检索结果-内蒙古大学图书馆

Sparse coding driven deep decision tree ensembles for nuclear segmentation in digital pathology images

学校读者我要写书评

暂无评论

arXiv 2020年

作者： Song, Jie Xiao, Liang Molaei, Mohsen Lian, Zhichao College of Automation & College of Artificial Intelligence Nanjing University of Posts and Telecommunications Nanjing210023 China School of Computer Science and Engineering Nanjing University of Science and Technology Nanjing210094 China School of Computer Science and Engineering Nanjing University of Science and Technology Nanjing210094 China Key Laboratory of Intelligent Perception and Systems for High-Dimensional Information of Ministry of Education Nanjing University of Science and Technology Nanjing210094 China

In this paper, we propose an easily trained yet powerful representation learning approach with performance highly competitive to deep neural networks in a digital pathology image segmentation task. The method, called sparse coding driven deep decision tree ensembles that we abbreviate as ScD2TE, provides a new perspective on representation learning. We explore the possibility of stacking several layers based on non-differentiable pairwise modules and generate a densely concatenated architecture holding the characteristics of feature map reuse and end-to-end dense learning. Under this architecture, fast convolutional sparse coding is used to extract multi-level features from the output of each layer. In this way, rich image appearance models together with more contextual information are integrated by learning a series of decision tree ensembles. The appearance and the high-level context features of all the previous layers are seamlessly combined by concatenating them to feed-forward as input, which in turn makes the outputs of subsequent layers more accurate and the whole model efficient to train. Compared with deep neural networks, our proposed ScD2TE does not require back-propagation computation and depends on less hyper-parameters. ScD2TE is able to achieve a fast end-to-end pixel-wise training in a layer-wise manner. We demonstrated the superiority of our segmentation technique by evaluating it on the multi-disease state and multi-organ dataset where consistently higher performances were obtained for comparison against several state-of-the-art deep learning methods such as convolutional neural networks (CNN), fully convolutional networks (FCN), etc. Copyright © 2020, The Authors. All rights reserved.

关键词： Decision trees

Statistical approach to detection of attacks for stochastic cyber-physical systems

学校读者我要写书评

暂无评论

arXiv 2020年

作者： Marelli, Damián Sui, Tianju Fu, Minyue Lu, Renquan School of Automation Guangdong University of Technology Guangzhou China French Argentine International Center for Information and Systems Sciences National Scientific and Technical Research Council Argentina School of Control Science and Engineering Dalian University of Technology Dalian China School of Electrical Engineering and Computer Science University of Newcastle CallaghanNSW2308 Australia School of Automation Guangdong Provincial Key Laboratory of Intelligent Decision and Cooperative Control Guandong University of Technology Guangzhou China

We study the problem of detecting an attack on a stochastic cyber-physical system. We aim to treat the problem in its most general form. We start by introducing the notion of asymptotically detectable attacks, as those attacks introducing changes to the system’s output statistics which persist asymptotically. We then provide a necessary and sufficient condition for asymptotic detectability. This condition preserves generality as it holds under no restrictive assumption on the system and attacking scheme. To show the importance of this condition, we apply it to detect certain attacking schemes which are undetectable using simple statistics. Our necessary and sufficient condition naturally leads to an algorithm which gives a confidence level for attack detection. We present simulation results to illustrate the performance of this algorithm. Copyright © 2020, The Authors. All rights reserved.

关键词： Stochastic systems

CBS-GAN: A Band Selection Based Generative Adversarial Net for Hyperspectral Sample Generation

学校读者我要写书评

暂无评论

IOP Conference Series: Earth and Environmental Science 2021年第1期734卷

作者： Yulin Qiao Mostofa Zaman Mohammad Yi Li Xiaobo Liu Zhihua Cai School of Automation China University of Geosciences (Wuhan) 430074 Wuhan China Hubei Key Laboratory of Advanced Control and Intelligent Automation for Complex Systems 430074 Wuhan China Hubei Key Laboratory of Intelligent Geo-Information Processing China University of Geosciences Wuhan 430078 China School of Computer Science China University of Geosciences (Wuhan) 430078 Wuhan China

