检索结果-内蒙古大学图书馆

arXiv 2022年

作者： Chen, Geng Liu, Si-Jie Sun, Yu-Jia Ji, Ge-Peng Wu, Ya-Feng Zhou, Tao Northwestern Polytechnical University Xi’an710072 China National Engineering Laboratory for Integrated Aero-Space-Ground-Ocean Big Data Application Technology School of Computer Science and Engineering China Data Processing Center School of Power and Energy China Key Laboratory of System Control and Information Processing Ministry of Education Shanghai200240 China School of Computer Science and Engineering Nanjing University of Science and Technology Nanjing210094 China School of Computer Science Inner Mongolia University Hohhot010021 China Artificial Intelligence Institute School of Computer Science Wuhan University Wuhan430072 China

Camouflaged object detection (COD) aims to identify the objects that conceal themselves in natural scenes. Accurate COD suffers from a number of challenges associated with low boundary contrast and the large variation of object appearances, e.g., object size and shape. To address these challenges, we propose a novel Context-aware Cross-level Fusion Network (C2F-Net), which fuses context-aware cross-level features for accurately identifying camouflaged objects. Specifically, we compute informative attention coefficients from multi-level features with our Attention-induced Cross-level Fusion Module (ACFM), which further integrates the features under the guidance of attention coefficients. We then propose a Dual-branch Global Context Module (DGCM) to refine the fused features for informative feature representations by exploiting rich global context information. Multiple ACFMs and DGCMs are integrated in a cascaded manner for generating a coarse prediction from high-level features. The coarse prediction acts as an attention map to refine the low-level features before passing them to our Camouflage Inference Module (CIM) to generate the final prediction. We perform extensive experiments on three widely used benchmark datasets and compare C2F-Net with state-of-the-art (SOTA) models. The results show that C2F-Net is an effective COD model and outperforms SOTA models remarkably. Further, an evaluation on polyp segmentation datasets demonstrates the promising potentials of our C2F-Net in COD downstream applications. Our code is publicly available at: https://***/Ben57882/C2FNet-TSCVT. Copyright © 2022, The Authors. All rights reserved.

关键词： Object detection

来源：评论

学校读者我要写书评

暂无评论

iGniter: Interference-Aware GPU Resource Provisioning for Predictable DNN Inference in the Cloud

arXiv

引用

arXiv 2022年

作者： Xu, Fei Xu, Jianian Chen, Jiabin Chen, Li Shang, Ruitao Zhou, Zhi Liu, Fangming The Shanghai Key Laboratory of Multidimensional Information Processing School of Computer Science and Technology East China Normal University 3663 N. Zhongshan Road Shanghai200062 China The School of Computing and Informatics University of Louisiana at Lafayette 301 East Lewis Street LafayetteLA70504 United States The Guangdong Key Laboratory of Big Data Analysis and Processing School of Computer Science and Engineering Sun Yat-sen University 132 E. Waihuan Road Guangzhou510006 China The National Engineering Research Center for Big Data Technology and System The Services Computing Technology and System Lab Cluster and Grid Computing Lab School of Computer Science and Technology Huazhong University of Science and Technology 1037 Luoyu Road Wuhan430074 China

GPUs are essential to accelerating the latency-sensitive deep neural network (DNN) inference workloads in cloud datacenters. To fully utilize GPU resources, spatial sharing of GPUs among co-located DNN inference workloads becomes increasingly compelling. However, GPU sharing inevitably brings severe performance interference among co-located inference workloads, as motivated by an empirical measurement study of DNN inference on EC2 GPU instances. While existing works on guaranteeing inference performance service level objectives (SLOs) focus on either temporal sharing of GPUs or reactive GPU resource scaling and inference migration techniques, how to proactively mitigate such severe performance interference has received comparatively little attention. In this paper, we propose iGniter, an interference-aware GPU resource provisioning framework for cost-efficiently achieving predictable DNN inference in the cloud. iGniter is comprised of two key components: (1) a lightweight DNN inference performance model, which leverages the system and workload metrics that are practically accessible to capture the performance interference;(2) A cost-efficient GPU resource provisioning strategy that jointly optimizes the GPU resource allocation and adaptive batching based on our inference performance model, with the aim of achieving predictable performance of DNN inference workloads. We implement a prototype of iGniter based on the NVIDIA Triton inference server hosted on EC2 GPU instances. Extensive prototype experiments on four representative DNN models and datasets demonstrate that iGniter can guarantee the performance SLOs of DNN inference workloads with practically acceptable runtime overhead, while saving the monetary cost by up to 25% in comparison to the state-of-the-art GPU resource provisioning strategies. Copyright © 2022, The Authors. All rights reserved.

