检索结果-内蒙古大学图书馆

IEEE International Conference on Systems, Man, and Cybernetics

作者： Houtan Rahmanian Manfred Huber Dept. of Computer Science and Engineering University of Texas at Arlington Arlington TX USA

ISBN: (纸本)9781479906505

sparse coding is a very powerful method to learn high-level features from raw data input. It is able to learn an overcomplete basis that has the potential to capture robust and discriminative patterns within the data. However, like many other feature learning algorithms, it is unable to detect very similar features or stimuli on different input channels. In this paper, we propose a novel method to build general features that can be applicable to different sets of channels. This succinct representational model will express the stimuli independent of the locality in which they appeared. As a result, it prepares the groundwork for transferring the learned features from a set of input channels to other possible sets of input channels.

关键词： sparse coding Algorithm Generalized Features Channel-Remapping Data modelling sparse coding Stimuli High-level features Channels channels data entry ENTERING SETTING learning algorithms

来源：评论

学校读者我要写书评

暂无评论

EFFICIENT LARGE-SCALE SERVICE CLUSTERING VIA sparse FUNCTIONAL REPRESENTATION AND ACCELERATED OPTIMIZATION

引用

INTERNATIONAL JOURNAL OF COOPERATIVE INFORMATION SYSTEMS 2013年第4期22卷 1341001-1341001页

作者： Yu, Qi Rochester Inst Technol Coll Comp & Informat Sci Rochester NY 14623 USA

Clustering techniques offer a systematic approach to organize the diverse and fast increasing Web services by assigning relevant services into homogeneous service communities. However, the ever increasing number of Web services poses key challenges for building large-scale service communities. In this paper, we tackle the scalability issue in service clustering, aiming to accurately and efficiently discover service communities over very large-scale services. A key observation is that service descriptions are usually represented by long but very sparse term vectors as each service is only described by a limited number of terms. This inspires us to seek a new service representation that is economical to store, efficient to process, and intuitive to interpret. This new representation enables service clustering to scale to massive number of services. More specifically, a set of anchor services are identified that allows each service to represent as a linear combination of a small number of anchor services. In this way, the large number of services are encoded with a much more compact anchor service space. Despite service clustering can be performed much more efficiently in the compact anchor service space, discovery of anchor services from large-scale service descriptions may incur high computational cost. We develop principled optimization strategies for efficient anchor service discovery. Extensive experiments are conducted on real-world service data to assess both the effectiveness and efficiency of the proposed approach. Results on a dataset with over 3,700 Web services clearly demonstrate the good scalability of sparse functional representation and the efficiency of the optimization algorithms for anchor service discovery.

关键词： Service clustering sparse coding anchor service accelerated gradient algorithm

来源：评论

学校读者我要写书评

暂无评论

Learning Convolutional Neural Networks From Few Samples

Learning Convolutional Neural Networks From Few Samples

引用

International Joint Conference on Neural Networks

作者： Raimar Wagner Markus Thom Roland Schweiger Günther Palm Albrecht Rothermel driveU / Institute of Microelectronics University of Ulm Ulm Germany driveU / Institute of Measurement Control and Microtechnology University of Ulm Ulm Germany Daimler AG Ulm Germany Institute of Neural Information Processing University of Ulm Ulm Germany

ISBN: (纸本)9781467361279

Learning Convolutional Neural Networks (CNN) is commonly carried out by plain supervised gradient descent. With sufficient training data, this leads to very competitive results for visual recognition tasks when starting from a random initialization. When the amount of labeled data is limited, CNNs reveal their strong dependence on large amounts of training data. However, recent results have shown that a well chosen optimization starting point can be beneficial for convergence to a good generalizing minimum. This starting point was mostly found using unsupervised feature learning techniques such as sparse coding or transfer learning from related recognition tasks. In this work, we compare these two approaches against a simple patch based initialization scheme and a random initialization of the weights. We show that pre-training helps to train CNNs from few samples and that the correct choice of the initialization scheme can push the network's performance by up to 41% compared to random initialization.

关键词： CNN training data random initialization initialization Training data Neural network Transfer (Psychology) sparse coding

来源：评论

学校读者我要写书评

暂无评论

CLASSIFICATION OF TUMOR HISTOPATHOLOGY VIA sparse FEATURE LEARNING

CLASSIFICATION OF TUMOR HISTOPATHOLOGY VIA SPARSE FEATURE LE...

