检索结果-内蒙古大学图书馆

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

DouZero+: Improving DouDizhu AI by Opponent Modeling and Coach-guided Learning

arXiv

引用

arXiv 2022年

作者： Zhao, Youpeng Zhao, Jian Hu, Xunhan Zhou, Wengang Li, Houqiang CAS Key Laboratory of Technology in Geo-spatial Information Processing and Application System Department of Electronic Engineering and Information Science University of Science and Technology of China Hefei230027 China Institute of Artificial Intelligence Hefei Comprehensive National Science Center Hefei China

Recent years have witnessed the great breakthrough of deep reinforcement learning (DRL) in various perfect and imperfect information games. Among these games, DouDizhu, a popular card game in China, is very challenging due to the imperfect information, large state space, elements of collaboration and a massive number of possible moves from turn to turn. Recently, a DouDizhu AI system called DouZero has been proposed. Trained using traditional Monte Carlo method with deep neural networks and self-play procedure without the abstraction of human prior knowledge, DouZero has outperformed all the existing DouDizhu AI programs. In this work, we propose to enhance DouZero by introducing opponent modeling into DouZero. Besides, we propose a novel coach network to further boost the performance of DouZero and accelerate its training process. With the integration of the above two techniques into DouZero, our DouDizhu AI system achieves better performance and ranks top in the Botzone leaderboard among more than 400 AI agents, including DouZero. 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

3D Point Cloud Reconstruction of Vehicle using Inversely Mapping and Voting from CSAR Images

3D Point Cloud Reconstruction of Vehicle using Inversely Map...

引用

IEEE International Conference on Radar

作者： Shanshan Feng Yun Lin Fei Teng Wen Hong Key Laboratory of Technology in Geospatial Information Processing and Application System Aerospace Information Research Institute Chinese Academy of Sciences University of Chinese Academy of Sciences Institute of Electronics Chinese Academy of Sciences Beijing China School of Electronic Information Engineering North China University of Technology Beijing China

ISBN: (纸本)9781665468893

3D reconstruction of object has raised much interest in the field of SAR. The feature of target at multi aspect angles can be obtained from sub-aperture images provided by circular SAR(CSAR), which is conducive to 3D reconstruction. Radargrammetric method is a conventional way to extract DEM while its performance for 3D reconstruction is limited by the image registration. It is difficult to find corresponding points in different sub-aperture images. In this paper, we proposed a method for 3D reconstruction of vehicle based on projections in sub-aperture images. According to the imaging mechanism of CSAR, different targets located on the same iso-range line in the zero doppler plane fall into the same cell. For a projection point, given a series of offsets, the projection point will be mapped inversely to the 3D mesh along the iso-range line. We can obtain candidates of the target. The intersection of iso-range lines can be regarded as voting process. For a candidate, the more times of intersection, the higher the number of votes, and the candidate point will be reserved. This fully excavates the information contained in the angle dimension of CSAR. The proposed approach is verified by the Gotcha Volumetric SAR Data Set.

关键词： Point cloud compression Space vehicles Image registration Three-dimensional displays Imaging Radar imaging Feature extraction

来源：评论

学校读者我要写书评

暂无评论

Beyond triplet loss: Meta prototypical N-tuple loss for person re-identification

arXiv

引用

arXiv 2020年

作者： Zhang, Zhizheng Lan, Cuiling Zeng, Wenjun Chen, Zhibo Chang, Shih-Fu The CAS Key Laboratory of Technology in Geo-Spatial Information Processing and Application System University of Science and Technology of China Anhui Hefei China Microsoft Research Asia Beijing China Columbia University New YorkNY United States

Person Re-identification (ReID) aims at matching a person of interest across images. In convolutional neural network (CNN) based approaches, loss design plays a vital role in pulling closer features of the same identity and pushing far apart features of different identities. In recent years, triplet loss achieves superior performance and is predominant in ReID. However, triplet loss considers only three instances of two classes in per-query optimization (with an anchor sample as query) and it is actually equivalent to a two-class classification. There is a lack of loss design which enables the joint optimization of multiple instances (of multiple classes) within per-query optimization for person ReID. In this paper, we introduce a multi-class classification loss, i.e., N-tuple loss, to jointly consider multiple (N) instances for per-query optimization. This in fact aligns better with the ReID test/inference process, which conducts the ranking/comparisons among multiple instances. Furthermore, for more efficient multi-class classification, we propose a new meta prototypical N-tuple loss. With the multi-class classification incorporated, our model achieves the state-of-the-art performance on the benchmark person ReID datasets. Copyright © 2020, The Authors. All rights reserved.

