检索结果-内蒙古大学图书馆

Learned and Designed Features for sparse coding in Image Classification

Learned and Designed Features for Sparse Coding in Image Cla...

IEEE RIVF International Conference on Computing and Communication Technologies, Research, Innovation, and Vision for the Future

作者： Dung A. Doan Ngoc-Trung Tran Dinh-Phong Vo Bac Le University of Science

ISBN: (纸本)9781479913480

There is an amount of designed features (SIFT, SURF, or DAISY) which has been chosen in the standard implementation of some visual recognition and multimedia challenges. The power of these features lie on their invariance designed against rotation, scaling, and translation. Recent trends in deep learning, however, have pointed out that data-driven features learning performs better designed features in some tasks, since they can capture the global (via multi-layers network) or inter-local structures (convolutional network) of images. We argue that combining the two types of features can significantly improve visual object recognition performance. We propose in this paper a framework that uses sparse coding and the fusion of learned and designed features in order to build descriptive codewords. Evaluations on Caltech-101 and 15 Scenes validates our argument, with a better result compared with recent approaches.

关键词： sparse coding Image classification invariance MULTI-MEDIA SYSTEM alpine-type features

来源：评论

学校读者我要写书评

暂无评论

FACE RECOGNITION USING HOG FEATURE AND GROUP sparse coding

FACE RECOGNITION USING HOG FEATURE AND GROUP SPARSE CODING

引用

IEEE International Conference on Image Processing

作者： Yuhua Li Chun Qi The School of Electronic and Information Engineering Xi'an Jiaotong University China

ISBN: (纸本)9781479923427

Standard sparsity concept mainly focuses on the sparsity of coefficient vector while other important characteristics are less considered. For example, given a structured dictionary, some structured patterns are more likely to occur than the others. In this paper, a face recognition method using group sparse coding is presented. Training samples of the same class are gathered to form a sub-dictionary and a group structured dictionary is obtained by concentrating sub-dictionaries of all classes. We decompose each testing sample as a product of the group structured dictionary and a group sparse coefficient vector. Finally, recognition is accomplished by evaluating which class of training samples leads to the minimum reconstruction error. For better invariance to illumination and expression changes, histogram of oriented gradients (Hog) feature is extracted to represent face image. Experimental results on benchmark face databases show the proposed method leads to higher recognition rates and shorter recognition time.

关键词： Standard sparsity face recognition Hog feature group sparse coding Facial Recognition Dictionaries as Topic reconstruction error Face Face recognition techniques Recognition (Psychology) sparse coding illumination Lighting

来源：评论

学校读者我要写书评

暂无评论

Supervised sparse patch coding towards misalignment-robust face recognition

引用

JOURNAL OF VISUAL COMMUNICATION AND IMAGE REPRESENTATION 2013年第2期24卷 103-110页

作者： Lang, Congyan Feng, Songhe Chen, Bin Yuan, Xiaotong Beijing Jiaotong Univ Dept Comp Sci & Engn Beijing Peoples R China Natl Univ Singapore Dept Elect & Comp Engn Singapore 117548 Singapore

We address the challenging problem of face recognition under the scenarios where both training and test data are possibly contaminated with spatial misalignments. A supervised sparse coding framework is developed in this paper towards a practical solution to misalignment-robust face recognition. Each gallery face image is represented as a set of patches, in both original and misaligned positions and scales, and each given probe face image is then uniformly divided into a set of local patches. We propose to sparsely reconstruct each probe image patch from the patches of all gallery images, and at the same time the reconstructions for all patches of the probe image are regularized by one term towards enforcing sparsity on the subjects of those selected patches. The derived reconstruction coefficients by l(1)-norm minimization are then utilized to fuse the subject information of the patches for identifying the probe face. Such a supervised sparse coding framework provides a unique solution to face recognition with all (Here, we emphasize "all" because some conventional algorithms for face recognition possess partial of these characteristics.) the following four characteristics: (1) the solution is model-free, without the model learning process, (2) the solution is robust to spatial misalignments, (3) the solution is robust to image occlusions, and (4) the solution is effective even when there exist spatial misalignments for gallery images. Extensive face recognition experiments on three benchmark face datasets demonstrate the advantages of the proposed framework over holistic sparse coding and conventional subspace learning based algorithms in terms of robustness to spatial misalignments and image occlusions. (C) 2012 Elsevier Inc. All rights reserved.

