检索结果-内蒙古大学图书馆

Effective and Efficient Midlevel Visual Elements-Oriented Land-Use Classification Using VHR Remote Sensing Images

IEEE TRANSACTIONS ON GEOSCIENCE AND REMOTE SENSING 2015年第8期53卷 4238-4249页

作者： Cheng, Gong Han, Junwei Guo, Lei Liu, Zhenbao Bu, Shuhui Ren, Jinchang Northwestern Polytech Univ Sch Automat Xian 710072 Peoples R China Northwestern Polytech Univ Sch Aeronaut Xian 710072 Peoples R China Univ Strathclyde Fac Engn Dept Elect & Elect Engn Glasgow G1 1XW Lanark Scotland

Land-use classification using remote sensing images covers a wide range of applications. With more detailed spatial and textural information provided in very high resolution (VHR) remote sensing images, a greater range of objects and spatial patterns can be observed than ever before. This offers us a new opportunity for advancing the performance of land-use classification. In this paper, we first introduce an effective midlevel visual elements-oriented land-use classification method based on "partlets," which are a library of pretrained part detectors used for midlevel visual elements discovery. Taking advantage of midlevel visual elements rather than low-level image features, a partlets-based method represents images by computing their responses to a large number of part detectors. As the number of part detectors grows, a main obstacle to the broader application of this method is its computational cost. To address this problem, we next propose a novel framework to train coarse-to-fine shared intermediate representations, which are termed "sparselets," from a large number of pretrained part detectors. This is achieved by building a single-hidden-layer autoencoder and a single-hidden-layer neural network with an L0-norm sparsity constraint, respectively. Comprehensive evaluations on a publicly available 21-class VHR land-use data set and comparisons with state-of-the-art approaches demonstrate the effectiveness and superiority of this paper.

关键词： autoencoder land-use classification midlevel visual elements part detectors remote sensing images

来源：评论

学校读者我要写书评

暂无评论

A Map-reduce Method for Training autoencoders on Xeon Phi

A Map-reduce Method for Training Autoencoders on Xeon Phi

引用

IEEE International Conference on Ubiquitous Computing and Communications

作者： Qiongjie Yao Xiaofei Liao Hai Jin Services Computing Technology and System Lab Cluster and Grid Computing Lab School of Computer Science and Technology Huazhong University of Science and Technology Wuhan 430074 China

ISBN: (纸本)9781509001552

The stacked autoencoder is a deep learning model that consists of multiple autoencoders. This model has been widely applied in numerous machine learning applications. A significant amount of effort has been made to increase the size of the deep learning model with respect to the size of the training dataset and the parameter of the model to improve performance. However, training a large deep learning model is highly time consuming. Recent studies have applied the CPU cluster with thousands of machines as well as the single GPU or the GPU cluster, to train large scale deep learning models. As a high-performance coprocessor like GPU, the Xeon Phi can be an alternative tool for training large scale deep learning models on a single machine. The Xeon Phi can be recognized as a small cluster which features about 60 cores, and each core supports four hardware threads. Massive parallelism offsets the low computing capacity of every core, but challenges an efficient parallel autoencoders design. In this paper, we analyze the training algorithm of autoencoders based on the matrix operation and point out the thread oversubscription problem, which results in performance degradation. Based on the observation, we propose our map-reduce implementation of autoencoders on the Xeon Phi coprocessor. Our basic idea is to parallelize multiple autoencoder model replicas with bulk synchronous parallel (BSP) communication model where the parameters are updated after the computations of all replicas are completed. Each thread is responsible for one model replica, and all replicas work together on the same mini-batch. This data parallelism method is suitable for training autoencoders on the Xeon Phi, and can extend to asynchronous parallel training method without thread oversubscription. In our experiment the speedup is four times higher than that of sequential implementation. Enlarging the size of the autoencoder model, our method still gets stable speedup.

