检索结果-内蒙古大学图书馆

A regularization approach for instance-based superset label learning

学校读者我要写书评

暂无评论

arXiv 2019年

作者： Gong, Chen Liu, Tongliang Tang, Yuanyan Yang, Jian Yang, Jie Tao, Dacheng School of Computer Science and Engineering Nanjing University of Science and Technology Institute of Image Processing and Pattern Recognition Shanghai Jiao Tong University School of Software Faculty of Engineering and Information Technology University of Technology Sydney UltimoNSW2007 Australia Faculty of Science and Technology University of Macau Macau999078 China College of Computer Science Chongqing University Chongqing400000 China 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 School of Information Technologies Faculty of Engineering and Information Technologies University of Sydney J12/318 Cleveland St DarlingtonNSW2008 Australia

Different from the traditional supervised learning in which each training example has only one explicit label, Superset Label Learning (SLL) refers to the problem that a training example can be associated with a set of candidate labels, and only one of them is correct. Existing SLL methods are either regularization-based or instance-based, and the latter of which has achieved state-of-the-art performance. This is because the latest instance-based methods contain an explicit disambiguation operation that accurately picks up the groundtruth label of each training example from its ambiguous candidate labels. However, such disambiguation operation does not fully consider the mutually exclusive relationship among different candidate labels, so the disambiguated labels are usually generated in a nondiscriminative way, which is unfavorable for the instance-based methods to obtain satisfactory performance. To address this defect, we develop a novel Regularization approach for Instancebased Superset Label (RegISL) learning so that our instancebased method also inherits the good discriminative ability possessed by the regularization scheme. Specifically, we employ a graph to represent the training set, and require the examples that are adjacent on the graph to obtain similar labels. More importantly, a discrimination term is proposed to enlarge the gap of values between possible labels and unlikely labels for every training example. As a result, the intrinsic constraints among different candidate labels are deployed, and the disambiguated labels generated by RegISL are more discriminative and accurate than those output by existing instance-based algorithms. The experimental results on various tasks convincingly demonstrate the superiority of our RegISL to other typical SLL methods in terms of both training accuracy and test accuracy. Copyright © 2019, The Authors. All rights reserved.

关键词： Machine learning

Discrete Locally-Linear Preserving Hashing

学校读者我要写书评

暂无评论

Discrete Locally-Linear Preserving Hashing

IEEE International Conference on image processing

作者： Xiang Li Chao Ma Jie Yang Xiaolin Huang Institute of Image Processing and Pattern Recognition Shanghai Jiao Tong University Shanghai China

Recently, hashing has attracted considerable attention for nearest neighbor search due to its fast query speed and low storage cost. However, existing unsupervised hashing algorithms have two problems in common. Firstly, the widely utilized anchor graph construction algorithm has inherent limitations in local weight estimation. Secondly, the locally linear structure in the original feature space is seldom taken into account for binary encoding. Therefore, in this paper, we propose a novel unsupervised hashing method, dubbed “discrete locally-linear preserving hashing”, which effectively calculates the adjacent matrix while preserving the locally linear structure in the obtained hash space. Specifically, a novel local anchor embedding algorithm is adopted to construct the approximate adjacent matrix. After that, we directly minimize the reconstruction error with the discrete constrain to learn the binary codes. Experimental results on two typical image datasets indicate that the proposed method significantly outperforms the state-of-the-art unsupervised methods.

关键词：

LSTM MULTIPLE OBJECT TRACKER COMBINING MULTIPLE CUES

学校读者我要写书评

暂无评论

LSTM MULTIPLE OBJECT TRACKER COMBINING MULTIPLE CUES

IEEE International Conference on image processing

作者： Yiming Liang Yue Zhou Institute of Image Processing and Pattern Recognition Shanghai Jiao Tong University Shanghai China

Traditional methods for multiple object tracking usually consider features at image level and reason about simple space and time constraints. However, in this paper we propose a multiple object tracker based on LSTM network to learn temporally correlated features. Our tracker learns features on velocity, position and appearance aspects of the objects to improve tracking accuracy. In order to deal with occlusion problems, velocity model is also used to predict the lost detections for the occluded identities. Besides, pre-association is performed before appearance model to improve the efficiency of calculation. Final association problem is solved by taking the best match. Experiments in MOT17 dataset show that our tracker achieves leading performance compared to other state-of-the-art algorithms.

