Results 1  10
of
76
Laplacian Eigenmaps for Dimensionality Reduction and Data Representation
 Neural Computation
, 2003
"... Abstract One of the central problems in machine learning and pattern recognition is to develop appropriate representations for complex data. We consider the problem of constructing a representation for data lying on a low dimensional manifold embedded in a high dimensional space. Drawing on the corr ..."
Abstract

Cited by 1032 (14 self)
 Add to MetaCart
Abstract One of the central problems in machine learning and pattern recognition is to develop appropriate representations for complex data. We consider the problem of constructing a representation for data lying on a low dimensional manifold embedded in a high dimensional space. Drawing on the correspondence between the graph Laplacian, the Laplace Beltrami operator on the manifold, and the connections to the heat equation, we propose a geometrically motivated algorithm for representing the high dimensional data. The algorithm provides a computationally efficient approach to nonlinear dimensionality reduction that has locality preserving properties and a natural connection to clustering. Some potential applications and illustrative examples are discussed. 1 Introduction In many areas of artificial intelligence, information retrieval and data mining, one is often confronted with intrinsically low dimensional data lying in a very high dimensional space. Consider, for example, gray scale images of an object taken under fixed lighting conditions with a moving camera. Each such image would typically be represented by a brightness value at each pixel. If there were n 2
Think Globally, Fit Locally: Unsupervised Learning of Low Dimensional Manifolds
 Journal of Machine Learning Research
, 2003
"... The problem of dimensionality reduction arises in many fields of information processing, including machine learning, data compression, scientific visualization, pattern recognition, and neural computation. ..."
Abstract

Cited by 354 (11 self)
 Add to MetaCart
The problem of dimensionality reduction arises in many fields of information processing, including machine learning, data compression, scientific visualization, pattern recognition, and neural computation.
Locality Preserving Projections
, 2002
"... Many problems in information processing involve some form of dimensionality reduction. In this paper, we introduce Locality Preserving Projections (LPP). These are linear projective maps that arise by solving a variational problem that optimally preserves the neighborhood structure of the data s ..."
Abstract

Cited by 354 (16 self)
 Add to MetaCart
Many problems in information processing involve some form of dimensionality reduction. In this paper, we introduce Locality Preserving Projections (LPP). These are linear projective maps that arise by solving a variational problem that optimally preserves the neighborhood structure of the data set. LPP should be seen as an alternative to Principal Component Analysis (PCA)  a classical linear technique that projects the data along the directions of maximal variance. When the high dimensional data lies on a low dimensional manifold embedded in the ambient space, the Locality Preserving Projections are obtained by finding the optimal linear approximations to the eigenfunctions of the Laplace Beltrami operator on the manifold. As a result, LPP shares many of the data representation properties of nonlinear techniques such as Laplacian Eigenmaps or Locally Linear Embedding. Yet LPP is linear and more crucially is defined everywhere in ambient space rather than just on the training data points. This is borne out by illustrative examples on some high dimensional data sets.
Unsupervised Learning of Image Manifolds by Semidefinite Programming
, 2004
"... Can we detect low dimensional structure in high dimensional data sets of images and video? The problem of dimensionality reduction arises often in computer vision and pattern recognition. In this paper, we propose a new solution to this problem based on semidefinite programming. Our algorithm can be ..."
Abstract

Cited by 237 (10 self)
 Add to MetaCart
Can we detect low dimensional structure in high dimensional data sets of images and video? The problem of dimensionality reduction arises often in computer vision and pattern recognition. In this paper, we propose a new solution to this problem based on semidefinite programming. Our algorithm can be used to analyze high dimensional data that lies on or near a low dimensional manifold. It overcomes certain limitations of previous work in manifold learning, such as Isomap and locally linear embedding. We illustrate the algorithm on easily visualized examples of curves and surfaces, as well as on actual images of faces, handwritten digits, and solid objects.
Intensity versus identity coding in an olfactory system
 Neuron
, 2003
"... be thought of as a highdimensional vector of principal neuron states (e.g., instantaneous firing rates) evolving over the duration of the stimulus in a stimulusspecific ..."
Abstract

Cited by 90 (6 self)
 Add to MetaCart
(Show Context)
be thought of as a highdimensional vector of principal neuron states (e.g., instantaneous firing rates) evolving over the duration of the stimulus in a stimulusspecific
Learning an image manifold for retrieval
 In Proc. ACM Multimedia
, 2004
"... We consider the problem of learning a mapping function from lowlevel feature space to highlevel semantic space. Under the assumption that the data lie on a submanifold embedded in a high dimensional Euclidean space, we propose a relevance feedback scheme which is naturally conducted only on the im ..."
Abstract

Cited by 59 (4 self)
 Add to MetaCart
(Show Context)
We consider the problem of learning a mapping function from lowlevel feature space to highlevel semantic space. Under the assumption that the data lie on a submanifold embedded in a high dimensional Euclidean space, we propose a relevance feedback scheme which is naturally conducted only on the image manifold in question rather than the total ambient space. While images are typically represented by feature vectors in R n, the natural distance is often different from the distance induced by the ambient space R n. The geodesic distances on manifold are used to measure the similarities between images. However, when the number of data points is small, it is hard to discover the intrinsic manifold structure. Based on user interactions in a relevance feedback driven querybyexample system, the intrinsic similarities between images can be accurately estimated. We then develop an algorithmic framework to approximate the optimal mapping function by a Radial Basis Function (RBF) neural network. The semantics of a new image can be inferred by the RBF neural network. Experimental results show that our approach is effective in improving the performance of contentbased image retrieval systems.
Imagebased human age estimation by manifold learning and locally adjusted robust regression
 IEEE Transactions on Image Processing
, 2008
"... Abstract—Estimating human age automatically via facial image analysis has lots of potential realworld applications, such as human computer interaction and multimedia communication. However, it is still a challenging problem for the existing computer vision systems to automatically and effectively e ..."
Abstract

