检索结果-内蒙古大学图书馆

sparse coding based dense feature representation model for hyperspectral image classification

JOURNAL OF ELECTRONIC IMAGING 2015年第6期24卷

作者： Oguslu, Ender Zhou, Guoqing Zheng, Zezhong Iftekharuddin, Khan Li, Jiang Old Dominion Univ Batten Coll Engn & Technol Dept Elect & Comp Engn Norfolk VA 23529 USA Turkish Air Force NCO Vocat Coll Dept Elect TR-35410 Izmir Turkey Guilin Univ Technol Guangxi Key Lab Spatial Informat & Geomat Engn Guilin 541004 Guangxi Peoples R China Univ Elect Sci & Technol China Sch Resources & Environm Chengdu 610054 Peoples R China

We present a sparse coding based dense feature representation model (a preliminary version of the paper was presented at the SPIE Remote Sensing Conference, Dresden, Germany, 2013) for hyperspectral image (HSI) classification. The proposed method learns a new representation for each pixel in HSI through the following four steps: sub-band construction, dictionary learning, encoding, and feature selection. The new representation usually has a very high dimensionality requiring a large amount of computational resources. We applied the I-1/I-q regularized multiclass logistic regression technique to reduce the size of the new representation. We integrated the method with a linear support vector machine (SVM) and a composite kernels SVM (CKSVM) to discriminate different types of land cover. We evaluated the proposed algorithm on three well-known HSI datasets and compared our method to four recently developed classification methods: SVM, CKSVM, simultaneous orthogonal matching pursuit, and image fusion and recursive filtering. Experimental results show that the proposed method can achieve better overall and average classification accuracies with a much more compact representation leading to more efficient sparse models for HSI classification. (C) 2015 SPIE and IS&T

关键词： sparse coding feature extraction remote sensing hyperspectral imagery hyperspectral classification

来源：评论

学校读者我要写书评

暂无评论

sparse coding predicts optic flow specificities of zebrafish pretectal neurons

引用

NEURAL COMPUTING & APPLICATIONS 2020年第11期32卷 6745-6754页

作者： Ecke, Gerrit A. Bruijns, Sebastian A. Hoelscher, Johannes Mikulasch, Fabian A. Witschel, Thede Arrenberg, Aristides B. Malloy, Hanspeter A. Univ Tubingen Dept Biol Tubingen Germany

Zebrafish pretectal neurons exhibit specificities for large-field optic flow patterns associated with rotatory or translatory body motion. We investigate the hypothesis that these specificities reflect the input statistics of natural optic flow. Realistic motion sequences were generated using computer graphics simulating self-motion in an underwater scene. Local retinal motion was estimated with a motion detector and encoded in four populations of directionally tuned retinal ganglion cells, represented as two signed input variables. This activity was then used as input into one of three learning networks: a sparse coding network (competitive learning), PCA whitening with subsequent sparse coding, and a backpropagation network (supervised learning). All simulations developed specificities for optic flow which are comparable to those found in a neurophysiological study (Kubo et al. in Neuron 81(6):1344-1359, 2016. 10.1016/***.2014.02.043), but relative frequencies of the various neuronal responses were best modeled by the sparse coding approach without whitening. We conclude that the optic flow neurons in the zebrafish pretectum do reflect the optic flow statistics. The predicted vectorial receptive fields show not only typical optic flow fields but also "Gabor" and dipole-shaped patterns that likely reflect difference fields needed for reconstruction by linear superposition.

关键词： Optic flow sparse coding Optimality pretectum Egomotion detection

来源：评论

学校读者我要写书评

暂无评论

sparse coding Guided Spatiotemporal Feature Learning for Abnormal Event Detection in Large Videos

引用

IEEE TRANSACTIONS ON MULTIMEDIA 2019年第1期21卷 246-255页

作者： Chu, Wenqing Xue, Hongyang Yao, Chengwei Cai, Deng Zhejiang Univ State Key Lab CAD&CG Coll Comp Sci & Technol Hangzhou 310027 Peoples R China Zhejiang Univ Coll Comp Sci & Technol Hangzhou 310027 Peoples R China