引用

IEEE International Symposium on Biomedical Imaging

作者： Nandita Nayak Hang Chang Alexander Borowsky Paul Spellman Bahram Parvin Life Sciences Division Lawrence Berkeley National Laboratory Center for Comparative Medicine University of California Center for Spatial Systems Biomedicine Oregon Health Sciences University

ISBN: (纸本)9781467364560

Our goal is to decompose whole slide images (WSI) of histology sections into distinct patches (e.g., viable tumor, necrosis) so that statistics of distinct histopathology can be linked with the outcome. Such an analysis requires a large cohort of histology sections that may originate from different laboratories, which may not use the same protocol in sample preparation. We have evaluated a method based on a variation of the restricted Boltzmann machine (RBM) that learns intrinsic features of the image signature in an unsupervised fashion. Computed code, from the learned representation, is then utilized to classify patches from a curated library of images. The system has been evaluated against a dataset of small image blocks of 1k-by-1k that have been extracted from glioblastoma multiforme (GBM) and clear cell kidney carcinoma (KIRC) from the cancer genome atlas (TCGA) archive. The learned model is then projected on each whole slide image (e.g., of size 20k-by-20k pixels or larger) for characterizing and visualizing tumor architecture. In the case of GBM, each WSI is decomposed into necrotic, transition into necrosis, and viable. In the case of the KIRC, each WSI is decomposed into tumor types, stroma, normal, and others. Evaluation of 1400 and 2500 samples of GBM and KIRC indicates a performance of 84% and 81%, respectively.

关键词： Tumor characterization Whole slide imaging Feature learning sparse coding

来源：评论

学校读者我要写书评

暂无评论

LEARNING OVERCOMPLETE SPARSIFYING TRANSFORMS FOR SIGNAL PROCESSING

LEARNING OVERCOMPLETE SPARSIFYING TRANSFORMS FOR SIGNAL PROC...

引用

IEEE International Conference on Acoustics, Speech and Signal Processing

作者： Saiprasad Ravishankar Yoram Bresler Department of Electrical and Computer Engineering and the Coordinated Science Laboratory University of Illinois Urbana-Champaign IL 61801 USA

ISBN: (纸本)9781479903573

Adaptive sparse representations have been very popular in numerous applications in recent years. The learning of synthesis sparsifying dictionaries has particularly received much attention, and such adaptive dictionaries have been shown to be useful in applications such as image denoising, and magnetic resonance image reconstruction. In this work, we focus on the alternative sparsifying transform model, for which sparse coding is cheap and exact, and study the learning of tall or overcomplete sparsifying transforms from data. We propose various penalties that control the sparsifying ability, condition number, and incoherence of the learnt transforms. Our alternating algorithm for transform learning converges empirically, and significantly improves the quality of the learnt transform over the iterations. We present examples demonstrating the promising performance of adaptive overcomplete transforms over adaptive overcomplete synthesis dictionaries learnt using K-SVD, in the application of image denoising.

关键词： Sparsifying transform learning sparse representations dictionary learning Overcomplete representations signal processing Transform sparse representation Dictionaries as Topic image denoising Learning incoherence Self tuning sparse coding penalty iterative methods

来源：评论

学校读者我要写书评

暂无评论

DUAL-LAYER BAG-OF-FRAMES MODEL FOR MUSIC GENRE CLASSIFICATION

DUAL-LAYER BAG-OF-FRAMES MODEL FOR MUSIC GENRE CLASSIFICATIO...

引用

IEEE International Conference on Acoustics, Speech and Signal Processing

作者： Chin-Chia Michael Yeh Li Su Yi-Hsuan Yang Research Center for Information Technology Innovation Academia Sinica Taiwan

ISBN: (纸本)9781479903573

This paper concerns the development of a music dictionary-based model for summarizing local feature descriptors computed over time. Comparing to a holistic representation, this text-like, bag-of-frames representation better captures the rich and time -varying information of music. However, the dictionary used in classical bag-of-frames model only captures frame-level elements of the music;thus, there exists a semantic gap between the dictionary element and commonly seen music description. In order to reduce the gap, a new feature representation called dual-layer bag-of-frames is proposed in this paper. It models the music with a two layer structure, where the first-layer dictionary captures the frame-level characteristics, and the second-layer dictionary captures the segment-level semantics. This hierarchical structure resembles the alphabet-word-document structure of text. Our result demonstrates that the proposed dual-layer bag-of-frames feature achieves state-of-the-art accuracy of music genre classification. The classification accuracy for the GTZAN benchmark reaches 86.7% with dictionary trained from GTZAN, and 83.6% with dictionary trained from another data set USPOP.

