检索结果-内蒙古大学图书馆

Partial Differential Equations is All You Need for Generating Neural Architectures - A Theory for Physical Artificial Intelligence Systems

学校读者我要写书评

暂无评论

arXiv 2021年

作者： Guo, Ping Huang, Kaizhu Xu, Zenglin Image Processing & Pattern Recognition Lab. Beijing Normal University Beijing100875 China Data Science Research Center Duke Kunshan University Jiangsu Kunshan215316 China School of Computer Science and Technology Harbin Institute of Technology at ShenZhen Peng Cheng National Lab Guangdong Shenzhen510855 China

In this work, we generalize the reaction-diffusion equation in statistical physics, Schrödinger equation in quantum mechanics, and Helmholtz equation in paraxial optics into the neural partial differential equations (NPDE), which can be considered as the fundamental equations in the field of artificial intelligence research. We take the finite difference method to discretize NPDEs for finding the numerical solution. Moreover, the basic building blocks of deep neural network architectures, including multi-layer perceptron, convolutional neural networks, and recurrent neural networks, are generated. The learning strategies, such as Adaptive moment estimation, L-BFGS, pseudoinverse learning algorithms, and partial differential equation constrained optimization, are also developed. This work is of significance in that it presents a clear view of interpretable deep neural networks physically, enables high possibility to be applied to analog computing device design, and paves the road to physical artificial intelligence. © 2021, CC BY-NC-SA.

关键词： Schrodinger equation

Measurement of amplitude of the moiré patternsin digital autostereoscopic 3D display

学校读者我要写书评

暂无评论

arXiv 2017年

作者： Saveljev, Vladimir Kim, Sung-Kyu NEMO Lab. Department of Physics Myongji University Yongin-si Gyeonggi-do17058 Korea Republic of Center for Image Media Research Korea Institute of Science and Technology Seoul136-791 Korea Republic of

The article presents the experimental measurements of the amplitude of the moiré patterns in a digital autostereoscopic barrier-type 3D display across a wide angular range with a small increment. The period and orientation of the moiré patterns were also measured as functions of the angle. Simultaneous branches are observed and analyzed. The theoretical interpretation is also given. The results can help preventing or minimizing the moiré effect in displays. Copyright © 2017, The Authors. All rights reserved.

关键词： Moire fringes

Geese PSO optimization in geometric constraint solving

学校读者我要写书评

暂无评论

Information technology Journal 2012年第4期11卷 504-507页

作者： Cao, Chun-Hong Wang, Li-Min Han, Chun-Yan Zhao, Da-Zhe Zhang, Bin College of Information Science and Engineering Northeastern University Shenyang 110819 China College of Computer Science and Technology Jilin University Changchun Jilin 130012 China State Key Lab. for Novel Software Technology Nanjing University China Key Laboratory of Medical Image Computing Ministry of Education Northeastern University Shenyang Liaoning 110819 China

Geometric constraint problem is equivalent to the problem of solving a set of nonlinear equations substantially. The constraint problem can be transformed to an optimization n problem. We can solve the problem with GeesePSO optimization. In this paper, an improved algorithm is proposed using the characteristics of the flight of geese for reference. The improved algorithm has superiority over PSO;for one thing, it keeps the population various by ordering all the particles and making each particle fly following its anterior particle;for another thing, it strengthens cooperation and competition between particles by making each particle share more useful information of the other particles. The experiment shows that it can improve the geometric constraint solving efficiency and possess better convergence property than the compared algorithms. © 2012 Asian Network for Scientific Information.

关键词： Nonlinear equations

A Combining Method for Tumors Detection from Near-infrared Breast Imaging

学校读者我要写书评

暂无评论

A Combining Method for Tumors Detection from Near-infrared B...

Annual International Conference of the IEEE Engineering in Medicine and Biology Society (EMBC)

作者： Zhicheng Wang Jian Liu Jinwen Tian Zeping Xie State Education Commission Key Laboratory for Image Processing and Intelligent Control Institute for Pattern Recognition and Artificial Intelligence Huazhong Univ. of Sci. & Tech. Wuhan 430074 China Key Lab. for Image Process. & Intelligent Control State Educ. Comm. School of Life Science & Technology Huazhong University of Science and Technology Wuhan China

