检索结果-内蒙古大学图书馆

Robust and Fast Measure of Information via Low-rank Representation

学校读者我要写书评

暂无评论

arXiv 2022年

作者： Dong, Yuxin Gong, Tieliang Yu, Shujian Chen, Hong Li, Chen School of Computer Science and Technology Xi’an Jiaotong University Xi’an710049 China Shaanxi Provincial Key Laboratory of Big Data Knowledge Engineering Ministry of Education Xi’an710049 China Machine Learning Group UiT - The Arctic University of Norway Norway College of Science Huazhong Agriculture University Wuhan430070 China Engineering Research Center of Intelligent Technology for Agriculture Ministry of Education Wuhan430070 China

The matrix-based Rényi’s entropy allows us to directly quantify information measures from given data, without explicit estimation of the underlying probability distribution. This intriguing property makes it widely applied in statistical inference and machine learning tasks. However, this information theoretical quantity is not robust against noise in the data, and is computationally prohibitive in large-scale applications. To address these issues, we propose a novel measure of information, termed low-rank matrix-based Rényi’s entropy, based on low-rank representations of infinitely divisible kernel matrices. The proposed entropy functional inherits the specialty of of the original definition to directly quantify information from data, but enjoys additional advantages including robustness and effective calculation. Specifically, our low-rank variant is more sensitive to informative perturbations induced by changes in underlying distributions, while being insensitive to uninformative ones caused by noises. Moreover, low-rank Rényi’s entropy can be efficiently approximated by random projection and Lanczos iteration techniques, reducing the overall complexity from O(n3) to O(n2s) or even O(ns2), where n is the number of data samples and s n. We conduct large-scale experiments to evaluate the effectiveness of this new information measure, demonstrating superior results compared to matrix-based Rényi’s entropy in terms of both performance and computational efficiency. Copyright © 2022, The Authors. All rights reserved.

关键词： Entropy

Uncertainty-based Model Acceleration for Cancer Classification in Whole-Slide Images

学校读者我要写书评

暂无评论

Uncertainty-based Model Acceleration for Cancer Classificati...

IEEE International Conference on Bioinformatics and Biomedicine (BIBM)

作者： Zeyu Gao Anyu Mao Jialun Wu Yang Li Chunbao Wang Caixia Ding Tieliang Gong Chen Li School of Computer Science and Technology Xi’an Jiaotong University Xi’an China Shaanxi Provincial Key Laboratory of Big Data Knowledge Engineering Xi’an Jiaotong University Xi’an China Department of Pathology the First Affiliated Hospital of Xi’an Jiaotong University Xi’an China Department of Pathology Shaanxi Provincial Cancer Hospital Xi’an China

ISBN: (数字)9781665468190

ISBN: (纸本)9781665468206

Computational Pathology (CPATH) offers the possibility for highly accurate and low-cost automated pathological diagnosis. However, the high time cost of model inference is one of the main issues limiting the application of CPATH methods. Due to the large size of Whole-Slide Image (WSI), commonly used CPATH methods divided a WSI into a large number of image patches at relatively high magnification, then predicted each image patch individually, which is time-consuming. In this paper, we propose a novel Uncertainty-based Model Acceleration (UMA) method for reducing the time cost of model inference, thereby relieving the deployment burden of CPATH applications. Enlightened by the slide-viewing process of pathologists, only a few high-uncertain regions are regarded as “suspicious” regions that need to be predicted at high magnification, and most of the regions in WSI are predicted at low magnification, thereby reducing the times of image patch extraction and prediction. Meanwhile, uncertainty estimation ensures prediction accuracy at low magnification. We take two fundamental CPATH classification tasks (i.e., cancer region detection and subtyping) as examples. Extensive experiments on two large-scale renal cell carcinoma classification datasets demonstrate that our UMA can significantly reduce the time cost of model inference while maintaining competitive classification performance.