关键词： Deep neural networks

来源：评论

学校读者我要写书评

暂无评论

A cross Transformer for image denoising

arXiv

引用

arXiv 2023年

作者： Tian, Chunwei Zheng, Menghua Zuo, Wangmeng Zhang, Shichao Zhang, Yanning Lin, Chia-Wen School of Software Northwestern Polytechnical University Shaanxi Xi’an710129 China National Engineering Laboratory for Integrated Aero-Space-Ground-Ocean Big Data Application Technology Shaanxi Xi’an710129 China School of Computer Science and Technology Harbin Institute of Technology Heilongjiang Harbin150001 China Peng Cheng Laboratory Shenzhen518055 China School of Computer Science and Engineering Central South University Hunan Changsha410083 China School of Computer Science Northwestern Polytechnical University Shaanxi Xi’an710129 China Department of Electrical Engineering The Institute of Communications Engineering National Tsing Hua University Hsinchu30013 Taiwan

Deep convolutional neural networks (CNNs) depend on feedforward and feedback ways to obtain good performance in image denoising. However, how to obtain effective structural information via CNNs to efficiently represent given noisy images is key for complex scenes. In this paper, we propose a cross Transformer denoising CNN (CTNet) with a serial block (SB), a parallel block (PB), and a residual block (RB) to obtain clean images for complex scenes. A SB uses an enhanced residual architecture to deeply search structural information for image denoising. To avoid loss of key information, PB uses three heterogeneous networks to implement multiple interactions of multi-level features to broadly search for extra information for improving the adaptability of an obtained denoiser for complex scenes. Also, to improve denoising performance, Transformer mechanisms are embedded into the SB and PB to extract complementary salient features for effectively removing noise in terms of pixel relations. Finally, a RB is applied to acquire clean images. Experiments illustrate that our CTNet is superior to some popular denoising methods in terms of real and synthetic image denoising. It is suitable to mobile digital devices, i.e., phones. Codes can be obtained at https://***/hellloxiaotian/CTNet. Copyright © 2023, The Authors. All rights reserved.

关键词： Image denoising

来源：评论

学校读者我要写书评

暂无评论

Federated Learning for Medical Image Classification: Advances, Challenges and Opportunities

SSRN

引用

SSRN 2023年

作者： Zhang, Xiaobo Zhao, Xiaole Wu, Yunyang Zheng, Hailong Li, Yang School of Computing and Artificial Intelligence Southwest Jiaotong University Chengdu611756 China Artificial Intelligence Research Institute Southwest Jiaotong University Chengdu611756 China National Engineering Laboratory of Integrated Transportation Big Data Application Technology Southwest Jiaotong University Chengdu611756 China Engineering Research Center of Sustainable Urban Intelligent Transportation Ministry of Education China School of Automation Science and Electrical Engineering Beihang University Beijing100191 China

Medical images are private integrations comprising private patient information owned by various hospitals and relevant research institutes, and the generated image data can be utilized to infer physical health conditions. In recent years, more and more AI researchers have used medical images as datasets for their analysis purposes, which will cause relevant personnel to worry about their privacy. As a distributed machine learning framework, federated learning can effectively solve the problem of data privacy. It participates in and completes model training without sharing personal data, with strong universality and good results. In this work, Computed Tomography (CT), Magnetic Resonance Imaging (MRI), Wilhelm Conrad Röntgen (X-Ray) as well as other typical medical imaging modes are used as research objects to summarize, analyze and look forward to the previous work related to federal learning in the field of medical image analysis. On the one hand, this survey classifies and compares the existing federal learning framework and algorithm for different medical image datasets;on the other hand, it discusses the relevant federal studies that are widely used in medical images, analyses the problems that need to be solved in the field of medical images, and looks forward to future studies. © 2023, The Authors. All rights reserved.

关键词： Medical imaging

来源：评论

学校读者我要写书评

暂无评论

A dynamic OD prediction approach for urban networks based on automatic number plate recognition data

引用

Transportation Research Procedia 2020年 47卷 601-608页

作者： Jing Liu Fangfang Zheng Henk J. van Zuylen Jie Li School of Transportation and Logistics Southwest Jiaotong University Western Hi-tech Zone Chengdu Sichuan 611756 P.R. China National Engineering Laboratory of Integrated Transportation Big Data Application Technology Southwest Jiaotong University Western Hi-tech Zone Chengdu Sichuan 611756 P.R. China Civil Engineering College Hunan University Lushan South Road 410082 Changsha Hunan Province P.R. China Transport and Planning Department Delft University of Technology P.O. Box 5048 2600 GA Delft the Netherlands