关键词：

An improved convex programming model for the inverse problem in intensity-modulated radiation therapy

学校读者我要写书评

暂无评论

International Journal of Performability Engineering 2018年第5期14卷 871-884页

作者： Lan, Yihua Zhang, Xingang Zhang, Jianyang Wang, Yang Hung, Chih-Cheng School of Computer and Information Technology Nanyang Normal University Nanyang473061 China Institute of Image Processing and Pattern Recognition Nanyang Normal University Nanyang473061 China Radiology Department Central Hospital of Nanyang Nanyang473061 China Laboratory for Machine Vision and Security Research College of Computing and Software Engineering Kennesaw State University - Marietta Campus 1100 South Marietta Parkway MariettaGA30067-2896 United States

Intensity modulated radiation therapy technology (IMRT) is one of the main approaches in cancer treatment because it can guarantee the killing of cancer cells while optimally protecting normal tissue from complications. Inverse planning, which is the core component of the entire IMRT system, is mainly based on accurate mathematical modeling and associated fast solving methods. In inverse planning, the fluence map optimization, which considers the multi-leaf collimator (MLC) modulation, is the current research focus. Although the hitting constrain problem with the unidirectional movement of leaf-sweeping has been solved, our goal is to solve the hitting constrain problem with the bidirectional movement of leaf-sweeping. In this study, we propose a non-synchronized type to solve the hitting constrain problem with the bidirectional movement of leaf-sweeping schemes for IMRT. In solving this problem, a new mathematical model is proposed under the framework of convex programming. The advantage of the convex model is to avoid the uncertainty and inaccuracy that occurs in the non-convex programming solving process. Experimental results for two clinical testing cases show that under the same condition of total number of monitoring units, the new proposed model produces better dose distribution than those of the total variance and quadratic models. © 2018 Totem Publisher, Inc. All rights reserved.

关键词： Convex optimization

Pulsar candidate selection using ensemble networks for FAST drift-scan survey

学校读者我要写书评

暂无评论

arXiv 2019年

作者： Wang, Hongfeng Zhu, Weiwei Guo, Ping Li, Di Feng, Sibo Yin, Qian Miao, Chenchen Tao, Zhenzhao Pan, Zhichen Wang, Pei Zheng, Xin Deng, Xiaodan Liu, Zhijie Xie, Xiaoyao Yu, Xuhong You, Shanping Zhang, Hui Image Processing and Pattern Recognition Laboratory College of Information Science and Technology Beijing Normal University Beijing100875 China CAS Key Laboratory of FAST Chinese Academy of Science Beijing100101 China School of Information Management Dezhou University Dezhou253023 China Image Processing and Pattern Recognition Laboratory School of Systems Science Beijing Normal University Beijing100875 China University of Chinese Academy of Sciences Beijing100049 China Key Laboratory of Information and Computing Science Guizhou Province Guizhou Normal University Guiyang550001 China School of Physics and Electronic Science Guizhou Normal University Guiyang550001 China

The Commensal Radio Astronomy Five-hundred-meter Aperture Spherical radio Telescope (FAST) Survey (CRAFTS) utilizes the novel drift-scan commensal survey mode of FAST and can generate billions of pulsar candidate signals. The human experts are not likely to thoroughly examine these signals, and various machine sorting methods are used to aid the classification of the FAST candidates. In this study, we propose a new ensemble classification system for pulsar candidates. This system denotes the further development of the pulsar image-based classification system (PICS), which was used in the Arecibo Telescope pulsar survey, and has been retrained and customized for the FAST drift-scan survey. In this study, we designed a residual network model comprising 15 layers to replace the convolutional neural networks (CNNs) in PICS. The results of this study demonstrate that the new model can sort >96% of real pulsars to belong the top 1% of all candidates and classify > 1.6 million candidates per day using a dual-GPU and 24-core computer. This increased speed and efficiency can help to facilitate real-time or quasi-real-time processing of the pulsar-search data stream obtained from CRAFTS. In addition, we have published the labeled FAST data used in this study online, which can aid in the development of new deep learning techniques for performing pulsar searches. Copyright © 2019, The Authors. All rights reserved.

关键词： Pulsars

Why is the Winner the Best?

学校读者我要写书评

暂无评论

Why is the Winner the Best?