关键词： Pathology Costs Uncertainty Limiting Hospitals Biological system modeling Computational modeling

SVT-Net: Super Light-Weight Sparse Voxel Transformer for Large Scale Place Recognition

学校读者我要写书评

暂无评论

arXiv 2021年

作者： Fan, Zhaoxin Song, Zhenbo Liu, Hongyan Lu, Zhiwu He, Jun Du, Xiaoyong Key Laboratory of Data Engineering Knowledge Engineering of MOE School of Information Renmin University of China Beijing100872 China Gaoling School of Artificial Intelligence Renmin University of China Beijing100872 China School of Computer Science and Engineering Nanjing University of Science and Technology Nanjing210094 China Department of Management Science and Engineering Tsinghua University Beijing100084 China

Simultaneous Localization and Mapping (SLAM) and Autonomous Driving are becoming increasingly more important in recent years. Point cloud-based large scale place recognition is the spine of them. While many models have been proposed and have achieved acceptable performance by learning short-range local features, they always skip long-range contextual properties. Moreover, the model size also becomes a serious shackle for their wide applications. To overcome these challenges, we propose a super light-weight network model termed SVT-Net. On top of the highly efficient 3D Sparse Convolution (SP-Conv), an Atom-based Sparse Voxel Transformer (ASVT) and a Cluster-based Sparse Voxel Transformer (CSVT) are proposed respectively to learn both short-range local features and long-range contextual features. Consisting of ASVT and CSVT, SVT-Net can achieve state-of-the-art performance in terms of both recognition accuracy and running speed with a super-light model size (0.9M parameters). Meanwhile, for the purpose of further boosting efficiency, we introduce two simplified versions, which also achieve state-of-the-art performance and further reduce the model size to 0.8M and 0.4M respectively. Copyright © 2021, The Authors. All rights reserved.

关键词： Machine learning

Near-Field Modelling and Performance Analysis for Extremely Large-Scale IRS Communications

学校读者我要写书评

暂无评论

arXiv 2023年

作者： Feng, Chao Lu, Haiquan Zeng, Yong Li, Teng Jin, Shi Zhang, Rui National Mobile Communications Research Laboratory Southeast University Nanjing210096 China Purple Mountain Laboratories Nanjing211111 China State Key Laboratory of Millimeter Waves Southeast University Nanjing210096 China The Chinese University of Hong Kong Shenzhen Shenzhen Research Institute of Big Data Shenzhen518172 China Department of Electrical and Computer Engineering National University of Singapore Singapore117583 Singapore

Intelligent reflecting surface (IRS) is an emerging technology for wireless communications, thanks to its powerful capability to engineer the radio environment. However, in practice, this benefit is attainable only when the passive IRS is of sufficiently large size, for which the conventional uniform plane wave (UPW)-based far-field model may become invalid. In this paper, we pursue a near-field modelling and performance analysis for wireless communications with extremely large-scale IRS (XL-IRS). By taking into account the directional gain pattern of IRS’s reflecting elements and the variations in signal amplitude across them, we derive both the lower- and upper-bounds of the resulting signal-to-noise ratio (SNR) for the generic uniform planar array (UPA)-based XL-IRS. Our results reveal that, instead of scaling quadratically and unboundedly with the number of reflecting elements M as in the conventional UPW-based model, the SNR under the new non-uniform spherical wave (NUSW)-based model increases with M with a diminishing return and eventually converges to a certain limit. To gain more insights, we further study the special case of uniform linear array (ULA)-based XL-IRS, for which a closed-form SNR expression in terms of the IRS size and locations of the base station (BS) and the user is derived. Our result shows that the SNR is mainly determined by the two geometric angles formed by the BS/user locations with the IRS, as well as the dimension of the IRS. Numerical results validate our analysis and demonstrate the necessity of proper near-field modelling for wireless communications aided by XL-IRS. Copyright © 2023, The Authors. All rights reserved.