This paper introduces the new qualitative and quantitative methods, which can diagnose breast tumors. Qualitative methods include blood vessel display inside and outside of pathological changes part of breast, display of equivalent pixel curves at the part of pathological changes and display of breast tumor image edge. Accordingly, three feature extraction operators are proposed, i.e. the combination operators of anisotropic gradient and smoothing operator, an improved Sobel operator and an edge sharpening operator. Furthermore, quantitative diagnostic approaches are discussed based on blood and oxygen contents according to abundant clinical data and pathological mechanism of breast tumors. The results of clinic show that the methods of combining qualitative and quantitative diagnose are effective for breast tumor images, especially for early and potential breast cancer

关键词： Breast tumors Displays Pathology Blood vessels Biomedical imaging Pixel Feature extraction Anisotropic magnetoresistance Smoothing methods Breast cancer

Bridge the Gap between Supervised and Unsupervised Learning for Fine-Grained Classification

学校读者我要写书评

暂无评论

arXiv 2022年

作者： Wang, Jiabao Li, Yang Wei, Xiu-Shen Li, Hang Miao, Zhuang Zhang, Rui Army Engineering University of PLA Nanjing210007 China PCA Lab Key Lab of Intelligent Perception and Systems for High-Dimensional Information of Ministry of Education Nanjing University of Science and Technology Nanjing210094 China Jiangsu Key Lab of Image and Video Understanding for Social Security School of Computer Science and Engineering Nanjing University of Science and Technology Nanjing210094 China State Key Lab. for Novel Software Technology Nanjing University Nanjing210023 China

Unsupervised learning technology has caught up with or even surpassed supervised learning technology in general object classification (GOC) and person re-identification (re-ID). However, it is found that the unsupervised learning of fine-grained visual classification (FGVC) is more challenging than GOC and person re-ID. In order to bridge the gap between unsupervised and supervised learning for FGVC, we investigate the essential factors (including feature extraction, clustering, and contrastive learning) for the performance gap between supervised and unsupervised FGVC. Furthermore, we propose a simple, effective, and practical method, termed as UFCL, to alleviate the gap. Three key issues are concerned and improved: First, we introduce a robust and powerful backbone, ResNet50-IBN, which has an ability of domain adaptation when we transfer imageNet pre-trained models to FGVC tasks. Next, we propose to introduce HDBSCAN instead of DBSCAN to do clustering, which can generate better clusters for adjacent categories with fewer hyper-parameters. Finally, we propose a weighted feature agent and its updating mechanism to do contrastive learning by using the pseudo lab.ls with inevitable noise, which can improve the optimization process of learning the parameters of the network. The effectiveness of our UFCL is verified on CUB-200-2011, Oxford-Flowers, Oxford-Pets, Stanford-Dogs, Stanford-Cars and FGVC-Aircraft datasets. Under the unsupervised FGVC setting, we achieve state-of-the-art results, and analyze the key factors and the important parameters to provide a practical guidance. Copyright © 2022, The Authors. All rights reserved.

关键词： image classification

Towards Harnessing Feature Embedding for Robust Learning with Noisy lab.ls

学校读者我要写书评

暂无评论

arXiv 2022年

作者： Zhang, Chuang Shen, Li Yang, Jian Gong, Chen Pca Lab The Key Lab. of Intelligent Percept. and Syst. for High-Dimensional Info. of Ministry of Education School of Computer Science and Engineering Nanjing University of Science and Technology China Jiangsu Key Lab of Image and Video Understanding for Social Security China Jd Explore Academy China College of Computer Science Nankai University China

The memorization effect of deep neural networks (DNNs) plays a pivotal role in recent lab.l noise learning methods. To exploit this effect, the model prediction-based methods have been widely adopted, which aim to exploit the outputs of DNNs in the early stage of learning to correct noisy lab.ls. However, we observe that the model will make mistakes during lab.l prediction, resulting in unsatisfactory performance. By contrast, the produced features in the early stage of learning show better robustness. Inspired by this observation, in this paper, we propose a novel feature embedding-based method for deep learning with lab.l noise, termed lab.l NoiseDilution (LEND). To be specific, we first compute a similarity matrix based on current embedded features to capture the local structure of training data. Then, the noisy supervision signals carried by mislab.led data are overwhelmed by nearby correctly lab.led ones (i.e., lab.l noise dilution), of which the effectiveness is guaranteed by the inherent robustness of feature embedding. Finally, the training data with diluted lab.ls are further used to train a robust classifier. Empirically, we conduct extensive experiments on both synthetic and real-world noisy datasets by comparing our LEND with several representative robust learning approaches. The results verify the effectiveness of our LEND. © 2022, CC BY.

