods are inherently limited as they neglected the characteristics of the decomposition operations and only utilized a limited set of LF sub-spaces ending up failing to sufficiently extract spatio-angular features and leading to a performance bottleneck. To overcome these limitations, in this paper, we comprehensively discover the potentials of LF decomposition and propose a novel concept of decomposition kernels. In particular, we systematically unify the decomposition operations of various sub-spaces into a series of such decomposition kernels, which are incorporated into our proposed Decomposition Kernel Network (DKNet) for comprehensive spatio-angular feature extraction. The proposed DKNet is experimentally verified to achieve considerable improvements compared with the state-of-the-art methods. To further improve DKNet in producing more visually pleasing LFSR results, based on the VGG network, we propose a LFVGG loss to guide the Texture-Enhanced DKNet (TE-DKNet) to generate rich authentic textures and enhance LF images’ visual quality significantly. We also propose an indirect evaluation metric by taking advantage of LF material recognition to objectively assess the perceptual enhancement brought by the LFVGG loss. Copyright © 2021, The Authors. All rights reserved.

关键词： Optical resolving power

来源：评论

学校读者我要写书评

暂无评论

An Auxiliary Industrial Equipment Maintenance System Using Mixed Reality

An Auxiliary Industrial Equipment Maintenance System Using M...

引用

International Conference on Industrial engineering and applications (ICIEA)

作者： Xia Su Zheng Cheng Bin Luo School of Automation Engineering University of Electronic Science and Technology of China Chengdu China Institute of Computer Application China Academy of Engineering Physics Mianyang China

ISBN: (纸本)9781665428958;9781665428965

The intellectualization of modern industrial equipment presents a great challenge to its maintenance. The traditional maintenance of equipment requires the repairer to reference related manual, resulting in low maintenance efficiency. And the attempt based on the Virtual Reality can not produce the real and operable experience. To solve the problems, we proposes an auxiliary equipment maintenance system based on Mixed Reality technology that superposes CAD model and other virtual information to the actual equipment using HoloLens. We take the maintenance of a gasoline engine as an example, mainly including troubleshooting, maintenance guidance and equipment part training, where users only need to follow the steps set by the system, and the experiment about system evaluation shows that it makes equipment maintenance work more simple, intuitive, convenient and efficient.

关键词： Training Visualization Solid modeling Mixed reality Virtual reality Manuals Maintenance engineering

来源：评论

学校读者我要写书评

暂无评论

A Multi-Objective Evolutionary Algorithm Based on Indicator and Performing Local Searches

A Multi-Objective Evolutionary Algorithm Based on Indicator ...

引用

Information science and Education (ICISE-IE), International Conference on

作者： Hanning Chen Xiangrui Zeng Kun Jia Yabao Hu Guopeng Wang School of Computer Science and technology Tiangong University Tianjin China Engineering Research Center of Integration and Application of Digital Learning Technology Ministry of Education Beijing China School of Artificial Intelligence Tiangong University Tianjin China Jingwei Textile Machinery Co. Ltd Beijing China College of Artificial Intelligence University of Science and Technology Tianjin China The Open University of China

The indicator-based multi-objective optimization evolutionary algorithm has gained significant attention for its strong performance across various optimization problems. We draw on the advantages and try to make improvements in the environmental selection process based on different selection criteria. From this, we developed a distinctive multi-objective evolutionary algorithm that based on indicator and performing local searches, namely INLS. The INLS algorithm includes a novel selection mechanism that does not rely on weight vectors, which employs a strategy choosing solutions with relatively poor convergence but good diversity to perturb the decision variables of the selected solutions, aiming to explore and discover solutions that demonstrate enhanced convergence and diversity characteristics. The experimental results obtained from conducting tests on the ZDT and DTLZ test suites provide clear evidence of the remarkable performance exhibited by the proposed INLS in comparison to various other well-known MOEAs. These results serve to underscore the competitiveness of the proposed method.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Improved Polar Complex Exponential Transform for Robust Local Image Description

SSRN

引用

SSRN 2022年

作者： Yang, Zhanlong Yang, Linzhi Chen, Geng Yap, Pew-Thian School of Marine Science and Technology Northwestern Polytechnical University Xi’an China National Engineering Laboratory for Integrated Aero-Space-Ground-Ocean Big Data Application Technology School of Computer Science and Engineering Northwestern Polytechnical University Xi’an China University of North Carolina Chapel HillNC United States

Image description via robust local descriptors plays a vital role in a large number of image representation and matching applications. In this paper, we propose a novel distinctive local image descriptor that is based on the phase and amplitude information of Polar Complex Exponential Transform (PCET). The proposed descriptor, called IPCET (Improved PCET), is robust to the common photometric transformations (e.g., illumination, noise, JPEG compression, and blur) and geometric transformations (e.g., scaling, rotation, translation, and significant affine distortion). We perform extensive experiments to compare our IPCET descriptor with five most cutting-edge region descriptors (i.e., SIFT, Zernike Moment, GLOH, PCA-SIFT, and SURF). Experimental results demonstrate that our IPCET descriptor outperforms cutting-edge moment-based descriptors. © 2022, The Authors. All rights reserved.

关键词： Image enhancement

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：