Sample generation is an effective method to improve the performance of hyperspectral image classification by generating virtual samples for training sample expansion in the training process of classification. However, there are some defects existing in the previous sample generation methods including the lack of spatial information, the redundant generation and the damage of the original spectral components. In this paper, we propose conditional band selection generative adversarial net, named CBS-GAN, to handle this problem. Firstly, the band selection net of CBS-GAN is utilized to avoid redundant bands and keep original spectral information, then the generation net of CBS-GAN generates the spatial-spectral data blocks by selected bands for sample generation. The experiments of classification are also used to demonstrate the availability of virtual samples generated by our method.

关键词：

Learning data-adaptive non-parametric kernels

学校读者我要写书评

暂无评论

The Journal of Machine Learning Research

The Journal of Machine Learning Research 2020年第1期21卷 8590-8628页

作者： Fanghui Liu Xiaolin Huang Chen Gong Jie Yang Li Li Department of Electrical Engineering ESAT-STADIUS KU Leuven Belgium Institute of Image Processing and Pattern Recognition Institute of Medical Robotics Shanghai Jiao Tong University Shanghai China PCA Lab Key Laboratory of Intelligent Perception and Systems for High-Dimensional Information of Ministry of Education School of Computer Science and Engineering Nanjing University of Science and Technology China and Department of Computing Hong Kong Polytechnic University Hong Kong SAR China Department of Automation BNRist Tsinghua University China

In this paper, we propose a data-adaptive non-parametric kernel learning framework in margin based kernel methods. In model formulation, given an initial kernel matrix, a data-adaptive matrix with two constraints is imposed in an entry-wise scheme. Learning this data-adaptive matrix in a formulation-free strategy enlarges the margin between classes and thus improves the model flexibility. The introduced two constraints are imposed either exactly (on small data sets) or approximately (on large data sets) in our model, which provides a controllable trade-off between model flexibility and complexity with theoretical demonstration. In algorithm optimization, the objective function of our learning framework is proven to be gradient-Lipschitz continuous. Thereby, kernel and classifier/regressor learning can be efficiently optimized in a unified framework via Nesterov's acceleration. For the scalability issue, we study a decomposition-based approach to our model in the large sample case. The effectiveness of this approximation is illustrated by both empirical studies and theoretical guarantees. Experimental results on various classification and regression benchmark data sets demonstrate that our non-parametric kernel learning framework achieves good performance when compared with other representative kernel learning based algorithms.

关键词： support vector machines non-parametric kernel learning gradient-Lipschitz continuous

A registration-aided domain adaptation network for 3D Point cloud based place recognition

学校读者我要写书评

暂无评论

arXiv 2020年

作者： Qiao, Zhijian Hu, Hanjiang Shi, Weiang Chen, Siyuan Liu, Zhe Wang, Hesheng Department of Automation Insititue of Medical Robotics Key Laboratory of System Control and Information Processing of Ministry of Education Key Laboratory of Marine Intelligent Equipment and System of Ministry of Education Shanghai Jiao Tong University Shanghai200240 China Beijing Advanced Innovation Center for Intelligent Robots and Systems Beijing Institute of Technology China Department of Mechanical Engineering Carnegie Mellon University United States Department of Computer Science and Technology University of Cambridge United Kingdom

In the field of large-scale SLAM for autonomous driving and mobile robotics, 3D point cloud based place recognition has aroused significant research interest due to its robustness to changing environments with drastic daytime and weather variance. However, it is time-consuming and effort-costly to obtain high-quality point cloud data for place recognition model training and ground truth for registration in the real world. To this end, a novel registration-aided 3D domain adaptation network for point cloud based place recognition is proposed. A structure-aware registration network is introduced to help to learn features with geometric information and a 6-DoFs pose between two point clouds with partial overlap can be estimated. The model is trained through a synthetic virtual LiDAR dataset through GTA-V with diverse weather and daytime conditions and domain adaptation is implemented to the real-world domain by aligning the global features. Our results outperform state-of-the-art 3D place recognition baselines or achieve comparable on the real-world Oxford RobotCar dataset with the visualization of registration on the virtual dataset. Copyright © 2020, The Authors. All rights reserved.