Conference on Computer Vision and pattern recognition (CVPR)

作者： M. Eisenmann A. Reinke V. Weru M. D. Tizabi F. Isensee T. J. Adler S. Ali V. Andrearczyk M. Aubreville U. Baid S. Bakas N. Balu S. Bano J. Bernal S. Bodenstedt A. Casella V. Cheplygina M. Daum M. De Bruijne A. Depeursinge R. Dorent J. Egger D. G. Ellis S. Engelhardt M. Ganz N. Ghatwary G. Girard P. Godau A. Gupta L. Hansen K. Harada M. Heinrich N. Heller A. Hering A. Huaulmé P. Jannin A. E. Kavur O. Kodym M. Kozubek J. Li H. Li J. Ma C. Martín-Isla B. Menze A. Noble V. Oreiller N. Padoy S. Pati K. Payette T. Rädsch J. Rafael-Patiño V. Singh Bawa S. Speidel C. H. Sudre K. Van Wijnen M. Wagner D. Wei A. Yamlahi M. H. Yap C. Yuan M. Zenk A. Zia D. Zimmerer D. Aydogan B. Bhattarai L. Bloch R. Brüngel J. Cho C. Choi Q. Dou I. Ezhov C. M. Friedrich C. Fuller R. R. Gaire A. Galdran Á. García Faura M. Grammatikopoulou S. Hong M. Jahanifar I. Jang A. Kadkhodamohammadi I. Kang F. Kofler S. Kondo H. Kuijf M. Li M. Luu T. Martinčič P. Morais M. A. Naser B. Oliveira D. Owen S. Pang J. Park S. Park S. Płotka E. Puybareau N. Rajpoot K. Ryu N. Saeed A. Shephard P. Shi D. Štepec R. Subedi G. Tochon H. R. Torres H. Urien J. L. Vilaça K. A. Wahid H. Wang J. Wang L. Wang X. Wang B. Wiestler M. Wodzinski F. Xia J. Xie Z. Xiong S. Yang Y. Yang Z. Zhao K. Maier-Hein P. F. Jäger A. Kopp-Schneider L. Maier-Hein Division of Intelligent Medical Systems German Cancer Research Center (DKFZ) Heidelberg Germany Helmholtz Imaging German Cancer Research Center (DKFZ) Heidelberg Germany Faculty of Mathematics and Computer Science Heidelberg University Heidelberg Germany Division of Biostatistics German Cancer Research Center (DKFZ) Heidelberg Germany Division of Medical Image Computing German Cancer Research Center (DKFZ) Heidelberg Germany Faculty of Engineering and Physical Sciences School of Computing University of Leeds Leeds UK Institute of Informatics School of Management HES-SO Valais-Wallis University of Applied Sciences and Arts Western Switzerland Sierre Switzerland Department of Nuclear Medicine and Molecular Imaging Lausanne University Hospital Lausanne Switzerland Technische Hochschule Ingolstadt Ingolstadt Germany Center for Artificial Intelligence and Data Science for Integrated Diagnostics (AI2D) and Center for Biomedical Image Computing and Analytics (CBICA) University of Pennsylvania Philadelphia PA USA Department of Pathology and Laboratory Medicine Perelman School of Medicine University of Pennsylvania Philadelphia PA USA Department of Radiology Perelman School of Medicine University of Pennsylvania Philadelphia PA USA Department of Radiology University of Washington Seattle WA USA Department of Computer Science Wellcome/EPSRC Centre for Interventional and Surgical Sciences (WEISS) University College London London UK Universitat Autònoma de Barcelona & Computer Vision Center Barcelona Spain Division of Translational Surgical Oncology National Center for Tumor Diseases (NCT/UCC) Dresden Dresden Germany Department of Advanced Robotics Istituto Italiano di Tecnologia Italy Department of Electronics Information and Bioengineering Politecnico di Milano Milan Italy IT University of Copenhagen Copenhagen Denmark Department of General Visceral and Transplantation Surgery Heidelberg University Hospital Heidelberg Germany Department of Radiology and Nuc

International benchmarking competitions have become fundamental for the comparative performance assessment of image analysis methods. However, little attention has been given to investigating what can be learnt from these competitions. Do they really generate scientific progress? What are common and successful participation strategies? What makes a solution superior to a competing method? To address this gap in the literature, we performed a multicenter study with all 80 competitions that were conducted in the scope of IEEE ISBI 2021 and MICCAI 2021. Statistical analyses performed based on comprehensive descriptions of the submitted algorithms linked to their rank as well as the underlying participation strategies revealed common characteristics of winning solutions. These typically include the use of multi-task learning (63%) and/or multi-stage pipelines (61%), and a focus on augmentation (100%), image preprocessing (97%), data curation (79%), and post-processing (66%). The “typical” lead of a winning team is a computer scientist with a doctoral degree, five years of experience in biomedical image analysis, and four years of experience in deep learning. Two core general development strategies stood out for highly-ranked teams: the reflection of the metrics in the method design and the focus on analyzing and handling failure cases. According to the organizers, 43% of the winning algorithms exceeded the state of the art but only 11% completely solved the respective domain problem. The insights of our study could help researchers (1) improve algorithm development strategies when approaching new problems, and (2) focus on open research questions revealed by this work.