Abnormal event detection in large videos is an important task in research and industrial applications, which has attracted considerable attention in recent years. Existing methods usually solve this problem by extracting local features and then learning an outlier detection model on training videos. However, most previous approaches merely employ hand-crafted visual features, which is a clear disadvantage due to their limited representation capacity. In this paper, we present a novel unsupervised deep feature learning algorithm for the abnormal event detection problem. To exploit the spatiotemporal information of the inputs, we utilize the deep three-dimensional convolutional network (C3D) to perform feature extraction. Then, the key problem is how to train the C3D network without any category labels. Here, we employ the sparse coding results of the hand-crafted features generated from the inputs to guide the unsupervised feature learning. Specifically, we define a multilevel similarity relationship between these inputs according to the statistical information of the shared atoms. In the following, we introduce the quadruplet concept to model the multilevel similarity structure, which could be used to construct a generalized triplet loss for training the C3D network. Furthermore, the C3D network could be utilized to generate the features for sparse coding again, and this pipeline could be iterated for several times. By jointly optimizing between the sparse coding and the unsupervised feature learning, we can obtain robust and rich feature representations. Based on the learned representations, the sparse reconstruction error is applied to predicting the anomaly score of each testing input. Experiments on several publicly available video surveillance datasets in comparison with a number of existing works demonstrate that the proposed algorithm performs favorably against the state-of-the-art methods.

关键词： Video analysis unsupervised feature learning sparse coding anomaly detection

来源：评论

学校读者我要写书评

暂无评论

sparse coding with Anomaly Detection

引用

JOURNAL OF SIGNAL PROCESSING SYSTEMS FOR SIGNAL IMAGE AND VIDEO TECHNOLOGY 2015年第2期79卷 179-188页

作者： Adler, Amir Elad, Michael Hel-Or, Yacov Rivlin, Ehud Technion Israel Inst Technol Dept Comp Sci IL-32000 Haifa Israel Interdisciplinary Ctr Dept Comp Sci Herzliyya Israel

We consider the problem of simultaneous sparse coding and anomaly detection in a collection of data vectors. The majority of the data vectors are assumed to conform with a sparse representation model, whereas the anomaly is caused by an unknown subset of the data vectors-the outliers-which significantly deviate from this model. The proposed approach utilizes the Alternating Direction Method of Multipliers (ADMM) to recover simultaneously the sparse representations and the outliers components for the entire collection. This approach provides a unified solution both for jointly sparse and independently sparse data vectors. We demonstrate the usefulness of the proposed approach for irregular heartbeats detection in Electrocardiogram (ECG) as well as for specular reflectance and shadows removal from natural images.

关键词： sparse coding Anomaly detection ADMM Arrythmia detection Specular reflectance removal Shadows removal

来源：评论

学校读者我要写书评

暂无评论

sparse coding with a somato-dendritic rule

引用

NEURAL NETWORKS 2020年 131卷 37-49页

作者： Drix, Damien Hafner, Verena V. Schmuker, Michael Univ Hertfordshire Dept Comp Sci Biocomputat Grp Hatfield Herts England Humboldt Univ Inst Informat Adapt Syst Lab Berlin Germany Bernstein Ctr Computat Neurosci Berlin Germany

Cortical neurons are silent most of the time: sparse activity enables low-energy computation in the brain, and promises to do the same in neuromorphic hardware. Beyond power efficiency, sparse codes have favourable properties for associative learning, as they can store more information than local codes but are easier to read out than dense codes. Auto-encoders with a sparse constraint can learn sparse codes, and so can single-layer networks that combine recurrent inhibition with unsupervised Hebbian learning. But the latter usually require fast homeostatic plasticity, which could lead to catastrophic forgetting in embodied agents that learn continuously. Here we set out to explore whether plasticity at recurrent inhibitory synapses could take up that role instead, regulating both the population sparseness and the firing rates of individual neurons. We put the idea to the test in a network that employs compartmentalised inputs to solve the task: rate-based dendritic compartments integrate the feedforward input, while spiking integrate-and-fire somas compete through recurrent inhibition. A somato-dendritic learning rule allows somatic inhibition to modulate nonlinear Hebbian learning in the dendrites. Trained on MNIST digits and natural images, the network discovers independent components that form a sparse encoding of the input and support linear decoding. These findings confirm that intrinsic homeostatic plasticity is not strictly required for regulating sparseness: inhibitory synaptic plasticity can have the same effect. Our work illustrates the usefulness of compartmentalised inputs, and makes the case for moving beyond point neuron models in artificial spiking neural networks. (C) 2020 The Authors. Published by Elsevier Ltd.

