检索结果-内蒙古大学图书馆

Towards a unified quadrature framework for large-scale kernel machines

学校读者我要写书评

暂无评论

arXiv 2020年

作者： Liu, Fanghui Huang, Xiaolin Chen, Yudong Suykens, Johan A.K. KU Leuven LeuvenB-3001 Belgium Institute of Image Processing and Pattern Recognition Shanghai Jiao Tong University Shanghai200240 China Institute of Medical Robotics Shanghai Jiao Tong University Shanghai200240 China School of Operations Research and Information Engineering Cornell University IthacaNY14850 United States

In this paper, we develop a quadrature framework for large-scale kernel machines via a numerical integration representation. Considering that the integration domain and measure of typical kernels, e.g., Gaussian kernels, arc-cosine kernels, are fully symmetric, we leverage deterministic fully symmetric interpolatory rules to efficiently compute quadrature nodes and associated weights for kernel approximation. The developed interpolatory rules are able to reduce the number of needed nodes while retaining a high approximation accuracy. Further, we randomize the above deterministic rules by the classical Monte-Carlo sampling and control variates techniques with two merits: 1) The proposed stochastic rules make the dimension of the feature mapping flexibly varying, such that we can control the discrepancy between the original and approximate kernels by tuning the dimnension. 2) Our stochastic rules have nice statistical properties of unbiasedness and variance reduction with fast convergence rate. In addition, we elucidate the relationship between our deterministic/stochastic interpolatory rules and current quadrature rules for kernel approximation, including the sparse grids quadrature and stochastic spherical-radial rules, thereby unifying these methods under our framework. Experimental results on several benchmark datasets show that our methods compare favorably with other representative kernel approximation based methods. Copyright © 2020, The Authors. All rights reserved.

关键词： Stochastic systems

Data consistent artifact reduction for limited angle tomography with deep learning prior

学校读者我要写书评

暂无评论

arXiv 2019年

作者： Huang, Yixing Preuhs, Alexander Lauritsch, Günter Manhart, Michael Huang, Xiaolin Maier, Andreas Pattern Recognition Lab Friedrich-Alexander-Universitt Erlangen-Nrnberg Erlangen91058 Germany Siemens Healthcare GmbH Forchheim91301 Germany Institute of Image Processing and Pattern Recognition Shanghai Jiao Tong University Shanghai200240 China Erlangen91058 Germany

Robustness of deep learning methods for limited angle tomography is challenged by two major factors: a) due to insufficient training data the network may not generalize well to unseen data;b) deep learning methods are sensitive to noise. Thus, generating reconstructed images directly from a neural network appears inadequate. We propose to constrain the reconstructed images to be consistent with the measured projection data, while the unmeasured information is complemented by learning based methods. For this purpose, a data consistent artifact reduction (DCAR) method is introduced: First, a prior image is generated from an initial limited angle reconstruction via deep learning as a substitute for missing information. Afterwards, a conventional iterative reconstruction algorithm is applied, integrating the data consistency in the measured angular range and the prior information in the missing angular range. This ensures data integrity in the measured area, while inaccuracies incorporated by the deep learning prior lie only in areas where no information is acquired. The proposed DCAR method achieves significant image quality improvement: for 120° cone-beam limited angle tomography more than 10% RMSE reduction in noise-free case and more than 24% RMSE reduction in noisy case compared with a state-of-the-art U-Net based method. Copyright © 2019, The Authors. All rights reserved.

关键词： image enhancement

Road segmentation for remote sensing images using adversarial spatial pyramid networks

学校读者我要写书评

暂无评论

arXiv 2020年

作者： Shamsolmoali, Pourya Zareapoor, Masoumeh Zhou, Huiyu Wang, Ruili Yang, Jie Institute of Image Processing and Pattern Recognition Shanghai Jiao Tong University Shanghai200240 China School of Informatics University of Leicester LeicesterLE1 7RH United Kingdom School of Logistics and Transportation Central South University of Forestry and Technology China School of Natural and Computational Sciences Massey University Auckland New Zealand

To read the paper please go to IEEE Transactions on Geoscience and Remote Sensing on IEEE Xplore. Road extraction in remote sensing images is of great importance for a wide range of applications. Because of the complex background, and high density, most of the existing methods fail to accurately extract a road network that appears correct and complete. Moreover, they suffer from either insufficient training data or high costs of manual annotation. To address these problems, we introduce a new model to apply structured domain adaption for synthetic image generation and road segmentation. We incorporate a feature pyramid network into generative adversarial networks to minimize the difference between the source and target domains. A generator is learned to produce quality synthetic images, and the discriminator attempts to distinguish them. We also propose a feature pyramid network that improves the performance of the proposed model by extracting effective features from all the layers of the network for describing different scales’ objects. Indeed, a novel scale-wise architecture is introduced to learn from the multi-level feature maps and improve the semantics of the features. For optimization, the model is trained by a joint reconstruction loss function, which minimizes the difference between the fake images and the real ones. A wide range of experiments on three datasets prove the superior performance of the proposed approach in terms of accuracy and efficiency. In particular, our model achieves state-of-the-art 78.86 IOU on the Massachusetts dataset with 14.89M parameters and 86.78B FLOPs, with 4× fewer FLOPs but higher accuracy (+3.47% IOU) than the top performer among state-of-the-art approaches used in the evaluation. Copyright © 2020, The Authors. All rights reserved.