关键词： sparse coding Deep structure Audio alphabets Audio words Music genre classification

来源：评论

学校读者我要写书评

暂无评论

NON-RIGID 3D SHAPE RECOGNITION VIA DICTIONARY LEARNING

NON-RIGID 3D SHAPE RECOGNITION VIA DICTIONARY LEARNING

引用

IEEE International Conference on Acoustics, Speech, and Signal Processing

作者： Yin Zhou Kai Liu Kenneth E. Barner University of Delaware Newark DE USA 19716 School of Electrical Engineering and Information Sichuan University China

ISBN: (纸本)9781479903573

Non-rigid 3D shape recognition is an important and challenging research topic in computer vision and pattern recognition. This paper presents a novel algorithm, called dictionary learning based on supervised locally linear representation (DL-SLLR), for efficient 3D shape recognition using shape descriptors. Specifically, we introduce a novel locality-preservation error term along with a label approximation error term into the objective function. The proposed algorithm optimizes a dictionary for its capability in representation as well as its locality-preservation capability, which thus allows more consistent encoding of similar descriptors compared with sparse coding. In addition, the proposed SLLR coding yields a closed-form solution, compared to many sparse coding algorithms. Experimental results demonstrate that using majority voting, DL-SLLR outperforms D-KSVD and SVM over a newly generated SLI 3D Face Dataset and the SHREC'11 Contest Dataset.

关键词： Shape recognition Point cloud classification Dictionary learning Classification sparse coding

来源：评论

学校读者我要写书评

暂无评论

K-WEB: NONNEGATIVE DICTIONARY LEARNING FOR sparse IMAGE REPRESENTATIONS

K-WEB: NONNEGATIVE DICTIONARY LEARNING FOR SPARSE IMAGE REPR...

引用

IEEE International Conference on Image Processing

作者： Marco Bevilacqua Aline Roumy Christine Guillemot Marie-Line Alberi Morel INRIA Rennes Alcatel-Lucent Bell Labs France

ISBN: (纸本)9781479923427

This paper presents a new nonnegative dictionary learning method, to decompose an input data matrix into a dictionary of nonnegative atoms, and a representation matrix with a strict l~0-sparsity constraint. This constraint makes each input vector representable by a limited combination of atoms. The proposed method consists of two steps which are alternatively iterated: a sparse coding and a dictionary update stage. As for the dictionary update, an original method is proposed, which we call K-WEB, as it involves the computation of k WEighted Barycenters. The so designed algorithm is shown to outperform other methods in the literature that address the same learning problem, in different applications, and both with synthetic and "real" data, i.e. coming from natural images.

关键词： Dictionary learning sparse representations K-SVD NMF NMF protocol Dictionaries as Topic sparse representation images sparse coding Nonnegative representations incoming data Learning

来源：评论

学校读者我要写书评

暂无评论

EDGE PRESERVING SINGLE IMAGE SUPER RESOLUTION IN sparse ENVIRONMENT

EDGE PRESERVING SINGLE IMAGE SUPER RESOLUTION IN SPARSE ENVI...

引用

IEEE International Conference on Image Processing

作者： Srimanta Mandal Anil Kumar Sao School of Computing and Electrical Engineering Indian Institute of Technology Mandi India

ISBN: (纸本)9781479923427

Quality of an image is associated with edge of the image. It is important to preserve the edge of the image while deriving high resolution (HR) image from low resolution (LR) image, also known as super-resolution (SR) problem. This paper proposes an edge preserving constraint, which preserve the edge information of image by minimizing the differences between edges of LR image and the edges of the reconstructed image (down-sampled version), in sparse coding based SR problem. Partial edge evidences, derived using 1-D processing of image, are used separately in the constraints. The experimental results show that proposed approach preserves the edges of image as well as outperforms objectively the existing SR approaches.

关键词： Image Super-resolution sparse coding Dictionary Edge evidence edge image images sparse coding Imagery (Psychotherapy) Dictionaries as Topic edges Preserves Image Resolving power SAVANNAH RIVER OPERATIONS OFFICE Strontium telecommunication standards cellular radio

来源：评论

学校读者我要写书评

暂无评论

Histograms of sparse Codes for Object Detection

Histograms of Sparse Codes for Object Detection

引用

IEEE Conference on Computer Vision and Pattern Recognition

作者： Xiaofeng Ren Deva Ramanan *** University of California

ISBN: (纸本)9781467364102

Object detection has seen huge progress in recent years, much thanks to the heavily-engineered Histograms of Oriented Gradients (HOG) features. Can we go beyond gradients and do better than HOG? We provide an affirmative answer by proposing and investigating a sparse representation for object detection, Histograms of sparse Codes (HSC). We compute sparse codes with dictionaries learned from data using K-SVD, and aggregate per-pixel sparse codes to form local histograms. We intentionally keep true to the sliding window framework (with mixtures and parts) and only change the underlying features. To keep training (and testing) efficient, we apply dimension reduction by computing SVD on learned models, and adopt supervised training where latent positions of roots and parts are given externally e.g. from a HOG-based detector. By learning and using local representations that are much more expressive than gradients, we demonstrate large improvements over the state of the art on the PASCAL benchmark for both root-only and part-based models.

关键词： Object detection histograms Codes Dictionaries as Topic sparse coding Gradient

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：