检索结果-内蒙古大学图书馆

arXiv 2021年

作者： Gong, Maoguo Gao, Yuan Xie, Yu Qin, A.K. Pan, Ke Ong, Yew-Soon The School of Electronic Engineering Key Laboratory of Intelligent Perception and Image Understanding Ministry of Education Xidian University Xi'an Shaanxi Province710071 China The Key Laboratory of Computational Intelligence and Chinese Information Processing Ministry of Education Shanxi University Taiyuan030006 China The Department of Computer Science and Software Engineering Swinburne University of Technology Melbourne Australia The School of Computer Science and Engineering Nanyang Technological University Singapore639798 Singapore

The performance of machine learning algorithms heavily relies on the availability of a large amount of training data. However, in reality, data usually reside in distributed parties such as different institutions and may not be directly gathered and integrated due to various data policy constraints. As a result, some parties may suffer from insufficient data available for training machine learning models. In this paper, we propose a multi-party dual learning (MPDL) framework to alleviate the problem of limited data with poor quality in an isolated party. Since the knowledge sharing processes for multiple parties always emerge in dual forms, we show that dual learning is naturally suitable to handle the challenge of missing data, and explicitly exploits the probabilistic correlation and structural relationship between dual tasks to regularize the training process. We introduce a feature-oriented differential privacy with mathematical proof, in order to avoid possible privacy leakage of raw features in the dual inference process. The approach requires minimal modifications to the existing multi-party learning structure, and each party can build flexible and powerful models separately, whose accuracy is no less than non-distributed self-learning approaches. The MPDL framework achieves significant improvement compared with state-of-the-art multi-party learning methods, as we demonstrated through simulations on real-world datasets. Copyright © 2021, The Authors. All rights reserved.

关键词： Machine learning

来源：评论

学校读者我要写书评

暂无评论

CTCNet: A CNN-Transformer Cooperation Network for Face image Super-Resolution

arXiv

引用

arXiv 2022年

作者： Gao, Guangwei Xu, Zixiang Li, Juncheng Yang, Jian Zeng, Tieyong Qi, Guo-Jun The Institute of Advanced Technology Nanjing University of Posts and Telecommunications Nanjing China The Provincial Key Laboratory for Computer Information Processing Technology Soochow University Suzhou China The School of Communication & Information Engineering Shanghai University Shanghai China Jiangsu Key Laboratory of Image and Video Understanding for Social Safety Nanjing University of Science and Technology Nanjing China The School of Computer Science and Technology Nanjing University of Science and Technology Nanjing China The Center for Mathematical Artificial Intelligence Department of Mathematics The Chinese University of Hong Kong Hong Kong Research Center for Industries of the Future School of Engineering Westlake University OPPO Research Seattle United States

Recently, deep convolution neural networks (CNNs) steered face super-resolution methods have achieved great progress in restoring degraded facial details by joint training with facial priors. However, these methods have some obvious limitations. On the one hand, multi-task joint learning requires additional marking on the dataset, and the introduced prior network will significantly increase the computational cost of the model. On the other hand, the limited receptive field of CNN will reduce the fidelity and naturalness of the reconstructed facial images, resulting in suboptimal reconstructed images. In this work, we propose an efficient CNN-Transformer Cooperation Network (CTCNet) for face super-resolution tasks, which uses the multi-scale connected encoder-decoder architecture as the backbone. Specifically, we first devise a novel Local-Global Feature Cooperation Module (LGCM), which is composed of a Facial Structure Attention Unit (FSAU) and a Transformer block, to promote the consistency of local facial detail and global facial structure restoration simultaneously. Then, we design an efficient Feature Refinement Module (FRM) to enhance the encoded features. Finally, to further improve the restoration of fine facial details, we present a Multi-scale Feature Fusion Unit (MFFU) to adaptively fuse the features from different stages in the encoder procedure. Extensive evaluations on various datasets have assessed that the proposed CTCNet can outperform other state-of-the-art methods significantly. Source code will be available at https://***/IVIPLab/CTCNet. Copyright © 2022, The Authors. All rights reserved.