OD flows provide important information for traffic management and planning. The prediction of dynamic OD matrices gives the possibility to apply anticipatory traffic management measures. In this paper, we propose an OD prediction approach based on the data obtained by Automated Number Plate Recognition (ANPR) cameras. The principal component analysis (PCA) is applied to reduce the dimension of the original OD matrices and to separate the main structure patterns from the noisier components. A state-space model is established for the main structure patterns and the structure deviations, and is incorporated in the Kalman filter framework to make predictions. We further propose three K-Nearest Neighbour (K-NN) based long-term pattern recognition approaches. The proposed approaches are validated with field ANPR data from Changsha city, P.R. China. The results show that the observed OD flows can be accurately predicted by our proposed approaches. Which prediction method performs best depends on the quality of the available data: for regular, periodic OD matrices the Kalman filter is better, for irregular OD matrices the pattern recognition that looks at different time periods in the historical data, gives better results.

关键词： OD matrix prediction principal component analysis state-space kalman filter model pattern recognition

来源：评论

学校读者我要写书评

暂无评论

How Does Knowledge Graph Embedding Extrapolate to Unseen data: A Semantic Evidence View

arXiv

引用

arXiv 2021年

作者： Li, Ren Cao, Yanan Zhu, Qiannan Bi, Guanqun Fang, Fang Liu, Yi Li, Qian Institute of Information Engineering Chinese Academy of Sciences China School of Cyber Security University of Chinese Academy of Sciences China Gaoling School of Artificial Intelligence Renmin University of China China Beijing Key Laboratory of Big Data Management and Analysis Methods China National Computer Network Emergency Response Technical Team Coordination Center of China China University of Technology Sydney Australia

Knowledge Graph Embedding (KGE) aims to learn representations for entities and relations. Most KGE models have gained great success, especially on extrapolation scenarios. Specifically, given an unseen triple (h, r, t), a trained model can still correctly predict t from (h, r,?), or h from (?, r, t), such extrapolation ability is impressive. However, most existing KGE works focus on the design of delicate triple modeling function, which mainly tells us how to measure the plausibility of observed triples, but offers limited explanation of why the methods can extrapolate to unseen data, and what are the important factors to help KGE extrapolate. Therefore in this work, we attempt to study the KGE extrapolation of two problems: 1. How does KGE extrapolate to unseen data? 2. How to design the KGE model with better extrapolation ability? For the problem 1, we first discuss the impact factors for extrapolation and from relation, entity and triple level respectively, propose three Semantic Evidences (SEs), which can be observed from train set and provide important semantic information for extrapolation. Then we verify the effectiveness of SEs through extensive experiments on several typical KGE methods. For the problem 2, to make better use of the three levels of SE, we propose a novel GNN-based KGE model, called Semantic Evidence aware Graph Neural Network (SE-GNN). In SE-GNN, each level of SE is modeled explicitly by the corresponding neighbor pattern, and merged sufficiently by the multi-layer aggregation, which contributes to obtaining more extrapolative knowledge representation. Finally, through extensive experiments on FB15k-237 and WN18RR datasets, we show that SE-GNN achieves state-of-the-art performance on Knowledge Graph Completion task and performs a better extrapolation ability. Our code is available at https://***/renli1024/SE-GNN. Copyright © 2021, The Authors. All rights reserved.

关键词： Knowledge graph

来源：评论

学校读者我要写书评

暂无评论

Cross-domain Human Parsing via Adversarial Feature and Label Adaptation

arXiv

引用

arXiv 2018年

作者： Liu, Si Sun, Yao Zhu, Defa Ren, Guanghui Chen, Yu Feng, Jiashi Han, Jizhong Institute of Information Engineering Chinese Academy of Sciences *** Department of Ece National University of Singapore Jiangsu Key Laboratory of Big Data Analysis Technology/B-DAT Nanjing University of Information Science and Technology Collab. Innov. Ctr. of Atmosph. Environ. and Equip. Technol. Nanjing Univ. of Info. Sci. and Technol. Nanjing China