关键词： Three dimensional computer graphics

Roadmap on Neuromorphic Photonics

学校读者我要写书评

暂无评论

arXiv 2025年

作者： Brunner, Daniel Shastri, Bhavin J. Al-Qadasi, Mohammed A. Ballani, H. Barbay, Sylvain Biasi, Stefano Bienstman, Peter Bilodeau, Simon Bogaerts, Wim Böhm, Fabian Brennan, G. Buckley, Sonia Cai, Xinlun Strinati, Marcello Calvanese Canakci, B. Charbonnier, Benoit Chemnitz, Mario Chen, Yitong Cheung, Stanley Chiles, Jeff Choi, Suyeon Christodoulides, Demetrios N. Chrostowski, Lukas Chu, J. Clegg, J.H. Cletheroe, D. Conti, Claudio Dai, Qionghai Di Lauro, Luigi Diamantopoulos, Nikolaos-Panteleimon Dinc, Niyazi Ulas Ewaniuk, Jacob Fan, Shanhui Fang, Lu Franchi, Riccardo Freire, Pedro Gentilini, Silvia Gigan, Sylvain Giorgi, Gian Luca Gkantsidis, C. Gladrow, J. Goi, Elena Goldmann, M. Grabulosa, A. Gu, Min Guo, Xianxin Hejda, Matěj Horst, F. Hsieh, Jih-Liang Hu, Jianqi Hu, Juejun Huang, Chaoran Hurtado, Antonio Jaurigue, Lina Kalinin, K.P. Kamalian-Kopae, Morteza Kelly, D.J. Khajavikhan, Mercedeh Kremer, H. Laydevant, Jeremie Lederman, Joshua C. Lee, Jongheon Lenstra, Daan Li, Gordon H.Y. Li, Mo Li, Yuhang Lin, Xing Lin, Zhongjin Lis, Mieszko Lüdge, Kathy Lugnan, Alessio Lupo, Alessandro Lvovsky, A.I. Manuylovich, Egor Marandi, Alireza Marchesin, Federico Massar, Serge McCaughan, Adam N. McMahon, Peter L. Moralis-Pegios, Miltiadis Morandotti, Roberto Moser, Christophe Moss, David J. Mukherjee, Avilash Nikdast, Mahdi Offrein, B.J. Oguz, Ilker Oripov, Bakhrom O'Shea, G. Ozcan, Aydogan Parmigiani, F. Pasricha, Sudeep Pavanello, Fabio Pavesi, Lorenzo Peserico, Nicola Pickup, L. Pierangeli, Davide Pleros, Nikos Porte, Xavier Primavera, Bryce A. Prucnal, Paul Psaltis, Demetri Puts, Lukas Qiao, Fei Rahmani, B. Raineri, Fabrice Ríos Ocampo, Carlos A. Robertson, Joshua Romeira, Bruno Roques-Carmes, Charles Rotenberg, Nir Rowstron, A. Schoenhardt, Steffen Schwartz, Russell L.T. Shainline, Jeffrey M. Shekhar, Sudip Skalli, A. Sohoni, Mandar M. Sorger, Volker J. Soriano, Miguel C. Spall, James Stabile, Ripalta Stiller, Birgit Sunada, Satoshi Tefas, Anastasios Tossoun, Bassem Tsakyridis, Apostolos Turitsyn, Sergei K. Van der Sande, G Université Marie et Louis Pasteur CNRS UMR 6174 Institut FEMTO-ST Besançon25000 France Centre for Nanophotonics Department of Physics Engineering Physics & Astronomy Queen's University Canada Department of Electrical and Computer Engineering The University of British Columbia Vancouver Canada Microsoft Research Cambridge United Kingdom Université Paris-Saclay CNRS Centre de Nanosciences et de Nanotechnologies France Nanoscience Laboratory Department of Physics University of Trento Italy Photonics Research Group Department of Information Technology Ghent University imec Belgium Princeton University NJ United States Hewlett Packard Labs Hewlett Packard Enterprise Böblingen Germany National Institute of Standards and Technology BoulderCO United States State Key Laboratory of Optoelectronic Materials and Technologies School of Electronics and Information Technology Sun Yat-sen University China Enrico Fermi Research Center Rome Italy Université Grenoble-Alpes CEA Leti Grenoble France Leibniz-Institute of Photonic Technology Jena Germany Institute of Applied Optics and Biophysics Jena Germany Department of Automation Tsinghua University Beijing China Department of Electrical and Computer Engineering North Carolina State University NC United States Department of Electrical Engineering Stanford University CA United States University of Southern California Los AngelesCA United States Department of Physics Sapienza University Rome Italy Institute for Complex Systems National Research Council Rome Italy Varennes Canada NTT Device Technology Labs NTT Corporation Kanagawa Atsugi Japan Institute of Electrical and Microengineering School of Engineering École Polytechnique Fédérale de Lausanne Switzerland Edward L. Ginzton Laboratory Stanford University StanfordCA United States Department of Electronic Engineering Tsinghua University China Beijing National Research Center for Information Science and Technology Tsinghua University China Aston Univ