关键词： Asymptotic analysis

SEA: Sentence encoder assembly for video retrieval by textual queries

学校读者我要写书评

暂无评论

arXiv 2020年

作者： Li, Xirong Zhou, Fangming Xu, Chaoxi Ji, Jiaqi Yang, Gang Key Lab of Data Engineering and Knowledge Engineering AI & Media Computing Lab School of Information Renmin University of China Beijing100872 China

Retrieving unlabeled videos by textual queries, known as Ad-hoc Video Search (AVS), is a core theme in multimedia data management and retrieval. The success of AVS counts on cross-modal representation learning that encodes both query sentences and videos into common spaces for semantic similarity computation. Inspired by the initial success of previously few works in combining multiple sentence encoders, this paper takes a step forward by developing a new and general method for effectively exploiting diverse sentence encoders. The novelty of the proposed method, which we term Sentence Encoder Assembly (SEA), is two-fold. First, different from prior art that use only a single common space, SEA supports text-video matching in multiple encoder-specific common spaces. Such a property prevents the matching from being dominated by a specific encoder that produces an encoding vector much longer than other encoders. Second, in order to explore complementarities among the individual common spaces, we propose multi-space multi-loss learning. As extensive experiments on four benchmarks (MSR-VTT, TRECVID AVS 2016-2019, TGIF and MSVD) show, SEA surpasses the state-of-the-art. In addition, SEA is extremely ease to implement. All this makes SEA an appealing solution for AVS and promising for continuously advancing the task by harvesting new sentence encoders. © 2020, CC-BY.

关键词： Signal encoding

Deep Representation of Hierarchical Semantic Attributes for Zero-shot Learning

学校读者我要写书评

暂无评论

Deep Representation of Hierarchical Semantic Attributes for ...

International Joint Conference on Neural Networks (IJCNN)

作者： Zhaocheng Zhang Gang Yang School of Information Renmin University of China Beijing China Key Lab of Data Engineering and Knowledge Engineering Renmin University of China Beijing China

ISBN: (数字)9781728169262

ISBN: (纸本)9781728169279

On account of a large scale of dataset need to be annotated to fit for specific tasks, Zero-Shot Learning(ZSL) has invoked so much attention and got significant progress in recent research due to the prevalence of deep neural networks. At present, ZSL is mainly solved through the utilization of auxiliary information, such as semantic attributes and text descriptions. And then, we can employ the mapping method to bridge the gap between visual and semantic space. However, due to the lack of effective use of auxiliary information, this problem has not been solved well. Inspired by previous work, we consider that visual space can be used as the embedding space to get a stronger ability to express the precise characteristics of semantic information. Meanwhile, we take into account that there are some noise attributes in the annotated information of public datasets that need to be processed. Based on these considerations, we propose an end-to-end method with convolutional architecture, instead of conventionally linear projection, to provide a deep representation for semantic information to solve ZSL. Semantic features would express more detailed and precise information after being feed into our method. Besides, we use word embedding to generate some superclasses for original classes and propose a new loss function for these superclasses to assist in training. Experiments show that our method can get decent improvements for ZSL and Generalized Zero-Shot Learning(GZSL) on several public datasets.

关键词： Semantics Visualization Training Testing Task analysis Neural networks Probabilistic logic

Research progress of CDT 8

学校读者我要写书评

暂无评论

Research progress of CDT

8th International Conference on Bioinformatics and Biomedical Science, ICBBS 2019

作者： Yuting, Gao Shutong, Shen Sanhong, Deng School of Information Management Nanjing University China Key Laboratory of Data Engineering and Knowledge Services in Jiangsu China

ISBN: (纸本)9781450372510

With the high mortality rate for the cases of malignant tumors, the discovery and early treatment of cancer is critical to improving the 5-year survival rate of cancer. The biggest challenge in control and prevention is how to detect tumors as early as possible, so that the most effective means can be used for treatment. With the help of the WOS database, researchers found that liquid biopsy, genetic material/protein expression and computer imaging play an important role in cancer detection. Through analysis of the history and current status of cancer detection technology development, this paper also aims to provide guidance for the clinical practice of current cancer screening and provide inspiration for future technological development. © 2019 Association for Computing Machinery.