关键词：

Adversarial attack type I: Cheat classifiers by significant changes

学校读者我要写书评

暂无评论

arXiv 2018年

作者： Tang, Sanli Huang, Xiaolin Chen, Mingjian Sun, Chengjin Yang, Jie Institute of Image Processing and Pattern Recognition Institute of Medical Robotics Shanghai Jiao Tong University Shanghai China

Despite the great success of deep neural networks, the adversarial attack can cheat some well-trained classifiers by small permutations. In this paper, we propose another type of adversarial attack that can cheat classifiers by significant changes. For example, we can significantly change a face but well-trained neural networks still recognize the adversarial and the original example as the same person. Statistically, the existing adversarial attack increases Type II error and the proposed one aims at Type I error, which are hence named as Type II and Type I adversarial attack, respectively. The two types of attack are equally important but are essentially different, which are intuitively explained and numerically evaluated. To implement the proposed attack, a supervised variation autoencoder is designed and then the classifier is attacked by updating the latent variables using gradient information. Besides, with pretrained generative models, Type I attack on latent spaces is investigated as well. Experimental results show that our method is practical and effective to generate Type I adversarial examples on large-scale image datasets. Most of these generated examples can pass detectors designed for defending Type II attack and the strengthening strategy is only efficient with a specific type attack, both implying that the underlying reasons for Type I and Type II attack are different. Copyright © 2018, The Authors. All rights reserved.

关键词： Deep neural networks

Robust Visual Tracking Revisited: From Correlation Filter to Template Matching

学校读者我要写书评

暂无评论

arXiv 2019年

作者： Liu, Fanghui Gong, Chen Huang, Xiaolin Zhou, Tao Yang, Jie Tao, Dacheng Institute of Image Processing and Pattern Recognition Shanghai Jiao Tong University Shanghai200240 China School of Computer Science and Engineering Nanjing University of Science and Technology Nanjing210094 China UBTECH Sydney Artificial Intelligence Centre School of Information Technologies Faculty of Engineering and Information Technologies University of Sydney 6 Cleveland St DarlingtonNSW2008 Australia

In this paper, we propose a novel matching based tracker by investigating the relationship between template matching and the recent popular correlation filter based trackers (CFTs). Compared to the correlation operation in CFTs, a sophisticated similarity metric termed "mutual buddies similarity" (MBS) is proposed to exploit the relationship of multiple reciprocal nearest neighbors for target matching. By doing so, our tracker obtains powerful discriminative ability on distinguishing target and background as demonstrated by both empirical and theoretical analyses. Besides, instead of utilizing single template with the improper updating scheme in CFTs, we design a novel online template updating strategy named "memory filtering" (MF), which aims to select a certain amount of representative and reliable tracking results in history to construct the current stable and expressive template set. This scheme is beneficial for the proposed tracker to comprehensively "understand" the target appearance variations, "recall" some stable results. Both qualitative and quantitative evaluations on two benchmarks suggest that the proposed tracking method performs favorably against some recently developed CFTs and other competitive trackers. Copyright © 2019, The Authors. All rights reserved.

关键词： Template matching

Incremental transformer with deliberation decoder for document grounded conversations

学校读者我要写书评

暂无评论

arXiv 2019年

作者： Li, Zekang Niu, Cheng Meng, Fandong Feng, Yang Li, Qian Zhou, Jie Dian Group School of Electronic Information and Communications Huazhong University of Science and Technology Pattern Recognition Center WeChat AI Tencent Inc China Key Laboratory of Intelligent Information Processing Institute of Computing Technology Chinese Academy of Sciences School of Computer Science and Engineering Northeastern University China

Document Grounded Conversations is a task to generate dialogue responses when chatting about the content of a given document. Obviously, document knowledge plays a critical role in Document Grounded Conversations, while existing dialogue models do not exploit this kind of knowledge effectively enough. In this paper, we propose a novel Transformerbased architecture for multi-turn document grounded conversations. In particular, we devise an Incremental Transformer to encode multi-turn utterances along with knowledge in related documents. Motivated by the human cognitive process, we design a two-pass decoder (Deliberation Decoder) to improve context coherence and knowledge correctness. Our empirical study on a real-world Document Grounded Dataset proves that responses generated by our model significantly outperform competitive baselines on both context coherence and knowledge relevance. Copyright © 2019, The Authors. All rights reserved.

关键词： Decoding