关键词： Classification (of information)

来源：评论

学校读者我要写书评

暂无评论

Patch reordering: A novel way to achieve rotation and translation invariance in convolutional neural networks

arXiv

引用

arXiv 2019年

作者： Shen, Xu Tian, Xinmei Sun, Shaoyan Tao, Dacheng CAS Key Laboratory of Technology in Geo-spatial Information Processing and Application System University of Science and Technology of China Hefei Anhui230027 China Centre for Artificial Intelligence Faculty of Engineering and Information Technology University of Technology Sydney 81 Broadway Street UltimoNSW2007 Australia

Convolutional Neural Networks (CNNs) have demonstrated state-of-the-art performance on many visual recognition tasks. However, the combination of convolution and pooling operations only shows invariance to small local location changes in meaningful objects in input. Sometimes, such networks are trained using data augmentation to encode this invariance into the parameters, which restricts the capacity of the model to learn the content of these objects. A more efficient use of the parameter budget is to encode rotation or translation invariance into the model architecture, which relieves the model from the need to learn them. To enable the model to focus on learning the content of objects other than their locations, we propose to conduct patch ranking of the feature maps before feeding them into the next layer. When patch ranking is combined with convolution and pooling operations, we obtain consistent representations despite the location of meaningful objects in input. We show that the patch ranking module improves the performance of the CNN on many benchmark tasks, including MNIST digit recognition, large-scale image recognition, and image retrieval. The code is available at https://***//jasonustc/caffe-multigpu/tree/TICNN. Copyright © 2019, The Authors. All rights reserved.

关键词： Convolution

来源：评论

学校读者我要写书评

暂无评论

Simultaneous Double Q-learning with Conservative Advantage Learning for Actor-Critic Methods

arXiv

引用

arXiv 2022年

作者： Li, Qing Zhou, Wengang Lu, Zhenbo Li, Houqiang The CAS Key Laboratory of Technology in Geo-Spatial Information Processing and Application System Department of Electronic Engineering and Information Science University of Science and Technology of China Hefei230027 China The Institute of Artificial Intelligence Hefei Comprehensive National Science Center Hefei230000 China

Actor-critic Reinforcement Learning (RL) algorithms have achieved impressive performance in continuous control tasks. However, they still suffer two nontrivial obstacles, i.e., low sample efficiency and overestimation bias. To this end, we propose Simultaneous Double Q-learning with Conservative Advantage Learning (SDQ-CAL). Our SDQ-CAL boosts the Double Q-learning for off-policy actor-critic RL based on a modification of the Bellman optimality operator with Advantage Learning. Specifically, SDQ-CAL improves sample efficiency by modifying the reward to facilitate the distinction from experience between the optimal actions and the others. Besides, it mitigates the overestimation issue by updating a pair of critics simultaneously upon double estimators. Extensive experiments reveal that our algorithm realizes less biased value estimation and achieves state-of-the-art performance in a range of continuous control benchmark tasks. We release the source code of our method at: https://***/LQNew/SDQ-CAL. 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

A Cloaking-Based Approach to Protect Location Privacy in Location-Based Services

A Cloaking-Based Approach to Protect Location Privacy in Loc...

引用

第三十三届中国控制会议

作者： Zheng Jiangyu Tan Xiaobin Cliff Zou Niu Yukun Zhu Jin CAS Key Laboratory of Technology in Geo-spatial Information Processing and Application System University of Science and Technology of China Department of Automation University of Science and Technology of China Department of Electrical Engineering and Computer Science University of Central FloridaOrlandoFL 32816-2362

ISBN: (纸本)9781479947249

With the widespread use of mobile devices, the location-based service(LBS) applications become increasingly popular, which introduces the new security challenge to protect user's location privacy. On one hand, a user expects to report his own location as far as possible away from his real location to protect his location privacy. On the other hand, in order to obtain high quality of service(QoS), users are required to report their locations as accurate as possible. To achieve the dedicated tradeoff between privacy requirement and QoS requirement, we propose a novel approach based on cloaking technique. We also discuss the disadvantage of the traditional general system model and propose an improved model. The basic idea of our approach is to select a sub-area from the generated cloaking area as user's reported location. The sub-area may not contain a user's real location,which prevents an adversary from performing attack with side information. Specifically, by defining an objective function with a novel location privacy metric and a QoS metric, we are able to convert the privacy issue to an optimization problem. Then, location privacy metric and QoS metric are given. To reduce the complexity of the optimization, a heuristic algorithm is *** privacy-preserving analysis and comparison with related work [8], we demonstrate the effectiveness and efficiency of our approach.

