检索结果-内蒙古大学图书馆

pattern recognition 2024年 151卷

作者： Huihui Shao Jing Bai Rusong Wu Jinzhe Jiang Hongbo Liang the School of Computer Science and Engineering North Minzu University Yinchuan 750021 China the Key Laboratory of Images Processing and Pattern Recognition Laboratory Commission: IPPRLab North Minzu University Yinchuan 750021 China

Learning with asymmetric kernels: Least squares and feature interpretation

学校读者我要写书评

暂无评论

arXiv 2022年

作者： He, Mingzhen He, Fan Shi, Lei Huang, Xiaolin Suykens, Johan A.K. Institute Of Image Processing And Pattern Recognition Shanghai Jiao Tong University Shanghai200240 China Shanghai Key Laboratory For Contemporary Applied Mathematics Fudan University Shanghai200433 China School Of Mathematical Sciences Fudan University Shanghai200433 China KU Leuven LeuvenB-3001 Belgium

Asymmetric kernels naturally exist in real life, e.g., for conditional probability and directed graphs. However, most of the existing kernel-based learning methods require kernels to be symmetric, which prevents the use of asymmetric kernels. This paper addresses the asymmetric kernel-based learning in the framework of the least squares support vector machine named AsK-LS, resulting in the first classification method that can utilize asymmetric kernels directly. We will show that AsK-LS can learn with asymmetric features, namely source and target features, while the kernel trick remains applicable, i.e., the source and target features exist but are not necessarily known. Besides, the computational burden of AsK-LS is as cheap as dealing with symmetric kernels. Experimental results on the Corel database, directed graphs, and the UCI database will show that, in the case asymmetric information is crucial, the proposed AsK-LS can learn with asymmetric kernels and performs much better than the existing kernel methods that have to do symmetrization to accommodate asymmetric kernels. © 2022, CC BY.

关键词： Directed graphs

A generalization theory based on independent and task-identically distributed assumption

学校读者我要写书评

暂无评论

arXiv 2019年

作者： Zheng, Guanhua Sang, Jitao Li, Houqiang Yu, Jian Xu, Changsheng University of Science and Technology of China School of Computer and Information Technology Beijing Key Laboratory of Traffic Data Analysis and Mining Beijing Jiaotong University Beijing100044 China Chinese Academy of Sciences Key Laboratory of Technology in Geo-Spatial Information Processing and Application System Hefei230026 China National Lab of Pattern Recognition Institute of Automation CAS Beijing100190 China University of Chinese Academy of Sciences

—Existing generalization theories analyze the generalization performance mainly based on the model complexity and training process. The ignorance of the task properties, which results from the widely used IID assumption, makes these theories fail to interpret many generalization phenomena or guide practical learning tasks. In this paper, we propose a new Independent and Task-Identically Distributed (ITID) assumption, to consider the task properties into the data generating process. The derived generalization bound based on the ITID assumption identifies the significance of hypothesis invariance in guaranteeing generalization performance. Based on the new bound, we introduce a practical invariance enhancement algorithm from the perspective of modifying data distributions. Finally, we verify the algorithm and theorems in the context of image classification task on both toy and real-world datasets. The experimental results demonstrate the reasonableness of the ITID assumption and the effectiveness of new generalization theory in improving practical generalization performance. Copyright © 2019, The Authors. All rights reserved.

关键词： Classification (of information)

Efficient spatialtemporal context modeling for action recognition?

学校读者我要写书评

暂无评论

arXiv 2021年

作者： Cao, Congqi Lu, Yue Zhang, Yifan Jiang, Dongmei Zhang, Yanning Natl. Engineering Laboratory for Integrated Aero-Space-Ground-Ocean Big Data Application Technology Shaanxi Provincial Key Lab on Speech and Image Information Processing School of Computer Science Northwestern Poly-technical University Xi'an710129 China National Laboratory of Pattern Recognition Institute of Automation Chinese Academy of Sciences University of Chinese Academy of Sciences Beijing100190 China