关键词： Restoration

来源：评论

学校读者我要写书评

暂无评论

Cross-receptive Focused Inference Network for Lightweight image Super-Resolution

arXiv

引用

arXiv 2022年

作者： Li, Wenjie Li, Juncheng Gao, Guangwei Deng, Weihong Zhou, Jiantao Yang, Jian Qi, Guo-Jun The Intelligent Visual Information Perception Laboratory Institute of Advanced Technology Nanjing University of Posts and Telecommunications Nanjing210046 China The Provincial Key Laboratory for Computer Information Processing Technology Soochow University Suzhou215006 China The School of Communication and Information Engineering Shanghai University Shanghai200444 China Jiangsu Key Laboratory of Image and Video Understanding for Social Safety Nanjing University of Science and Technology Nanjing210094 China The Pattern Recognition and Intelligent System Laboratory School of Artificial Intelligence Beijing University of Posts and Telecommunications Beijing100876 China The State Key Laboratory of Internet of Things for Smart City Department of Computer and Information Science Faculty of Science and Technology University of Macau 999078 China The School of Computer Science and Technology Nanjing University of Science and Technology Nanjing210094 China The Research Center for Industries of the Future The School of Engineering Westlake University Hangzhou310024 China OPPO Research SeattleWA98101 United States

Recently, Transformer-based methods have shown impressive performance in single image super-resolution (SISR) tasks due to the ability of global feature extraction. However, the capabilities of Transformers that need to incorporate contextual information to extract features dynamically are neglected. To address this issue, we propose a lightweight Cross-receptive Focused Inference Network (CFIN) that consists of a cascade of CT Blocks mixed with CNN and Transformer. Specifically, in the CT block, we first propose a CNN-based Cross-Scale Information Aggregation Module (CIAM) to enable the model to better focus on potentially helpful information to improve the efficiency of the Transformer phase. Then, we design a novel Cross-receptive Field Guided Transformer (CFGT) to enable the selection of contextual information required for reconstruction by using a modulated convolutional kernel that understands the current semantic information and exploits the information interaction within different self-attention. Extensive experiments have shown that our proposed CFIN can effectively reconstruct images using contextual information, and it can strike a good balance between computational cost and model performance as an efficient model. Source codes will be available at https://***/IVIPLab/CFIN. Copyright © 2022, The Authors. All rights reserved.

关键词： Semantics

来源：评论

学校读者我要写书评

暂无评论

RTM3D: Real-time monocular 3D detection from object keypoints for autonomous driving

arXiv

引用

arXiv 2020年

作者： Li, Peixuan Zhao, Huaici Liu, Pengfei Cao, Feidao Shenyang Institute of Automation Chinese Academy of Sciences Institutes for Robotics and Intelligent Manufacturing Chinese Academy of Sciences University of Chinese Academy of Sciences Key Laboratory of Opto-Electronic Information Processing Chinese Academy of Sciences Key Lab of Image Understanding and Computer Vision Liaoning Province

In this work, we propose an efficient and accurate monocular 3D detection framework in single shot. Most successful 3D detectors take the projection constraint from the 3D bounding box to the 2D box as an important component. Four edges of a 2D box provide only four constraints and the performance deteriorates dramatically with the small error of the 2D detector. Different from these approaches, our method predicts the nine perspective keypoints of a 3D bounding box in image space, and then utilize the geometric relationship of 3D and 2D perspectives to recover the dimension, location, and orientation in 3D space. In this method, the properties of the object can be predicted stably even when the estimation of keypoints is very noisy, which enables us to obtain fast detection speed with a small architecture. Training our method only uses the 3D properties of the object without the need for external networks or supervision data. Our method is the first real-time system for monocular image 3D detection while achieves state-ofthe-art performance on the KITTI benchmark. Code will be released at https://***/Banconxuan/RTM3D. Copyright © 2020, The Authors. All rights reserved.

关键词： Real time systems

来源：评论

学校读者我要写书评

暂无评论

Multi-level graph convolutional network with automatic graph learning for hyperspectral image classification

arXiv

引用

arXiv 2020年

作者： Wan, Sheng Gong, Chen Pan, Shirui Yang, Jie Yang, Jian PCA Lab Key Laboratory of Intelligent Perception and Systems for High-Dimensional Information of Ministry of Education Jiangsu Key Laboratory of Image Video Understanding for Social Security School of Computer Science and Engineering Nanjing University of Science and Technology Nanjing210094 China Institute of Image Processing and Pattern Recognition Shanghai Jiao Tong University Shanghai200240 China Faculty of Information Technology Monash University ClaytonVIC3800 Australia