关键词： Deep Learning autoencoder Xeon Phi Mapreduce BSP

来源：评论

学校读者我要写书评

暂无评论

A Continuous Learning Framework for Activity Recognition Using Deep Hybrid Feature Models

引用

IEEE TRANSACTIONS ON MULTIMEDIA 2015年第11期17卷 1909-1922页

作者： Hasan, Mahmudul Roy-Chowdhury, Amit K. Univ Calif Riverside Dept Comp Sci & Engn Riverside CA 92521 USA Univ Calif Riverside Dept Elect & Comp Engn Riverside CA 92521 USA

Most of the research on human activity recognition has focused on learning a static model, considering that all the training instances are labeled and present in advance, while in streaming videos new instances continuously arrive and are not labeled. Moreover, these methods generally use application-specific hand-engineered and static feature models, which are not suitable for continuous learning. Some recent approaches on activity recognition use deep-learning-based hierarchical feature models, but the large size of these networks constrain them from being used in continuous learning scenarios. In this work, we propose a continuous activity learning framework for streaming videos by intricately tying together deep hybrid feature models and active learning. This allows us to automatically select the most suitable features and take the advantage of incoming unlabeled instances to improve the existing model incrementally. Given the segmented activities from streaming videos, we learn features in an unsupervised manner using deep hybrid networks, which have the ability to take the advantage of both the local hand-engineered features and the deep model in an efficient way. Additionally, we use active learning to train the activity classifier using a reduced amount of manually labeled instances. Retraining the models with a huge amount of accumulated examples is computationally expensive and not suitable for continuous learning. Hence, we propose a method to select the best subset of these examples to update the models incrementally. We conduct rigorous experiments on four challenging human activity datasets to demonstrate the effectiveness of our framework.

关键词： Active learning activity recognition autoencoder hybrid feature model incremental learning

来源：评论

学校读者我要写书评

暂无评论

Saliency-Guided Unsupervised Feature Learning for Scene Classification

引用

IEEE TRANSACTIONS ON GEOSCIENCE AND REMOTE SENSING 2015年第4期53卷 2175-2184页

作者： Zhang, Fan Du, Bo Zhang, Liangpei Wuhan Univ State Key Lab Informat Engn Surveying Mapping & R Wuhan 430079 Peoples R China Wuhan Univ Sch Comp Sci Wuhan 430072 Peoples R China

Due to the rapid technological development of various different satellite sensors, a huge volume of high-resolution image data sets can now be acquired. How to efficiently represent and recognize the scenes from such high-resolution image data has become a critical task. In this paper, we propose an unsupervised feature learning framework for scene classification. By using the saliency detection algorithm, we extract a representative set of patches from the salient regions in the image data set. These unlabeled data patches are exploited by an unsupervised feature learning method to learn a set of feature extractors which are robust and efficient and do not need elaborately designed descriptors such as the scale-invariant-feature-transform-based algorithm. We show that the statistics generated from the learned feature extractors can characterize a complex scene very well and can produce excellent classification accuracy. In order to reduce overfitting in the feature learning step, we further employ a recently developed regularization method called "dropout," which has proved to be very effective in image classification. In the experiments, the proposed method was applied to two challenging high-resolution data sets: the UC Merced data set containing 21 different aerial scene categories with a submeter resolution and the Sydney data set containing seven land-use categories with a 60-cm spatial resolution. The proposed method obtained results that were equal to or even better than the previous best results with the UC Merced data set, and it also obtained the highest accuracy with the Sydney data set, demonstrating that the proposed unsupervised-feature-learning-based scene classification method provides more accurate classification results than the other latent-Dirichlet-allocation-based methods and the sparse coding method.

关键词： autoencoder saliency detection scene classification unsupervised feature learning

来源：评论

学校读者我要写书评

暂无评论

Online Marginalized Linear Stacked Denoising autoencoders for Learning from Big Data Stream

Online Marginalized Linear Stacked Denoising Autoencoders fo...