Contextual information plays an important role in action recognition. Local operations have difficulty to model the relation between two elements with a long-distance interval. However, directly modeling the contextual information between any two points brings huge cost in computation and memory, especially for action recognition, where there is an additional temporal dimension. Inspired from 2D criss-cross attention used in segmentation task, we propose a recurrent 3D criss-cross attention (RCCA-3D) module to model the dense long-range spatiotemporal contextual information in video for action recognition. The global context is factorized into sparse relation maps. We model the relationship between points in the same line along the direction of horizon, vertical and depth at each time, which forms a 3D criss-cross structure, and duplicate the same operation with recurrent mechanism to transmit the relation between points in a line to a plane finally to the whole spatiotemporal space. Compared with the non-local method, the proposed RCCA-3D module reduces the number of parameters and FLOPs by 25% and 30% for video context modeling. We evaluate the performance of RCCA-3D with two latest action recognition networks on three datasets and make a thorough analysis of the architecture, obtaining the optimal way to factorize and fuse the relation maps. Comparisons with other state-of-the-art methods demonstrate the effectiveness and efficiency of our model. Copyright © 2021, The Authors. All rights reserved.

关键词： Machine learning

Analysis of Least Squares Regularized Regression in Reproducing Kernel Kreın Spaces

学校读者我要写书评

暂无评论

arXiv 2020年

作者： Liu, Fanghui Shi, Lei Huang, Xiaolin Yang, Jie Suykens, Johan A.K. Department of Electrical Engineering [ESAT-STADIUS KU Leuven LeuvenB-3001 Belgium Institute of Image Processing and Pattern Recognition Institute of Medical Robotics Shanghai Jiao Tong University Shanghai China Shanghai Key Laboratory for Contemporary Applied Mathematics School of Mathematical Sciences Fudan University Shanghai China

In this paper, we study the asymptotical properties of least squares regularized regression with indefinite kernels in reproducing kernel Kreın spaces (RKKS). The classical approximation analysis cannot be directly applied to study its asymptotical behavior under the framework of learning theory as this problem is in essence non-convex and outputs stationary points. By introducing a bounded hyper-sphere constraint to such non-convex regularized risk minimization problem, we theoretically demonstrate that this problem has a globally optimal solution with a closed form on the sphere, which makes our approximation analysis feasible in RKKS. Accordingly, we modify traditional error decomposition techniques, prove convergence results for the introduced hypothesis error based on matrix perturbation theory, and derive learning rates of such regularized regression problem in RKKS. Under some conditions, the derived learning rates in RKKS are the same as that in reproducing kernel Hilbert spaces (RKHS), which is actually the first work on approximation analysis of regularized learning algorithms in RKKS. Copyright © 2020, The Authors. All rights reserved.

关键词： Learning algorithms

An Improved Adaptive Exponential Smoothing Model for Short-term Travel Time Forecasting of Urban Arterial Street

学校读者我要写书评

暂无评论

Acta Automatica Sinica 2008年第11期34卷 1404-1409页

作者： Zhi-Peng LI Hong YU Yun-Cai LIU Fu-Qiang LIU Key Laboratory of Embedded System and Service Computing Ministry of Education Tongji University Shanghai 200092 P. R. China Intelligent Transportation System Department Shanghai Electrical Apparatus Research Institute Shanghai 200063 P. R. China Institute of Image Processing and Pattern Recognition Shanghai Jiao Tong University Shanghai 200240 P. R. China

Short-term forecasting of travel time is essential for the success of intelligent transportation system. In this paper, we review the state-of-art of short-term traffic forecasting models and outline their basic ideas, related works, advantages and disadvantages of each model. An improved adaptive exponential smoothing (IAES) model is also proposed to overcome the drawbacks of the previous adaptive exponential smoothing model. Then, comparing experiments are carried out under normal traffic condition and abnormal traffic condition to evaluate the performance of four main branches of forecasting models on direct travel time data obtained by license plate matching (LPM). The results of experiments show each model seems to have its own strength and weakness. The forecasting performance of IASE is superior to other models in shorter forecasting horizon (one and two step forecasting) and the IASE is capable of dealing with all kind of traffic conditions.