Nowadays, deep learning methods, especially the Graph Convolutional Network (GCN), have shown impressive performance in hyperspectral image (HSI) classification. However, the current GCN-based methods treat graph construction and image classification as two separate tasks, which often results in suboptimal performance. Another defect of these methods is that they mainly focus on modeling the local pairwise importance between graph nodes while lack the capability to capture the global contextual information of HSI. In this paper, we propose a Multi-level GCN with Automatic Graph Learning method (MGCN-AGL) for HSI classification, which can automatically learn the graph information at both local and global levels. By employing attention mechanism to characterize the importance among spatially neighboring regions, the most relevant information can be adaptively incorporated to make decisions, which helps encode the spatial context to form the graph information at local level. Moreover, we utilize multiple pathways for local-level graph convolution, in order to leverage the merits from the diverse spatial context of HSI and to enhance the expressive power of the generated representations. To reconstruct the global contextual relations, our MGCN-AGL encodes the long range dependencies among image regions based on the expressive representations that have been produced at local level. Then inference can be performed along the reconstructed graph edges connecting faraway regions. Finally, the multi-level information is adaptively fused to generate the network output. In this means, the graph learning and image classification can be integrated into a unified framework and benefit each other. Extensive experiments have been conducted on three real-world hyperspectral datasets, which are shown to outperform the state-of-the-art methods. Copyright © 2020, The Authors. All rights reserved.

关键词： image classification

来源：评论

学校读者我要写书评

暂无评论

image Restoration for Terahertz image Based on Complex-Valued Deconvolution 8

Image Restoration for Terahertz Image Based on Complex-Value...

引用

8th Asia-Pacific Conference on Antennas and Propagation, APCAP 2019

作者： Ning, Wei Qi, Feng Wang, Jinkuan Northeastern University School of Computer Science and Engineering Shenyang110169 China Chinese Academy of Sciences Shenyang Institute of Automation Shenyang110016 China Institutes for Robotics and Intelligent Manufacturing Chinese Academy of Sciences Shenyang110016 China Key Laboratory of Opto-Electronic Information Processing Chinese Academy of Sciences Shenyang110016 China Key Lab of Image Understanding and Computer Vision Liaoning Province Shenyang110016 China

ISBN: (纸本)9781665400541

According to the unique characteristics of terahertz (THz) waves, THz imaging has become a hot topic in widely application areas. However, the imaging resolution is constrained by its long wavelength. Generally, the deconvolution is always used to reconstruct the object function. In this paper, a method that combining the classic deconvolution algorithm with the complex-value data processing is investigated. It is posed that the proposed complex-number deconvolution achieves better performance compared to the real-valued deconvolution. © 2019 IEEE.

关键词： Deconvolution

来源：评论

学校读者我要写书评

暂无评论

94 GHz Three-Dimensional Imaging Radar for Environmental Detection 8

94 GHz Three-Dimensional Imaging Radar for Environmental Det...

引用

8th Asia-Pacific Conference on Antennas and Propagation, APCAP 2019

作者： Wu, HongMing Qi, Feng Wang, Jinkuan Northeastern University College of Information Science and Engineering Shenyang110819 China Chinese Academy of Sciences Shenyang Institute of Automation Shenyang110016 China Institutes for Robotics and Intelligent Manufacturing Chinese Academy of Sciences Shenyang110016 China Key Laboratory of Opto-Electronic Information Processing Chinese Academy of Sciences Shenyang110016 China Key Lab of Image Understanding and Computer Vision Liaoning Province Shenyang110016 China

ISBN: (纸本)9781665400541

At present, With the development of technology, the high resolution of millimeter wave (terahertz) can be applied to environmental sensing imaging. In this paper, Using the frequency-modulated continuous-wave (FMCW) radar technique with a 1GHz bandwidth, we show experimentally that a high-resolution real time imaging radar operating at 93.5-94.5GHz is capable of detecting different car models at standoff ranges of 12 m. We also achieved 3D high-resolution imaging of the building. at 140 meters. © 2019 IEEE.

关键词： Millimeter waves

来源：评论

学校读者我要写书评

暂无评论

Pixel-wise PolSAR image classification via a novel complex-valued deep fully convolutional network

arXiv

引用

arXiv 2019年

作者： Cao, Yice Wu, Yan Zhang, Peng Liang, Wenkai Li, Ming Remote Sensing Image Processing and Fusion Group School of Electronic Engineering Xidian University Xi'an710071 China National Key Laboratory of Radar Signal Processing Xidian University Xi'an710071 China Collaborative Innovation Center of Information Sensing and Understanding Xidian University Xian710071 China