Neuromorphic photonics are processors inspired by the human brain and enabled by light (photons) instead of traditional electronics. Neuromorphic photonics and its associated concepts are experiencing a significant resurgence, building on foundational research from the 1980s and 1990s. This renewed momentum is driven by breakthroughs in photonic integration, nonlinear optics, and advanced materials, alongside the growing necessity of neuro-inspired computing in numerous applications of economic and societal relevance. The increasing demand for energy-efficient artificial intelligence (AI) solutions underscores the need for innovation and a cohesive vision to address key challenges, including scalability, energy efficiency, precision, and standardized performance benchmarks. Together, these efforts present an opportunity to establish a unique photonic advantage with practical, real-world applications. This roadmap consolidates recent advances while exploring emerging applications, reflecting the remarkable diversity of hardware platforms, neuromorphic concepts, and implementation philosophies reported in the field. It emphasizes the critical role of cross-disciplinary collaboration in this rapidly evolving field. The roadmap introduces various approaches to embedding the high-complexity transformations central to neuromorphic computing, focusing on frequency, delay, and spectral embeddings. This is followed by a discussion of architectures of photonic neural networks (PNNs) and an in-depth analysis of methods for implementing these architectures in photonic hardware. Dedicated sections delve into integrated photonic hardware, the realization of photonic weights and memories, and the optimization of training processes for photonic neuromorphic architectures. The roadmap concludes by exploring numerous potential applications, highlighting the challenges and advances necessary to transition neuromorphic photonic computing from a primarily academic pursuit to a technolog

关键词： Philosophical aspects

Learning Attentions: Residual Attentional Siamese Network for High Performance Online Visual Tracking 31

学校读者我要写书评

暂无评论

Learning Attentions: Residual Attentional Siamese Network fo...

31st IEEE/CVF Conference on computer Vision and Pattern Recognition (CVPR)

作者： Wang, Qiang Teng, Zhu Xing, Junliang Gao, Jin Hu, Weiming Maybank, Stephen University of Chinese Academy of Sciences Beijing China School of Computer and Information Technology Beijing Jiaotong University Beijing China National Laboratory of Pattern Recognition Institute of Automation Chinese Academy of Sciences Beijing China Department of Computer Science and Information Systems Birkbeck College University of London UK

ISBN: (纸本)9781538664209

Offline training for object tracking has recently shown great potentials in balancing tracking accuracy and speed. However, it is still difficult to adapt an offline trained model to a target tracked online. This work presents a Residual Attentional Siamese Network (RASNet) for high performance object tracking. The RASNet model reformulates the correlation filter within a Siamese tracking framework, and introduces different kinds of the attention mechanisms to adapt the model without updating the model online. In particular, by exploiting the offline trained general attention, the target adapted residual attention, and the channel favored feature attention, the RASNet not only mitigates the over-fitting problem in deep network training, but also enhances its discriminative capacity and adaptability due to the separation of representation learning and discriminator learning. The proposed deep architecture is trained from end to end and takes full advantage of the rich spatial temporal information to achieve robust visual tracking. Experimental results on two latest benchmarks, OTB-2015 and VOT2017, show that the RASNet tracker has the state-of-the-art tracking accuracy while runs at more than 80 frames per second.