关键词： Deep neural networks

Multiscale detection of curvilinear structures in 2-D and 3-D image data

学校读者我要写书评

暂无评论

Multiscale detection of curvilinear structures in 2-D and 3-...

International Conference on Computer Vision (ICCV)

作者： T.M. Koller G. Gerig G. Szekely D. Dettwiler Comnmnication Technology Laboratory Image Science ETH Zentrum-ETL Zurich Switzerland Eidgenossische Technische Hochschule Zurich Zurich ZH CH Commun. Technol. Lab. Eidgenossische Tech. Hochschule Zurich Switzerland

Presents a novel, parameter-free technique for the segmentation and local description of line structures on multiple scales, both in 2D and in 3D. The algorithm is based on a nonlinear combination of linear filters and searches for elongated, symmetric line structures, while suppressing the response to edges. The filtering process creates one sharp maximum across the line-feature profile and across the scale-space. The multi-scale response reflects local contrast and is independent of the local width. The filter is steerable in both the orientation and scale domains, leading to an efficient, parameter-free implementation. A local description is obtained that describes the contrast, the position of the center-line, the width, the polarity, and the orientation of the line. Examples of images from different application domains demonstrate the generic nature of the line segmentation scheme. The 3D filtering is applied to magnetic resonance volume data in order to segment cerebral blood vessels.< >

关键词： Nonlinear filters Filtering image segmentation Pixel Detectors image edge detection Shape lab.ratories Blood vessels Biomedical imaging

White Paper on Industrial Applications of Computer Vision and Pattern Recognition

学校读者我要写书评

暂无评论

White Paper on Industrial Applications of Computer Vision an...

17th International Conference on image Analysis and Processing (ICIAP)

作者： Garibotto, Giovanni Murrieri, Pierpaolo Capra, Alessandro De Muro, Stefano Petillo, Ugo Flammini, Francesco Esposito, Mariana Pragliola, Concetta Di Leo, Giuseppe Lengu, Roald Mazzino, Nadia Paolillo, Alfredo D'Urso, Michele Vertucci, Raffaele Narducci, Fabio Ricciardi, Stefano Casanova, Andrea Fenu, Gianni De Mizio, Marco Savastano, Mario Di Capua, Michele Ferone, Alessio Selex ES Italy STMicroelectronics Catania Italy RFI Rete Ferroviaria Italiana Roma Italy Ansaldo STS Italy University of Naples Federico II Napoli Italy Dept. of Industrial Engineering University of Salerno Italy Biometric and Image Proc. Lab. University of Salerno Italy University of Cagliari Italy CIRA Italian Aerospace Research Centre Capua Italy CNR Napoli Italy Unlimited Software srl Naples Italy Dept. of Science and Technology University of Naples Parthenope Italy

ISBN: (纸本)9783642411847;9783642411830

The paper provides a summary of the contributions to the industrial session at ICIAP2013, describing a few practical applications of Video Analysis, in the Surveillance and Security field. The session has been organized to stimulate an open discussion within the scientific community of CVPR on new emerging research areas which deserve particular attention, and may contribute to the improvement of industrial applications in the near future.

关键词： Computer vision

Neurons of the Human Dentate Nucleus: Box-Count Method in the Quantitative Analysis of Cell Morphology

学校读者我要写书评

暂无评论

Neurons of the Human Dentate Nucleus: Box-Count Method in th...

International Conference on Control Systems and Computer science (CSCS)

作者： Duica L. Maric Nebojša T. Miloševic Herbert F. Jelinek Katarina Rajkovic University of Novi Sad Serbia University of Belgrade Serbia Department of Biomedical Engineering Khalifa University of Science Technology and Research UAE Department of Biophysics University of Belgrade Serbia Lab. for Image Anal. in Medical faculty University of Belgrade Serbia

ISBN: (纸本)9781467361408

The morphology of neurons from the human dentate nucleus was analyzed estimating the size and shape of the dendritic field, shape of the neuron, space-filling property and the degree of dendrite aberrations. Among them, the last three morphological properties were investigated using the most popular technique of fractal analysis: the box-count method. The box dimensions of binary images and dendritic field area were statistically investigated in order to test whether the binary box dimension can quantify the size of the neuron. The same analysis was carried out using the box dimension of outline images and image circularity. The parameters, presented in this study have proved to be a useful means for quantifying the morphology of dentate neurons as they provide a robust means of differentiating between neuron subtypes in the dentate nucleus. The findings of the present study are in accordance with previous qualitative data.

关键词： Neurons Shape Fractals Morphology Correlation Filling Educational institutions