关键词： Generative adversarial networks

A novel deep structure U-net for sea-land segmentation in remote sensing images

学校读者我要写书评

暂无评论

arXiv 2020年

作者： Shamsolmoali, Pourya Zareapoor, Masoumeh Wang, Ruili Zhou, Huiyu Yang, Jie Institute of Image Processing and Pattern Recognition Shanghai Jiao Tong University Shanghai200240 China School of Logistics and Transportation Central South University of Forestry and Technology China School of Natural and Computational Sciences Massey University Auckland New Zealand Department of Informatics University of Leicester LeicesterLE1 7RH United Kingdom

Sea-land segmentation is an important process for many key applications in remote sensing. Proper operative sea–land segmentation for remote sensing images remains a challenging issue due to complex and diverse transition between sea and lands. Although several Convolutional Neural Networks (CNNs) have been developed for sea-land segmentation, the performance of these CNNs is far from the expected target. This paper presents a novel deep neural network structure for pixel-wise sea-land segmentation, a Residual Dense U-Net (RDU-Net), in complex and high-density remote sensing images. RDU-Net is a combination of both downsampling and upsampling paths to achieve satisfactory results. In each down- and up-sampling path, in addition to the convolution layers, several densely connected residual network blocks are proposed to systematically aggregate multi-scale contextual information. Each dense network block contains multilevel convolution layers, short-range connections and an identity mapping connection which facilitates features reuse in the network and makes full use of the hierarchical features from the original images. These proposed blocks have a certain number of connections that are designed with shorter distance backpropagation between the layers and can significantly improve segmentation results whilst minimizing computational costs. We have performed extensive experiments on two real datasets Google-Earth and ISPRS and compare the proposed RDU-Net against several variations of Dense Networks. The experimental results show that RDU-Net outperforms the other state-of-the-art approaches on the sea-land segmentation tasks. Copyright © 2020, The Authors. All rights reserved.

关键词： Deep neural networks

Multi-level graph convolutional network with automatic graph learning for hyperspectral image classification

学校读者我要写书评

暂无评论

arXiv 2020年

作者： Wan, Sheng Gong, Chen Pan, Shirui Yang, Jie Yang, Jian PCA Lab Key Laboratory of Intelligent Perception and Systems for High-Dimensional Information of Ministry of Education Jiangsu Key Laboratory of Image Video Understanding for Social Security 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 Faculty of Information Technology Monash University ClaytonVIC3800 Australia

Nowadays, deep learning methods, especially the Graph Convolutional Network (GCN), have shown impressive performance in hyperspectral image (HSI) classification. However, the current GCN-based methods treat graph construction and image classification as two separate tasks, which often results in suboptimal performance. Another defect of these methods is that they mainly focus on modeling the local pairwise importance between graph nodes while lack the capability to capture the global contextual information of HSI. In this paper, we propose a Multi-level GCN with Automatic Graph Learning method (MGCN-AGL) for HSI classification, which can automatically learn the graph information at both local and global levels. By employing attention mechanism to characterize the importance among spatially neighboring regions, the most relevant information can be adaptively incorporated to make decisions, which helps encode the spatial context to form the graph information at local level. Moreover, we utilize multiple pathways for local-level graph convolution, in order to leverage the merits from the diverse spatial context of HSI and to enhance the expressive power of the generated representations. To reconstruct the global contextual relations, our MGCN-AGL encodes the long range dependencies among image regions based on the expressive representations that have been produced at local level. Then inference can be performed along the reconstructed graph edges connecting faraway regions. Finally, the multi-level information is adaptively fused to generate the network output. In this means, the graph learning and image classification can be integrated into a unified framework and benefit each other. Extensive experiments have been conducted on three real-world hyperspectral datasets, which are shown to outperform the state-of-the-art methods. Copyright © 2020, The Authors. All rights reserved.