Cited by 54 (5 self)
 Add to MetaCart
(Show Context)
Abstract—Estimating human age automatically via facial image analysis has lots of potential realworld applications, such as human computer interaction and multimedia communication. However, it is still a challenging problem for the existing computer vision systems to automatically and effectively estimate human ages. The aging process is determined by not only the person’s gene, but also many external factors, such as health, living style, living location, and weather conditions. Males and females may also age differently. The current age estimation performance is still not good enough for practical use and more effort has to be put into this research direction. In this paper, we introduce the age manifold learning scheme for extracting face aging features and design a locally adjusted robust regressor for learning and prediction of human ages. The novel approach improves the age estimation accuracy significantly over all previous methods. The merit of the proposed approaches for imagebased age estimation is shown by extensive experiments on a large internal age database and the public available FGNET database. Index Terms—Age manifold, human age estimation, locally adjusted robust regression, manifold learning, nonlinear regression, support vector machine (SVM), support vector regression (SVR). I.
Strategies of shape representation in macaque visual area V2
 Visual Neuroscience
"... Contours and surface textures provide powerful cues used in image segmentation and the analysis of object shape. To learn more about how the visual system extracts and represents these visual cues, we studied the responses of V2 neurons in awake, fixating monkeys to complex contour stimuli (angles, ..."
Abstract

Cited by 20 (4 self)
 Add to MetaCart
(Show Context)
Contours and surface textures provide powerful cues used in image segmentation and the analysis of object shape. To learn more about how the visual system extracts and represents these visual cues, we studied the responses of V2 neurons in awake, fixating monkeys to complex contour stimuli (angles, intersections, arcs, and circles) and texture patterns such as nonCartesian gratings, along with conventional bars and sinusoidal gratings. Substantial proportions of V2 cells conveyed information about many contour and texture characteristics associated with our stimuli, including shape, size, orientation, and spatial frequency. However, the cells differed considerably in terms of their degree of selectivity for the various stimulus characteristics. On average, V2 cells responded better to grating stimuli but were more selective for contour stimuli. Metric multidimensional scaling and principal components analysis showed that, as a population, V2 cells show strong correlations in how they respond to different stimulus types. The first two and five principal components accounted for 69 % and 85 % of the overall response variation, respectively, suggesting that the response correlations simplified the population representation of shape information with relatively little loss of information. Moreover, smaller random subsets of the population carried response correlation patterns very similar to the population as a whole, indicating that the response correlations were a widespread property of V2 cells. Thus, V2 cells extract information about a number of higher order shape cues related to contours and surface textures and about similarities among many of these shape cues. This may reflect an efficient strategy of representing cues for image segmentation and object shape using finite neuronal resources.
Is a single energy functional sufficient? adaptive energy functionals and automatic initialization
 In Proc. MICCAI, Part II, volume 4792 of LNCS
, 2007
"... Abstract. Energy functional minimization is an increasingly popular technique for image segmentation. However, it is far too commonly applied with handtuned parameters and initializations that have only been validated for a few images. Fixing these parameters over a set of images assumes the same p ..."
Abstract

Cited by 18 (4 self)
 Add to MetaCart
(Show Context)
Abstract. Energy functional minimization is an increasingly popular technique for image segmentation. However, it is far too commonly applied with handtuned parameters and initializations that have only been validated for a few images. Fixing these parameters over a set of images assumes the same parameters are ideal for each image. We highlight the effects of varying the parameters and initialization on segmentation accuracy and propose a framework for attaining improved results using image adaptive parameters and initializations. We provide an analytical definition of optimal weights for functional terms through an examination of segmentation in the context of image manifolds, where nearby images on the manifold require similar parameters and similar initializations. Our results validate that fixed parameters are insufficient in addressing the variability in real clinical data, that similar images require similar parameters, and demonstrate how these parameters correlate with the image manifold. We present significantly improved segmentations for synthetic images and a set of 470 clinical examples. 1
Learning high dimensional correspondences from low dimensional manifolds
 In: Workshop on The Continuum from Labeled to Unlabeled Data in Machine Learning and Data Mining
, 2003
"... Many different high dimensional data sets are characterized by the same underlying modes of variability. When these modes of variability are continuous and few in number, they can be viewed as parameterizing a low dimensional manifold. The manifold provides a compact shared representation of the dat ..."
Abstract

Cited by 18 (0 self)
 Add to MetaCart
(Show Context)
Many different high dimensional data sets are characterized by the same underlying modes of variability. When these modes of variability are continuous and few in number, they can be viewed as parameterizing a low dimensional manifold. The manifold provides a compact shared representation of the data, suggesting correspondences between the high dimensional examples from different data sets. These correspondences, though naturally induced by the underlying manifold, are difficult to learn using traditional methods in supervised learning. In this paper, we generalize three methods in unsupervised learning—principal components analysis, factor analysis, and locally linear embedding— to discover subspaces and manifolds that provide common low dimensional representations of different high dimensional data sets. We use the shared representations discovered by these algorithms to put high dimensional examples from different data sets into correspondence. Finally, we show that a notion of “selfcorrespondence” between examples in the same data set can be used to improve the performance of these algorithms on small data sets. The algorithms are demonstrated on images and text. 1.