关键词： Gene expression

Toward PTNET Network Topology Analysis and Routing Algorithm Design 6th

学校读者我要写书评

暂无评论

Toward PTNET Network Topology Analysis and Routing Algorithm...

6th International Conference on data Science, ICDS 2019

作者： Han, Zhijie Zhang, Qingfang Du, Xiaoyu Guo, Kun He, Mingshu Institute of Data and Knowledge Engineering Henan University KaifengHenan475004 China Jiangsu High Technology Research Key Laboratory for Wireless Sensor Network NanjingJiangsu210003 China School of Computer and Information Engineering Henan University KaifengHenan475004 China University of Chinese Academy of Sciences Beijing China

ISBN: (纸本)9789811528095

In recent years, data center network is used for transmission, storage and processing of big data, which plays an important role for applications in cloud computing and CDN distribution. Network topology and routing algorithm are its core research content and key technical issues. The traditional network topology is difficult to guarantee the quality of service in scalability and fault tolerance. The server-centric data center network topology can ensure the scale of the data center network by recursively increasing the number of network nodes and links. relative to the Dcell, BCube, and BCCC typical network topology, PTNet network as a typical representative of a new type of the server-centric data center network topology, which has more advantages in scalability, fault tolerance and so on. Multicast and broadcast in data center network have more application scenarios and use value. For example, the video conference online, multimedia remote education and other development are inseparable from the application and promotion of network multicast and broadcast. So it is necessary to research the routing algorithms of multicast and broadcast in the network. Based on the deep research of PTNet network, this paper analyzes and researches the network topology, multicast and broadcast routing algorithm. © Springer Nature Singapore Pte Ltd 2020.

关键词： Network topology

data augmentation in microscopic images for material data mining

学校读者我要写书评

暂无评论

npj Computational Materials 2020年第1期6卷 601-609页

作者： Boyuan Ma Xiaoyan Wei Chuni Liu Xiaojuan Ban Haiyou Huang Hao Wang Weihua Xue Stephen Wu Mingfei Gao Qing Shen Michele Mukeshimana Adnan Omer Abuassba Haokai Shen Yanjing Su Beijing Advanced Innovation Center for Materials Genome Engineering University of Science and Technology BeijingBeijing 100083China School of Computer and Communication Engineering University of Science and Technology BeijingBeijing 100083China Beijing Key Laboratory of Knowledge Engineering for Materials Science Beijing 100083China Institute for Advanced Materials and Technology University of Science and Technology BeijingBeijing 100083China School of Materials Science and Engineering University of Science and Technology BeijingBeijing 100083China School of Materials Science and Technology Liaoning Technical UniversityLiaoning 114051China The Institute of Statistical Mathematics Research Organization of Information and SystemsTachikawaTokyo 190-8562Japan National Intellectual Property Administration Beijing 100088China Faculty of Engineering Sciences University of BurundiBujumburaBurundi Faculty of Engineering and Technology Palestine Technical University–KadoorieTulkaremPalestine College of Information Science and Engineering China University of PetroleumBeijingChina Key Lab of Petroleum Data Mining China University of PetroleumBeijingChina

Recent progress in material data mining has been driven by high-capacity models trained on large ***,collecting experimental data(real data)has been extremely costly owing to the amount of human effort and expertise ***,we develop a novel transfer learning strategy to address problems of small or insufficient *** strategy realizes the fusion of real and simulated data and the augmentation of training data in a data mining *** a specific task of grain instance image segmentation,this strategy aims to generate synthetic data by fusing the images obtained from simulating the physical mechanism of grain formation and the“image style”information in real *** results show that the model trained with the acquired synthetic data and only 35%of the real data can already achieve competitive segmentation performance of a model trained on all of the real *** the time required to perform grain simulation and to generate synthetic data are almost negligible as compared to the effort for obtaining real data,our proposed strategy is able to exploit the strong prediction power of deep learning without significantly increasing the experimental burden of training data preparation.

关键词： mining instance competitive