关键词： image classification

Unsupervised Local Discrimination for Medical images

学校读者我要写书评

暂无评论

arXiv 2021年

作者： Chen, Huai Wang, Renzhen Wang, Xiuying Li, Jieyu Fang, Qu Li, Hui Bai, Jianhao Peng, Qing Meng, Deyu Wang, Lisheng Institute of Image Processing and Pattern Recognition Department of Automation Shanghai Jiao Tong University Shanghai200240 China School of Mathematics and Statistics Ministry of Education Key Lab of Intelligent Networks and Network Security Xi’an Jiaotong University Xi’an710049 China The School of Computer Science The University of Sydney SydneyNSW2006 Australia Department of Ophthalmology Shanghai Tenth People’s Hospital Tongji University Shanghai200240 China The Cooperative Medianet Innovation Center Shanghai Jiao Tong University Shanghai200240 China The Changchun GeneScience Pharmaceutical Co. LTD China

Contrastive learning, which aims to capture general representation from unlabeled images to initialize the medical analysis models, has been proven effective in alleviating the high demand for expensive annotations. Current methods mainly focus on instance-wise comparisons to learn the global discriminative features, however, pretermitting the local details to distinguish tiny anatomical structures, lesions, and tissues. To address this challenge, in this paper, we propose a general unsupervised representation learning framework, named local discrimination (LD), to learn local discriminative features for medical images by closely embedding semantically similar pixels and identifying regions of similar structures across different images. Specifically, this model is equipped with an embedding module for pixel-wise embedding and a clustering module for generating segmentation. And these two modules are unified through optimizing our novel region discrimination loss function in a mutually beneficial mechanism, which enables our model to reflect structure information as well as measure pixel-wise and region-wise similarity. Furthermore, based on LD, we propose a center-sensitive one-shot landmark localization algorithm and a shape-guided cross-modality segmentation model to foster the generalizability of our model. When transferred to downstream tasks, the learned representation by our method shows a better generalization, outperforming representation from 18 state-of-the-art (SOTA) methods and winning 9 out of all 12 downstream tasks. Especially for the challenging lesion segmentation tasks, the proposed method achieves significantly better performances. The source codes are publicly available at https://***/HuaiChen-1994/LDLearning. Copyright © 2021, The Authors. All rights reserved.

关键词： Embeddings

EEG-Based Brain-Computer Interfaces Are Vulnerable to Backdoor Attacks

学校读者我要写书评

暂无评论

Research Square

Research Square 2021年

作者： Meng, Lubin Huang, Jian Zeng, Zhigang Jiang, Xue Yu, Shan Jung, Tzyy-Ping Lin, Chin-Teng Chavarriaga, Ricardo Wu, Dongrui Ministry of Education Key Laboratory of Image Processing and Intelligent Control School of Artificial Intelligence and Automation Huazhong University of Science and Technology Wuhan China Brainnetome Center and National Laboratory of Pattern Recognition Institute of Automation Chinese Academy of Sciences Beijing China La Jolla CA United States Center for Advanced Neurological Engineering Institute of Engineering in Medicine UCSD La Jolla CA United States Centre of Artificial Intelligence Faculty of Engineering and Information Technology University of Technology Sydney Australia ZHAW DataLab Zürich University of Applied Sciences Winterthur8401 Switzerland

Research and development of electroencephalogram (EEG) based brain-computer interfaces (BCIs) have advanced rapidly, partly due to the wide adoption of sophisticated machine learning approaches for decoding the EEG signals. However, recent studies have shown that machine learning algorithms are vulnerable to adversarial attacks, e.g., the attacker can add tiny adversarial perturbations to a test sample to fool the model, or poison the training data to insert a secret backdoor. Previous research has shown that adversarial attacks are also possible for EEG-based BCIs. However, only adversarial perturbations have been considered, and the approaches are theoretically sound but very difficult to implement in practice. This article proposes to use narrow period pulse for poisoning attack of EEG-based BCIs, which is more feasible in practice and has never been considered before. One can create dangerous backdoors in the machine learning model by injecting poisoning samples into the training set. Test samples with the backdoor key will then be classified into the target class specified by the attacker. What most distinguishes our approach from previous ones is that the backdoor key does not need to be synchronized with the EEG trials, making it very easy to implement. The effectiveness and robustness of the backdoor attack approach is demonstrated, highlighting a critical security concern for EEG-based BCIs. © 2021, CC BY.

关键词： Electroencephalography

The Effect of Data Augmentation on Classification of Atrial Fibrillation in Short Single-Lead ECG Signals Using Deep Neural Networks

学校读者我要写书评

暂无评论

The Effect of Data Augmentation on Classification of Atrial ...

IEEE International Conference on Acoustics, Speech and Signal processing

作者： Faezeh Nejati Hatamian Nishant Ravikumar Sulaiman Vesal Felix P. Kemeth Matthias Struck Andreas Maier Department of Image Processing and Medical Technology Fraunhofer Institute for Integrated Circuits IIS Erlangen Germany Centre for Computational Imaging and Simulation Technologies in Biomedicine (CISTIB) School of Computing LICAMM Leeds Institute of Cardiovascular and Metabolic Medicine School of Medicine University of Leeds United Kingdom Pattern Recognition Lab Friedrich-Alexander University Erlangen-Nürnberg Erlangen Germany

ISBN: (数字)9781509066315

ISBN: (纸本)9781509066322

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