Human parsing has been extensively studied recently (Yamaguchi et al. 2012;Xia et al. 2017) due to its wide applications in many important scenarios. Mainstream fashion parsing models (i.e., parsers) focus on parsing the high-resolution and clean images. However, directly applying the parsers trained on benchmarks of high-quality samples to a particular application scenario in the wild, e.g., a canteen, airport or workplace, often gives non-satisfactory performance due to domain shift. In this paper, we explore a new and challenging cross-domain human parsing problem: Taking the benchmark dataset with extensive pixel-wise labeling as the source domain, how to obtain a satisfactory parser on a new target domain without requiring any additional manual labeling? To this end, we propose a novel and efficient crossdomain human parsing model to bridge the cross-domain differences in terms of visual appearance and environment conditions and fully exploit commonalities across domains. Our proposed model explicitly learns a feature compensation network, which is specialized for mitigating the cross-domain differences. A discriminative feature adversarial network is introduced to supervise the feature compensation to effectively reduces the discrepancy between feature distributions of two domains. Besides, our proposed model also introduces a structured label adversarial network to guide the parsing results of the target domain to follow the high-order relationships of the structured labels shared across domains. The proposed framework is end-to-end trainable, practical and scalable in real applications. Extensive experiments are conducted where LIP dataset is the source domain and 4 different datasets including surveillance videos, movies and runway shows without any annotations, are evaluated as target domains. The results consistently confirm data efficiency and performance advantages of the proposed method for the challenging cross-domain human parsing problem. Copyright

关键词： Security systems

来源：评论

学校读者我要写书评

暂无评论

Spatial analysis of Taxi Speeding Event Using GPS Trajectory data *

Spatial Analysis of Taxi Speeding Event Using GPS Trajectory...

引用

International Conference on Intelligent Transportation

作者： Chuanyun Fu Yue Zhou Chuan Xu Haipeng Cui School of Transportation and Logistics Southwest Jiaotong University Southwest Jiaotong University Chengdu P.R. of China National Engineering Laboratory of Integrated Transportation Big Data Application Technology Southwest Jiaotong University Chengdu P.R. of China School of Transportation and Logistics Southwest Jiaotong University Chengdu P.R. of China College of Transportation Engineering Tongji University Shanghai P.R. of China

ISBN: (纸本)9781538670255

GPS-equipped taxis can generate large-scale trajectory data which enables scholars to uncover taxi abnormal behaviors, such as speeding. Hence, this study intends to disclose the characteristics of taxi speeding event (SE), identify the spatial factors impacting the frequency of taxi SE, using 5,757 taxis' GPS trajectory data in a part of the central area of Chengdu city from November 1 to November 30, 2016, along with speed limit data, electronic map data, etc. By comparing the calculated travel speeds with speed limits, taxi SEs were identified and categorized into five groups: SE (

关键词： Public transportation Global Positioning System Roads Trajectory Correlation Vehicles

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

Cooperative Sensing and Heterogeneous Information Fusion in VCPS: A Multi-agent Deep Reinforcement Learning Approach

arXiv

引用

arXiv 2022年

作者： Xu, Xincao Liu, Kai Dai, Penglin Xie, Ruitao Cao, Jingjing Luo, Jiangtao The College of Computer Science Chongqing University Chongqing400040 China The School of Computing and Artificial Intelligence Southwest Jiaotong University Chengdu611756 China The National Engineering Laboratory of Integrated Transportation Big Data Application Technology Chengdu611756 China The College of Computer Science and Software Engineering Shenzhen University Shenzhen518060 China The School of Transportation and Logistics Engineering Wuhan University of Technology Hubei430063 China The Electronic Information and Networking Research Institute Chongqing University of Posts and Telecommunications Chongqing400065 China

Cooperative sensing and heterogeneous information fusion are critical to realize vehicular cyber-physical systems (VCPSs). This paper makes the first attempt to quantitatively measure the quality of VCPS by designing a new metric called Age of View (AoV). Specifically, we first present the system architecture where heterogeneous information can be cooperatively sensed and uploaded via vehicle-to-infrastructure (V2I) communications in vehicular edge computing (VEC). Logical views are constructed by fusing the heterogeneous information at edge nodes. Further, we formulate the problem by deriving a cooperative sensing model based on the multi-class M/G/1 priority queue, and defining the AoV by modeling the timeliness, completeness and consistency of the logical views. On this basis, a multi-agent deep reinforcement learning solution is proposed. In particular, the system state includes vehicle sensed information, edge cached information and view requirements. The vehicle action space consists of the sensing frequencies and uploading priorities of information. A difference-reward-based credit assignment is designed to divide the system reward, which is defined as the VCPS quality, into the difference reward for vehicles. Edge node allocates V2I bandwidth to vehicles based on predicted vehicle trajectories and view requirements. Finally, we build the simulation model and give a comprehensive performance evaluation, which conclusively demonstrates the superiority of the proposed solution. Copyright © 2022, The Authors. All rights reserved.

关键词： Reinforcement learning

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：