关键词： Face recognition Spatial misalignment Image occlusions sparse coding Misalignment robust Supervised sparse coding Dual sparsity Collective sparse reconstructions

来源：评论

学校读者我要写书评

暂无评论

The Statistical Structure of the Hippocampal Code for Space as a Function of Time, Context, and Value

引用

CELL 2020年第3期183卷 620-+页

作者： Lee, Jae Sung Briguglio, John J. Cohen, Jeremy D. Romani, Sandro Lee, Albert K. HHMI Janelia Res Campus Ashburn VA 20147 USA

Hippocampal activity represents many behaviorally important variables, including context, an animal's location within a given environmental context, time, and reward. Using longitudinal calcium imaging in mice, multiple large virtual environments, and differing reward contingencies, we derived a unified probabilistic model of CA1 representations centered on a single feature-the field propensity. Each cell's propensity governs how many place fields it has per unit space, predicts its reward-related activity, and is preserved across distinct environments and over months. Propensity is broadly distributed-with many low, and some very high, propensity cells-and thus strongly shapes hippocampal representations. This results in a range of spatial codes, from sparse to dense. Propensity varied similar to 10-fold between adjacent cells in salt-and-pepper fashion, indicating substantial functional differences within a presumed cell type. Intracellular recordings linked propensity to cell excitability. The stability of each cell's propensity across conditions suggests this fundamental property has anatomical, transcriptional, and/or developmental origins.

关键词： hippocampus place cell place field memory calcium imaging propensity gain modulation sparse coding intracellular recording excitability

来源：评论

学校读者我要写书评

暂无评论

Multipath sparse coding Using Hierarchical Matching Pursuit

Multipath Sparse Coding Using Hierarchical Matching Pursuit

引用

IEEE Conference on Computer Vision and Pattern Recognition

作者： Liefeng Bo Xiaofeng Ren Dieter Fox ISTC-PC Intel Labs University of Washington

ISBN: (纸本)9781467364102

Complex real-world signals, such as images, contain discriminative structures that differ in many aspects including scale, invariance, and data channel. While progress in deep learning shows the importance of learning features through multiple layers, it is equally important to learn features through multiple paths. We propose Multipath Hierarchical Matching Pursuit (M-HMP), a novel feature learning architecture that combines a collection of hierarchical sparse features for image classification to capture multiple aspects of discriminative structures. Our building blocks are MI-KSVD, a codebook learning algorithm that balances the reconstruction error and the mutual incoherence of the codebook, and batch orthogonal matching pursuit (OMP);we apply them recursively at varying layers and scales. The result is a highly discriminative image representation that leads to large improvements to the state-of-the-art on many standard benchmarks, e.g., Caltech-101, Caltech-256, MIT-Scenes, Oxford-IIIT Pet and Caltech-UCSD Bird-200.

关键词： invariance data channel scales channels (data transmission) invariance Image classification matching pursuits reconstruction error codebook BALANCES sparse coding Hierarchical Dermal denticles image representation Scale invariance

来源：评论

学校读者我要写书评

暂无评论

Selective Routing of Spatial Information Flow from Input to Output in Hippocampal Granule Cells

引用

NEURON 2020年第6期107卷 1212-+页

作者： Zhang, Xiaomin Schloegl, Alois Jonas, Peter IST Austria Inst Sci & Technol Austria Cellular Neurosci Campus 1 A-3400 Klosterneuburg Austria

Dentate gyrus granule cells (GCs) connect the entorhinal cortex to the hippocampal CA3 region, but how they process spatial information remains enigmatic. To examine the role of GCs in spatial coding, we measured excitatory postsynaptic potentials (EPSPs) and action potentials (APs) in head-fixed mice running on a linear belt. Intracellular recording from morphologically identified GCs revealed that most cells were active, but activity level varied over a wide range. Whereas only similar to 5% of GCs showed spatially tuned spiking, similar to 50% received spatially tuned input. Thus, the GC population broadly encodes spatial information, but only a subset relays this information to the CA3 network. Fourier analysis indicated that GCs received conjunctive place-grid-like synaptic input, suggesting code conversion in single neurons. GC firing was correlated with dendritic complexity and intrinsic excitability, but not extrinsic excitatory input or dendritic cable properties. Thus, functional maturation may control input-output transformation and spatial code conversion.

关键词： dentate gyrus granule cells intracellular in vivo recording place cells grid cells sparse coding EPSPs intrinsic excitability action potential threshold code conversion spatial navigation

来源：评论

学校读者我要写书评

暂无评论

FIRMNET: A SPARSITY AMPLIFIED DEEP NETWORK FOR SOLVING LINEAR INVERSE PROBLEMS 44

FIRMNET: A SPARSITY AMPLIFIED DEEP NETWORK FOR SOLVING LINEA...