引用

International Conference on Advanced Computer Science and Information Systems

作者： Arif Budiman Mohamad Ivan Fanany Chan Basaruddin Faculty of Computer Science University of Indonesia Depok West Java Indonesia

ISBN: (纸本)9781509003648

Big non-stationary data, which comes in gradual fashion or stream, is one important issue in the application of big data to train deep learning machines. In this paper, we focused on a unique variant of traditional autoencoder, which is called Marginalized Linear Stacked Denoising autoencoder (MLSDA). MLSDA uses a simple linear model. It is faster and uses less number of parameters than the traditional SDA. It also takes advantages of convex optimization. It has better improvement in the bag of words feature representation. However, the traditional SDA with stochastic gradient descent has been more widely accepted in many applications. The stochastic gradient descent is naturally an online learning. It makes the traditional SDA more scalable for streaming big data. This paper proposes a simple modification of MLSDA. Our modification uses matrix multiplication concept for online learning. The experiment result showed the similar accuracy level compared with a batch version of MLSDA and using lower computation resources. The online MLSDA will improve the scalability of MLSDA for handling streaming big data that representing bag of words features for natural language processing, information retrieval, and computer vision.

关键词： autoencoder big data deep learning denoising online sequential

来源：评论

学校读者我要写书评

暂无评论

FACE IDENTIFICATION FROM LOW RESOLUTION NEAR-INFRARED IMAGES

FACE IDENTIFICATION FROM LOW RESOLUTION NEAR-INFRARED IMAGES

引用

IEEE International Conference on Image Processing

作者： Soumyadeep Ghosh Rohit Keshari Richa Singh Mayank Vatsa IIIT Delhi

ISBN: (纸本)9781467399623

Face identification from low quality and low resolution Near-Infrared (NIR) face images is a challenging problem. Since surveillance cameras typically acquire images at a large standoff distance, the effective resolution of the face is not large enough to identify the individuals. Moreover for a 24-hour surveillance footage, images in low light and at nighttime are acquired in NIR mode which makes the identification problem even more challenging. We propose an effective method using both hand-crafted and learned features for face identification of low resolution NIR images. We show that learned features contribute considerably to the performance of identification algorithm, and that using both feature level and score level fusion in a hierarchal approach gives good performance. The results demonstrate the effectiveness of the proposed approach on images which are of low quality, low resolution and acquired under challenging illumination conditions in near-infrared mode by surveillance cameras.

关键词： Low resolution face recognition Near Infrared autoencoder Restricted Boltzmann Machine near infrared images Detective cameras Facial Recognition Resolving power low light Nighttime

来源：评论

学校读者我要写书评

暂无评论

A Hybrid Malicious Code Detection Method based on Deep Learning

引用

INTERNATIONAL JOURNAL OF SECURITY AND ITS APPLICATIONS 2015年第5期9卷 205-215页

作者： Li, Yuancheng Ma, Rong Jiao, Runhai North China Elect Power Univ Sch Control & Comp Engn Beijing Peoples R China

In this paper;we propose a hybrid malicious code detection scheme based on autoencoder and DBN (Deep Belief Networks). Firstly, we use the autoencoder deep learning method to reduce the dimensionality of data. This could convert complicated high-dimensional data into low dimensional codes with the nonlinear mapping, thereby reducing the dimensionality of data, extracting the main features of the data;then using DBN learning method to detect malicious code. DBN is composed of multilayer Restricted Boltzmann Machines (RBM, Restricted Boltzmann Machine) and a layer of BP neural network. Based on unsupervised training of every layer of RBM, we make the output vector of the last layer of RBM as the input vectors of BP neural network, then conduct supervised training to the BP neural network, finally achieve the optimal hybrid model by fine-tuning the entire network. After inputting testing samples into the hybrid model, the experimental results show that the detection accuracy getting by the hybrid detection method proposed in this paper is higher than that of single DBN. The proposed method reduces the time complexity and has better detection performance.