关键词： Travel time short-term forecasting license plate matching (LPM) exponential smoothing

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

Image denoising algorithm based on noise detection

学校读者我要写书评

暂无评论

Moshi Shibie yu Rengong Zhineng/pattern recognition and Artificial Intelligence 2008年第3期21卷 298-302页

作者： Jin, Liang-Hai Li, De-Hua State Education Commission Key Laboratory for Image Processing and Intelligent Control Institute for Pattern Recognition and Artificial Intelligence Huazhong Univ. of Sci. and Technol. Wuhan 430074 China

An efficient image denoising algorithm is introduced. Firstly, image pixels are classified into noisy pixels and noise-free pixels by four directional operators. Then an adaptive weighted median filter is designed to remove and restore the detected noisy pixels and keep the noise-free ones unchanged. Experimental results indicate that the proposed algorithm preserves image details well while removing impulsive noise efficiently, and its filtering performance is significantly superior to the classical median filter and some other typical and recently developed improved median filters.

关键词： Median filters

Boosting discriminative model for moving cast shadow detection

学校读者我要写书评

暂无评论

Jisuanji Xuebao/Chinese Journal of Computers 2007年第8期30卷 1295-1301页

作者： Zha, Yu-Fei Chu, Ying Wang, Xun Ma, Shi-Ping Bi, Du-Yan Signal and Information Processing Laboratory Engineering College Air Force Engineering University Xi'an 710038 China Key Laboratory for Image Processing and Intelligent Control Institute of Pattern Recognition and Artificial Intelligence Huazhong Univ. of Sci. and Technol. Wuhan 430074 China

Moving cast shadow causes serious problem while segmenting and extracting foreground from image sequences, due to the misclassification of moving shadow as foreground. This paper proposes a Boosting discriminative model to eliminate cast shadow on Discriminative Random Fields (DRFs). The method combines different features for Boosting to discriminate cast shadow from moving objects, then temporal and spatial coherence of shadow and foreground are incorporated on Discriminative Random Fields and the problem can be solved by graph cut. Firstly, moving objects are obtained by background subtraction;secondly, shadow candidates can be derived through pre-processing moving objects, in terms of the shadow physical property;thirdly, color information and texture information is derived by comparing shadow and foreground points in current image with corresponding points in background image, which are selected as features for Boosting;finally, temporal and spatial coherence of shadow and foreground is employed on Discriminative Random Fields and discriminate shadow and foreground by graph cut accurately.

关键词： Image processing

Sparse generalized canonical correlation analysis: Distributed alternating iteration based approach

学校读者我要写书评

暂无评论

arXiv 2020年

作者： Cai, Jia Lv, Kexin Huo, Junyi Huang, Xiaolin Yang, Jie School of Statistics and Mathematics Guangdong University of Finance & Economics Big Data and Educational Statistics Application Laboratory 21 Chisha Road Guangzhou Guangdong510320 China Institute of Image Processing and Pattern Recognition Shanghai Jiao Tong University MOE Key Laboratory of System Control and Information Processing 800 Dongchuan Road Shanghai200240 China School of Electronics and Computer Science University of Southampton University Road SouthamptonSO17 1BJ United Kingdom

Sparse canonical correlation analysis (CCA) is a useful statistical tool to detect latent information with sparse structures. However, sparse CCA works only for two datasets, i.e., there are only two views or two distinct objects. To overcome this limitation, in this paper, we propose a sparse generalized canonical correlation analysis (GCCA), which could detect the latent relations of multiview data with sparse structures. Moreover, the introduced sparsity could be considered as Laplace prior on the canonical variates. Specifically, we convert the GCCA into a linear system of equations and impose 1 minimization penalty for sparsity pursuit. This results in a nonconvex problem on Stiefel manifold, which is difficult to solve. Motivated by Boyd’s consensus problem, an algorithm based on distributed alternating iteration approach is developed and theoretical consistency analysis is investigated elaborately under mild conditions. Experiments on several synthetic and real world datasets demonstrate the effectiveness of the proposed algorithm. Copyright © 2020, The Authors. All rights reserved.

关键词： Statistical mechanics