引用

44th IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)

作者： Pokala, Praveen Kumar Mahurkar, Amol G. Seelamantula, Chandra Sekhar Indian Inst Sci Dept Elect Engn Bangalore 12 Karnataka India

ISBN: (纸本)9781479981311

Recovering a sparse signal from a noisy linear measurement is an important problem in signal processing. Typically, one employs greedy pursuit techniques such as OMP, CoSaMP to solve an l(0) regularization problem. For large-scale problems, iterative shrinkage techniques such as ISTA, FISTA, AMP-l(1) have been introduced. The underlying formulation in the iterative algorithms is a LASSO problem with an l(1)-penalty. It is known in the literature that an l(1)-penalty in LASSO suffers from underestimation of large signal amplitudes. Also, the iterative shrinkage-based approaches such as ISTA typically have only one free parameter to trade-off between noise variance and sparsity. We consider a minimax-concave penalty-based formulation, which offers an unbiased estimate of the sparse signal. The resulting iterative firm-thresholding algorithm is restructured as a DNN architecture called FirmNet. The proposed network, FirmNet, has two interpretable shrinkage function parameters - one that controls the noise variance, and the other that allows for explicit sparsity control. We compare the network with a broader network architecture of Learned-ISTA (LISTA), and show that it outperforms in terms of the probability-of-error-in-support (PES) - a strong support recovery metric, by at least three-fold. We also observe an improvement of 2 to 4 dB in reconstruction SNR compared with LISTA.

关键词： sparse coding iterative algorithms proximal operators deep neural networks deep unfolding

来源：评论

学校读者我要写书评

暂无评论

Graph-Based Descriptor Learning for Non-Rigid 3D Shapes

Graph-Based Descriptor Learning for Non-Rigid 3D Shapes

引用

IEEE International Symposium on Circuits and Systems (IEEE ISCAS)

作者： Xiong, Yuehan Xiong, Hongkai Shanghai Jiao Tong Univ Dept Elect Engn Shanghai Peoples R China

ISBN: (纸本)9781728103976

In this paper, we propose a deformable 3D shape descriptor learning approach that takes into account the spatial correlations among local shape descriptors. By constructing a weighted graph that connects salient points on a shape surface, local feature descriptors on salient points are considered as signals defined on graph vertices, incorporating local surface information into the global graph structure. We then learn a graph structure-aware dictionary for each category of shapes with the multi-graph dictionary learning strategy, capturing similar spectral properties among graph signals generated from different shapes of the same category. Experiments conducted on representative 3D shape benchmark datasets demonstrate that our method improves over the state-of-the-art.

关键词： Shape descriptors sparse coding graph dictionary learning non-rigid 3D shapes spectral graph theory

来源：评论

学校读者我要写书评

暂无评论

A New Algorithm for Dictionary Learning Based on Convex Approximation 27

A New Algorithm for Dictionary Learning Based on Convex Appr...

引用

27th European Signal Processing Conference (EUSIPCO)

作者： Parsa, Javad Sadeghi, Mostafa Babaie-Zadeh, Massoud Jutten, Christian Sharif Univ Technol Elect Engn Dept Tehran Iran GIPSA Lab Grenoble France Inst Univ France Paris France

ISBN: (纸本)9789082797039

The purpose of dictionary learning problem is to learn a dictionary D from a training data matrix Y such that Y approximate to DX and the coefficient matrix X is sparse. Many algorithms have been introduced to this aim, which minimize the representation error subject to a sparseness constraint on X. However, the dictionary learning problem is non-convex with respect to the pair (D,X). In a previous work [Sadeghi et al., 2013], a convex approximation to the non-convex term DX has been introduced which makes the whole DL problem convex. This approach can be almost applied to any existing DL algorithm and obtain better algorithms. In the current paper, it is shown that a simple modification on that approach significantly improves its performance, in terms of both accuracy and speed. Simulation results on synthetic dictionary recovery are provided to confirm this claim.

关键词： Compressed sensing sparse coding convex approximation convergence rate dictionary learning

来源：评论

学校读者我要写书评

暂无评论

Approximate Guarantees for Dictionary Learning 32

Approximate Guarantees for Dictionary Learning

引用

32nd Conference on Learning Theory (COLT) part of the ACM Federated Computing Research Conference

作者： Bhaskara, Aditya Tai, Wai Ming Univ Utah Salt Lake City UT 84112 USA

In the dictionary learning (or sparse coding) problem, we are given a collection of signals (vectors in R-d), and the goal is to find a "basis" in which the signals have a sparse (approximate) representation. The problem has received a lot of attention in signal processing, learning, and theoretical computer science. The problem is formalized as factorizing a matrix X(d x n) (whose columns are the signals) as X = AY, where A has a prescribed number m of columns (typically m << n), and Y has columns that are k-sparse (typically k << d). Most of the known theoretical results involve assuming that the columns of the unknown A have certain incoherence properties, and that the coefficient matrix Y has random (or partly random) structure. The goal of our work is to understand what can be said in the absence of such assumptions. Can we still find A and Y such that X approximate to AY? We show that this is possible, if we allow violating the bounds on m and k by appropriate factors that depend on k and the desired approximation. Our results rely on an algorithm for what we call the threshold correlation problem, which turns out to be related to hypercontractive norms of matrices. We also show that our algorithmic ideas apply to a setting in which some of the columns of X are outliers, thus giving similar guarantees even in this challenging setting.

关键词： Dictionary learning sparse coding approximation algorithms pursuit algorithms

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：