关键词： Malicious code Detection autoencoder DBN RBM deep learning

来源：评论

学校读者我要写书评

暂无评论

Nonparametric guidance of autoencoder representations using label information

The Journal of Machine Learning Research

引用

The Journal of Machine Learning Research 2012年第1期13卷

作者： Jasper Snoek Ryan P. Adams Hugo Larochelle Department of Computer Science University of Toronto Toronto ON Canada School of Engineering and Applied Sciences Harvard University Cambridge MA Department of Computer Science University of Sherbrooke Sherbrooke QC Canada

While unsupervised learning has long been useful for density modeling, exploratory data analysis and visualization, it has become increasingly important for discovering features that will later be used for discriminative tasks. Discriminative algorithms often work best with highly-informative features; remarkably, such features can often be learned without the labels. One particularly effective way to perform such unsupervised learning has been to use autoencoder neural networks, which find latent representations that are constrained but nevertheless informative for reconstruction. However, pure unsupervised learning with autoencoders can find representations that may or may not be useful for the ultimate discriminative task. It is a continuing challenge to guide the training of an autoencoder so that it finds features which will be useful for predicting labels. Similarly, we often have a priori information regarding what statistical variation will be irrelevant to the ultimate discriminative task, and we would like to be able to use this for guidance as well. Although a typical strategy would be to include a parametric discriminative model as part of the autoencoder training, here we propose a nonparametric approach that uses a Gaussian process to guide the representation. By using a nonparametric model, we can ensure that a useful discriminative function exists for a given set of features, without explicitly instantiating it. We demonstrate the superiority of this guidance mechanism on four data sets, including a real-world application to rehabilitation research. We also show how our proposed approach can learn to explicitly ignore statistically significant covariate information that is label-irrelevant, by evaluating on the small NORB image recognition problem in which pose and lighting labels are available.

关键词： autoencoder gaussian process gaussian process latent variable model representation learning unsupervised learning

来源：评论

学校读者我要写书评

暂无评论

STOCHASTIC GRADIENT VARIATIONAL BAYES FOR DEEP LEARNING-BASED ASR

STOCHASTIC GRADIENT VARIATIONAL BAYES FOR DEEP LEARNING-BASE...

引用

IEEE Workshop on Automatic Speech Recognition and Understanding (ASRU)

作者： Tjandra, Andros Sakti, Sakriani Nakamura, Satoshi Adriani, Mirna Univ Indonesia Fac Comp Sci Java Indonesia Nara Inst Sci & Technol Grad Sch Informat Sci Ikoma Nara Japan

ISBN: (纸本)9781479972913

Many successful methods for training deep neural networks (DNN) rely on an unsupervised pretraining algorithm. It is particularly effective when the number of labeled training samples is not large enough, because pretraining method helps to initialize the parameter values in the appropriate range near a local good minimum, for further discriminative finetuning. However, while the improvement is impressive, training DNN is difficult because the objective function of DNN is highly non-convex function of the parameters. To avoid placing the parameter that generalizes poorly, a robust generative modelling is necessary. This paper explore an alternative of generative modelling for pretraining DNN-based acoustic modelling using Stochastic Gradient Variational Bayes (SGVB) within autoencoder framework called Variational Bayes autoencoder (VBAE). It performs an efficient approximate inference and learning with directed probabilistic graphical models. During fine-tuning, probabilistic encoder parameters with latent variable components are then used in discriminative training for acoustic model. Here, we investigate the performances of DNN-based acoustic model using the proposed pretrained VBAE in comparison with widely used pretraining algorithms like Restricted Boltzmann Machine (RBM) and Stacked Denoising autoencoder (SDAE). The results reveal that VBAE pretraining with Gaussian latent variables gave the best performance.

关键词： acoustic model deep neural network variational bayes autoencoder

来源：评论

学校读者我要写书评

暂无评论

Memristor Crossbar Based Unsupervised Training

Memristor Crossbar Based Unsupervised Training

引用

IEEE National Aerospace and Electronics Conference (NAECON)

作者： Hasan, Raqibul Taha, Tarek M. Univ Dayton Dept Elect & Comp Engn Dayton OH 45469 USA

ISBN: (纸本)9781467375658

Several big data applications are particularly focused on classification and clustering tasks. Robustness of such system depends on how well it can extract important features from the raw data. For big data processing we are interested for a generic feature extraction mechanism for different applications. autoencoder is a popular unsupervised training algorithm for dimensionality reduction and feature extraction. In this work we have examined memiistor crossbar based implementation of autoencoder which will consume very low power. We have designed on-chip training circuitry for the unsupervised training scheme.

关键词： Low power architecture memristor crossbars autoencoder training algorithm feature extraction

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：