关键词： sparse coding Neural Plasticity Hebbian Learning Dendrites Inhibitory plasticity Spiking Neurons

来源：评论

学校读者我要写书评

暂无评论

sparse coding for N-Gram Feature Extraction and Training for File Fragment Classification

引用

IEEE TRANSACTIONS ON INFORMATION FORENSICS AND SECURITY 2018年第10期13卷 2553-2562页

作者： Wang, Felix Quach, Tu-Thach Wheeler, Jason Aimone, James B. James, Conrad D. Sandia Natl Labs Albuquerque NM 87123 USA

File fragment classification is an important step in the task of file carving in digital forensics. In file carving, files must be reconstructed based on their content as a result of their fragmented storage on disk or in memory. Existing methods for classification of file fragments typically use hand -engineered features, such as byte histograms or entropy measures. In this paper, we propose an approach using sparse coding that enables automated feature extraction. sparse coding, or sparse dictionary learning, is an unsupervised learning algorithm, and is capable of extracting features based simply on how well those features can be used to reconstruct the original data. With respect to file fragments, we learn sparse dictionaries for n-grams, continuous sequences of bytes, of different sizes. These dictionaries may then be used to estimate n-gram frequencies for a given file fragment, but for significantly larger n-gram sizes than are typically found in existing methods which suffer from combinatorial explosion. To demonstrate the capability of our sparse coding approach, we used the resulting features to train standard classifiers, such as support vector machines over multiple file types. Experimentally, we achieved significantly better classification results with respect to existing methods, especially when the features were used in supplement to existing hand-engineered features.

关键词： File fragment classification file carving automated feature extraction sparse coding dictionary learning unsupervised learning n-gram support vector machine

来源：评论

学校读者我要写书评

暂无评论

sparse coding based visual tracking: Review and experimental comparison

引用

PATTERN RECOGNITION 2013年第7期46卷 1772-1788页

作者： Zhang, Shengping Yao, Hongxun Sun, Xin Lu, Xiusheng Harbin Inst Technol Sch Comp Sci & Technol Weihai Peoples R China Harbin Inst Technol Sch Comp Sci & Technol Harbin Peoples R China Harbin Inst Technol Sch Comp Sci & Technol Harbin 150006 Peoples R China

Recently, sparse coding has been successfully applied in visual tracking. The goal of this paper is to review the state-of-the-art tracking methods based on sparse coding. We first analyze the benefits of using sparse coding in visual tracking and then categorize these methods into appearance modeling based on sparse coding (AMSC) and target searching based on sparse representation (TSSR) as well as their combination. For each categorization, we introduce the basic framework and subsequent improvements with emphasis on their advantages and disadvantages. Finally, we conduct extensive experiments to compare the representative methods on a total of 20 test sequences. The experimental results indicate that: (1) AMSC methods significantly outperform TSSR methods. (2) For AMSC methods, both discriminative dictionary and spatial order reserved pooling operators are important for achieving high tracking accuracy. (3) For TSSR methods, the widely used identity pixel basis will degrade the performance when the target or candidate images are not aligned well or severe occlusion occurs. (4) For TSSR methods, l(1) norm minimization is not necessary. In contrast, l(2) norm minimization can obtain comparable performance but with lower computational cost. The open questions and future research topics are also discussed. (C) 2012 Elsevier Ltd. All rights reserved.