关键词： Location-based Services,Location Privacy,k-anonymity,Cloaking Area

来源：评论

学校读者我要写书评

暂无评论

Radio frequency interference mitigation using pseudoinverse learning autoencoders

引用

Research in Astronomy and Astrophysics 2020年第8期20卷 121-128页

作者： Hong-Feng Wang Mao Yuan Qian Yin Ping Guo Wei-Wei Zhu Di Li Si-Bo Feng Image Processing and Pattern Recognition Laboratory School of Artificial IntelligenceBeijing Normal UniversityBeijing 100875China CAS Key Laboratory of FAST National Astronomical ObservatoriesChinese Academy of SciencesBeijing 100101China School of Information Management Dezhou UniversityDezhou 253023China Image Processing and Pattern Recognition Laboratory School of System ScienceBeijing Normal UniversityBeijing 100875China Institute for Astronomical Science Dezhou UniversityDezhou 253023China University of Chinese Academy of Sciences Beijing 100049China Hanvon Technology Co. LtdBeijing 100193China NAOC-UKZN Computational Astrophysics Centre University of KwaZulu-NatalDurban 4000South Africa

Radio frequency interference(RFI)is an important challenge in radio *** comes from various sources and increasingly impacts astronomical observation as telescopes become more *** this study,we propose a fast and effective method for removing RFI in pulsar *** use pseudo-inverse learning to train a single hidden layer auto-encoder(AE).We demonstrate that the AE can quickly learn the RFI signatures and then remove them from fast-sampled spectra,leaving real pulsar *** method has the advantage over traditional threshold-based filter method in that it does not completely remove contaminated channels,which could also contain useful astronomical information.

关键词： pulsars:general methods:numerical methods:data analysis

来源：评论

学校读者我要写书评

暂无评论

Outage Analysis of Dual-Hop Transmission with Buffer Aided Amplify-and-Forward Relay

Outage Analysis of Dual-Hop Transmission with Buffer Aided A...

引用

IEEE Vehicular technology Conference

作者： Guan-Xing Li Chen Dong Dong Liu Guangtao Li Yonghui Zhang China Mobile Group Liaoning Ltd. School of ECS University of Southampton CAS Key Laboratory of Technology in Geo-spatial Information Processing and Application System University of Science and Technology of China RF Micro Devices Co. Ltd.

ISBN: (纸本)9781479944484

A new packet-selection based transmission scheme is proposed on a dual-hop link with buffer aided amplify-and-forward relay, where the relay with a buffer can record the channel information of source-relay hop and store the received packets. In order to satisfy the constraint of equivalent end-to-end SNR, the relay may pick up a packet in the buffer to transmit, with consideration of the channel statuses of both the source-relay hop and the relay-destination hop. Therefore, by adjusting the packet transmission order in the relay, the outage probability can be decreased in the proposed transmission scheme. Both theoretical analyses and simulation results show that the proposed scheme outperforms traditional ones by a significant margin of 2-4 dB gain in terms of outage probability.

关键词： Relays Signal to noise ratio Fading Tin Delays Wireless communication Buffer storage

来源：评论

学校读者我要写书评

暂无评论

Recent Advance in Content-based Image Retrieval: A literature survey

arXiv

引用

arXiv 2017年

作者： Zhou, Wengang Li, Houqiang Fellow, Tian I.E.E.E. CAS Key Laboratory of Technology in Geo-spatial Information Processing and Application System Department of Electronic Engineering and Information Science University of Science and Technology of China Hefei230027 China Department of Computer Science University of Texas San Antonio San AntonioTX78249 United States

—The explosive increase and ubiquitous accessibility of visual data on the Web have led to the prosperity of research activity in image search or retrieval. With the ignorance of visual content as a ranking clue, methods with text search techniques for visual retrieval may suffer inconsistency between the text words and visual content. Content-based image retrieval (CBIR), which makes use of the representation of visual content to identify relevant images, has attracted sustained attention in recent two decades. Such a problem is challenging due to the intention gap and the semantic gap problems. Numerous techniques have been developed for content-based image retrieval in the last decade. The purpose of this paper is to categorize and evaluate those algorithms proposed during the period of 2003 to 2016. We conclude with several promising directions for future research. Copyright © 2017, The Authors. All rights reserved.

关键词： Content based retrieval

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：