Although complex-valued (CV) neural networks have shown better classification results compared to their real-valued (RV) counterparts for polarimetric synthetic aperture radar (PolSAR) classification, the extension of pixel-level RV networks to the complex domain has not yet thoroughly examined. This paper presents a novel complex-valued deep fully convolutional neural network (CV-FCN) designed for PolSAR image classification. Specifically, CV-FCN uses PolSAR CV data that includes the phase information and utilizes the deep FCN architecture that performs pixel-level labeling. It integrates the feature extraction module and the classification module in a united framework. Technically, for the particularity of PolSAR data, a dedicated complex-valued weight initialization scheme is defined to initialize CV-FCN. It considers the distribution of polarization data to conduct CV-FCN training from scratch in an efficient and fast manner. CV-FCN employs a complex downsampling-then-upsampling scheme to extract dense features. To enrich discriminative information, multi-level CV features that retain more polarization information are extracted via the complex downsampling scheme. Then, a complex upsampling scheme is proposed to predict dense CV labeling. It employs complex max-unpooling layers to greatly capture more spatial information for better robustness to speckle noise. In addition, to achieve faster convergence and obtain more precise classification results, a novel average cross-entropy loss function is derived for CV-FCN optimization. Experiments on real PolSAR datasets demonstrate that CV-FCN achieves better classification performance than other state-of-art methods. Copyright © 2019, The Authors. All rights reserved.

关键词： image classification

来源：评论

学校读者我要写书评

暂无评论

A directional-progressive search method for infrared small target detection 3

A directional-progressive search method for infrared small t...

引用

3rd Optoelectronics Global Conference, OGC 2018

作者： Zhang, Xiangyue Ding, Qinghai Luo, Haibo Hui, Bin Chang, Zheng Zhang, Junchao Shenyang Institute of Automation Chinese Academy of Sciences Shenyang110016 China University of Chinese Academy of Sciences Beijing100049 China Key Laboratory of Opto-Electronic Information Processing CAS Shenyang110016 China Key Lab of Image Understanding and Computer Vision Liaoning Province Shenyang110016 China Space Star Technology Co. Ltd Beijing100086 China

ISBN: (纸本)9781538673973

Infrared small target detection plays a key role in infrared precision guidance and infrared early-warning system. It has been a difficult problem for researchers to study on how to detect targets accurately at a long distance as early as possible. Most of the existing algorithms can detect small targets in simple backgrounds, but they would fail on the detection when the background clutters are chaotic and the signal to clutter ratio (SCR) is low. Therefore, we propose a new infrared small target detection method which called a directional-progressive search (DPS) method. Our method derives from a fact that a small target is an isotropic Gaussian distribution at a long distance, while clutters show different characteristics in different directions. Based on this difference, we decompose the original image into first-order sub-images with different directions by using a first-order directional derivative (FODD) filter. Then zero-crossing points are detected in each direction step by step to distinguish small targets and background clutters. After screening progressively, the positions where existing zero-crossing points in every sub-image can be confirmed as targets. Experimental results show that our method acquires higher detection rates and lower false alarm rates compared with other methods. At the same time, our method can still keep better performance under various complex backgrounds. The robustness of our method is strong. © 2018 IEEE.

关键词： Clutter (information theory)

来源：评论

学校读者我要写书评

暂无评论

Static human behavior classification based on LLC features and GIST features 7

Static human behavior classification based on LLC features a...

引用

7th IEEE Annual International Conference on CYBER Technology in Automation, Control, and Intelligent Systems, CYBER 2017

作者： Ende, Wang Xukui, Hou Xuepeng, Li Shenyang Institute of Automation Chinese Academic of Sciences Key Lab of Image Understanding and Computer Vision Key Laboratory of Optical Electrical Image Processing Shenhe District Shenyang Liaoning China

ISBN: (纸本)9781538604892

This paper presents a method for recognizing human behavior in static images based on LLC and GIST features. The feature points in the image is densely located in sub-region of images and we extract SIFT feature from each sub-region. Then using the LLC method to encode the extracted dense SIFT features of each sub-region and each feature point descriptor is assigned to several nearest words, so that each descriptor can be expressed by the linear correlation coefficient of vocabulary. In order to increase the spatial information, we use the SPM model to divide the image into many blocks under different levels. We can get the pooled feature from each sub-region using the max pooling method. Then these pooled features from sub-region are concatenated and normalized as the final pooled features. In order to get GIST features, we divide the image into blocks and construct the Gabor filter group of 32 different scales and directions. Then each Gabor filter in the Gabor filter group does convolution operation with image blocks and we take the mean value of each blocks under each Gabor filter as the feature description. The features from each block under each Gabor filter are concatenated and normalized as the final GIST feature representation of the image. Then concatenating the final pooled features and the GIST features and take as the final feature representation. Finally, the intersection kernel function of SVM is used for classification. We performed experiments on several databases. By contrast, this algorithm has a good effect in accuracy and efficiency. © 2017 IEEE.

关键词： Gabor filters

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：