关键词： Visual tracking Appearance modeling sparse coding sparse representation Dictionary learning

来源：评论

学校读者我要写书评

暂无评论

sparse coding of hyperspectral imagery using online learning

引用

SIGNAL IMAGE AND VIDEO PROCESSING 2015年第4期9卷 959-966页

作者： Ulku, Irem Toreyin, Behcet Ugur Cankaya Univ Dept Elect & Elect Engn TR-06790 Ankara Turkey Sci & Technol Res Council Turkey TUBITAK Space Technol Inst UZAY TR-06800 Ankara Turkey

sparse coding ensures to express the data in terms of a few nonzero dictionary elements. Since the data size is large for hyperspectral imagery, it is reasonable to use sparse coding for compression of hyperspectral images. In this paper, a hyperspectral image compression method is proposed using a discriminative online learning-based sparse coding algorithm. Compression and anomaly detection tests are performed on hyperspectral images from the AVIRIS dataset. Comparative rate-distortion analyses indicate that the proposed method is superior to the state-of-the-art hyperspectral compression techniques.

关键词： sparse coding Hyperspectral imagery Anomaly detection Online learning

来源：评论

学校读者我要写书评

暂无评论

sparse coding for layered neural networks

引用

PHYSICA A-STATISTICAL MECHANICS AND ITS APPLICATIONS 2002年第3-4期310卷 532-546页

作者： Katayama, K Sakata, Y Horiguchi, T Tohoku Univ Dept Math & Comp Sci GSIS Sendai Miyagi 9808579 Japan

We investigate storage capacity of two types of fully connected layered neural networks with sparse coding when binary patterns are embedded into the networks by a Hebbian learning rule. One of them is a layered network. in which a transfer function of even layers is different from that of odd layers. The other is a layered network with intra-layer connections, in which the transfer function of inter-layer is different from that of intra-layer, and inter-layered neurons and intra-layered neurons are updated alternately, We derive recursion relations Cor order parameters by means of the signal-to-noise ratio method, and then apply the self-control threshold method proposed by Dominguez and Bolle to both layered networks with monotonic transfer functions. We find that a critical value alpha(C), of storage capacity is about 0. 11\a In a\ (a much less than 1 ) Cor both layered networks, where a is a neuronal activity. It turns out that the basin of attraction is larger for both layered networks when the self-control threshold method is applied. (C) 2002 Elsevier Science B.V. All rights reserved.

关键词： layered neural network sparse coding Hebb rule storage capacity basin of attraction self-control threshold method signal-to-noise ratio method

来源：评论

学校读者我要写书评

暂无评论

sparse coding based multi-option semantic composition

引用

OPTIK 2019年第0期182卷 793-801页

作者： Bi, Xiaohan Wu, Hao Xu, Huating Bie, Rongfang Guo, Junqi Beijing Jiaotong Univ Sch Comp & Informat Technol Beijing Peoples R China Beijing Normal Univ Coll Informat Sci & Technol Beijing Peoples R China

As a classic technique in the field of computer vision, image composition has been widely used and recognized. It could composite new regions extracted from candidate images into target images, which could achieve realistic composited results. However, in the process of composition, it is difficult for traditional composition methods to select enough semantically valid candidate images. Moreover, imperfect composition techniques apparently reduce the effectiveness of composition. Aiming at these problems, we proposed a sparse coding based candidate image selection model that could offer more semantically valid candidate images. At the same time, optimized composition techniques were also used for improving the composition quality. Finally, compared with traditional models, adequate experimental results using a large number of images indicate that our model not only could retrieve more effective candidate images but also could achieve consistent composition results.

关键词： sparse coding Candidate image Weight based KNN Multi-scale feature handling AP value AUC value

来源：评论

学校读者我要写书评

暂无评论

建议与咨询留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

时间限定

文献类型

馆藏选择

核心期刊

语言

文献类型

帮助

文字说明：

检索规则说明：

检索范例：

分类表

所选分类

限定检索结果

文献类型

馆藏范围

日期分布

学科分类号

主题

机构

作者

语言

请选择保存的检索档案：

请选择收藏分类：

通借通还

建议与咨询 留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

时间限定

文献类型

馆藏选择

核心期刊

语言

文献类型

帮助

文字说明：

检索规则说明：

检索范例：

分类表

所选分类

限定检索结果

文献类型

馆藏范围

日期分布

学科分类号

主题

机构

作者

语言

请选择保存的检索档案： 新增检索档案 确定 取消

请选择收藏分类： 新增自定义分类 确定 取消

通借通还

建议与咨询留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

请选择保存的检索档案：

请选择收藏分类：