关键词： Target tracking Correlation Feature extraction Training Adaptation models Visualization Object tracking

On the peculiarities of the exchange of data between applications in high-level languages and matlab functions 1

学校读者我要写书评

暂无评论

On the peculiarities of the exchange of data between applica...

1st Workshop computer Science and Engineering in the framework of the 5th International Scientific-Methodical Conference "Problems of Mathematical and Natural-Scientific Training in Engineering Education, CSITinMNSTinEE 2018

作者： Krasnovidov, Alexander V. Khomonenko, Anatoly D. Zabrodin, Andrew V. Smirnov, Alexander V. Department of Information and Computer Systems Emperor Alexander I St. Petersburg State Transport University St. Petersburg Russia Laboratory of Computer Aided Integrated Systems St.Petersburg Institute for Informatics and Automation of the RAS Saint Petersburg Russia

The possibilities of data exchange between functions in the language of the Matlab system with applications in high-level languages are considered. Programs in high-level languages appropriately to use in conjunction with mathematical packages to collect data, control various technological processes, and perform other similar actions. The instrumental means of organizing such an exchange are characterized. It had been shown the feasibility of integrating applications in high-level languages and the M-function of the Matlab system, if necessary, to organize input / output of large amounts of data. Copyright © by the papers’ authors.

关键词： Electronic data interchange

Convolutional ordinal regression forest for image ordinal estimation

学校读者我要写书评

暂无评论

arXiv 2020年

作者： Zhu, Haiping Shan, Hongming Zhang, Yuheng Che, Lingfu Xu, Xiaoyang Zhang, Junping Shi, Jianbo Wang, Fei-Yue The Shanghai Key Laboratory of Intelligent Information Processing School of Computer Science Fudan University Shanghai200433 China The Institute of Science and Technology for Brain-inspired Intelligence MOE Frontiers Center for Brain Science Fudan University Shanghai200433 China The Shanghai Center for Brain Science and Brain-inspired Technology Shanghai201210 China The GRASP Laboratory University of Pennsylvania PhiladelphiaPA United States The State Key Laboratory for Management and Control of Complex Systems Institute of Automation Chinese Academy of Sciences Beijing100190 China The Institute of Systems Engineering Macau University of Science and Technology 999078 China The University of Chinese Academy of Sciences Beijing100049 China

Image ordinal estimation is to predict the ordinal label of a given image, which can be categorized as an ordinal regression problem. Recent methods formulate an ordinal regression problem as a series of binary classification problems. Such methods cannot ensure that the global ordinal relationship is preserved since the relationships among different binary classifiers are neglected. We propose a novel ordinal regression approach, termed Convolutional Ordinal Regression Forest or CORF, for image ordinal estimation, which can integrate ordinal regression and differentiable decision trees with a convolutional neural network for obtaining precise and stable global ordinal relationships. The advantages of the proposed CORF are twofold. First, instead of learning a series of binary classifiers independently, the proposed method aims at learning an ordinal distribution for ordinal regression by optimizing those binary classifiers simultaneously. Second, the differentiable decision trees in the proposed CORF can be trained together with the ordinal distribution in an end-to-end manner. The effectiveness of the proposed CORF is verified on two image ordinal estimation tasks, i.e. facial age estimation and image aesthetic assessment, showing significant improvements and better stability over the state-of-the-art ordinal regression methods. Copyright © 2020, The Authors. All rights reserved.

关键词： Decision trees