Results 1  10
of
52
ObjectGraphs for ContextAware Category Discovery
, 2009
"... How can knowing about some categories help us to discover new ones in unlabeled images? Unsupervised visual category discovery is useful to mine for recurring objects without human supervision, but existing methods assume no prior information and thus tend to perform poorly for cluttered scenes with ..."
Abstract

Cited by 43 (3 self)
 Add to MetaCart
(Show Context)
How can knowing about some categories help us to discover new ones in unlabeled images? Unsupervised visual category discovery is useful to mine for recurring objects without human supervision, but existing methods assume no prior information and thus tend to perform poorly for cluttered scenes with multiple objects. We propose to leverage knowledge about previously learned categories to enable more accurate discovery. We introduce a novel objectgraph descriptor to encode the layout of objectlevel cooccurrence patterns relative to an unfamiliar region, and show that by using it to model the interaction between an image’s known and unknown objects we can better detect new visual categories. Rather than mine for all categories from scratch, our method can continually identify new objects while drawing on useful cues from familiar ones. We evaluate our approach on benchmark datasets and demonstrate clear improvements in discovery over conventional purely appearancebased baselines. 1.
Shape discovery from unlabeled image collections
 CVPR
, 2009
"... Can we discover common object shapes within unlabeled multicategory collections of images? While often a critical cue at the categorylevel, contour matches can be difficult to isolate reliably from edge clutter—even within labeled images from a known class, let alone unlabeled examples. We propose ..."
Abstract

Cited by 29 (1 self)
 Add to MetaCart
(Show Context)
Can we discover common object shapes within unlabeled multicategory collections of images? While often a critical cue at the categorylevel, contour matches can be difficult to isolate reliably from edge clutter—even within labeled images from a known class, let alone unlabeled examples. We propose a shape discovery method in which local appearance (patch) matches serve to anchor the surrounding edge fragments, yielding a more reliable affinity function for images that accounts for both shape and appearance. Spectral clustering from the initial affinities provides candidate object clusters. Then, we compute the withincluster match patterns to discern foreground edges from clutter, attributing higher weight to edges more likely to belong to a common object. In addition to discovering the object contours in each image, we show how to summarize what is found with prototypical shapes. Our results on benchmark datasets demonstrate the approach can successfully discover shapes from unlabeled images.
Heterogeneous image feature integration via multimodal spectral clustering
 In CVPR
, 1977
"... In recent years, more and more visual descriptors have been proposed to describe objects and scenes appearing in images. Different features describe different aspects of the visual characteristics. How to combine these heterogeneous features has become an increasing critical problem. In this paper, ..."
Abstract

Cited by 18 (4 self)
 Add to MetaCart
(Show Context)
In recent years, more and more visual descriptors have been proposed to describe objects and scenes appearing in images. Different features describe different aspects of the visual characteristics. How to combine these heterogeneous features has become an increasing critical problem. In this paper, we propose a novel approach to unsupervised integrate such heterogeneous features by performing multimodal spectral clustering on unlabeled images and unsegmented images. Considering each type of feature as one modal, our new multimodal spectral clustering (MMSC) algorithm is to learn a commonly shared graph Laplacian matrix by unifying different modals (image features). A nonnegative relaxation is also added in our method to improve the robustness and efficiency of image clustering. We applied our MMSC method to integrate five types of popularly used image features, including SIFT, HOG, GIST, LBP, CENTRIST and evaluated the performance by two benchmark data sets: Caltech101 andMSRCv1. Compared with existing unsupervised scene and object categorization methods, our approach always achieves superior performances measured by three standard clustering evaluation metrices. 1.
CostSensitive Active Visual Category Learning
, 2009
"... Are larger image training sets necessarily better for recognition? The accuracies of most current object recognition methods steadily improve as more and more labeled training data is made available. However, this requires manually collecting and possibly further annotating image examples, which i ..."
Abstract

Cited by 17 (0 self)
 Add to MetaCart
Are larger image training sets necessarily better for recognition? The accuracies of most current object recognition methods steadily improve as more and more labeled training data is made available. However, this requires manually collecting and possibly further annotating image examples, which is an expensive endeavor. Though the protocol of learning models from carefully gathered images has proven fruitful, it is too expensive to perpetuate in the longterm. Active learning strategies have the potential to reduce this burden by generally selecting only the most informative examples to label.
Distributed submodular maximization: Identifying representative elements in massive data
 In Neural Information Processing Systems (NIPS
, 2013
"... Abstract Many largescale machine learning problems (such as clustering, nonparametric learning, kernel machines, etc.) require selecting, out of a massive data set, a manageable yet representative subset. Such problems can often be reduced to maximizing a submodular set function subject to cardin ..."
Abstract

Cited by 16 (6 self)
 Add to MetaCart
Abstract Many largescale machine learning problems (such as clustering, nonparametric learning, kernel machines, etc.) require selecting, out of a massive data set, a manageable yet representative subset. Such problems can often be reduced to maximizing a submodular set function subject to cardinality constraints. Classical approaches require centralized access to the full data set; but for truly largescale problems, rendering the data centrally is often impractical. In this paper, we consider the problem of submodular function maximization in a distributed fashion. We develop a simple, twostage protocol GREEDI, that is easily implemented using MapReduce style computations. We theoretically analyze our approach, and show, that under certain natural conditions, performance close to the (impractical) centralized approach can be achieved. In our extensive experiments, we demonstrate the effectiveness of our approach on several applications, including sparse Gaussian process inference and exemplarbased clustering, on tens of millions of data points using Hadoop.
Finding Exemplars from Pairwise Dissimilarities via Simultaneous Sparse Recovery
"... Given pairwise dissimilarities between data points, we consider the problem of finding a subset of data points, called representatives or exemplars, that can efficiently describe the data collection. We formulate the problem as a rowsparsity regularized trace minimization problem that can be solved ..."
Abstract

Cited by 13 (3 self)
 Add to MetaCart
(Show Context)
Given pairwise dissimilarities between data points, we consider the problem of finding a subset of data points, called representatives or exemplars, that can efficiently describe the data collection. We formulate the problem as a rowsparsity regularized trace minimization problem that can be solved efficiently using convex programming. The solution of the proposed optimization program finds the representatives and the probability that each data point is associated with each one of the representatives. We obtain the range of the regularization parameter for which the solution of the proposed optimization program changes from selecting one representative for all data points to selecting all data points as representatives. When data points are distributed around multiple clusters according to the dissimilarities, we show that the data points in each cluster select representatives only from that cluster. Unlike metricbased methods, our algorithm can be applied to dissimilarities that are asymmetric or violate the triangle inequality, i.e., it does not require that the pairwise dissimilarities come from a metric. We demonstrate the effectiveness of the proposed algorithm on synthetic data as well as realworld image and text data. 1
Budgeted Nonparametric Learning from Data Streams
"... We consider the problem of extracting informative exemplars from a data stream. Examples of this problem include exemplarbased clustering and nonparametric inference such as Gaussian process regression on massive data sets. We show that these problems require maximization of a submodular function th ..."
Abstract

Cited by 12 (7 self)
 Add to MetaCart
(Show Context)
We consider the problem of extracting informative exemplars from a data stream. Examples of this problem include exemplarbased clustering and nonparametric inference such as Gaussian process regression on massive data sets. We show that these problems require maximization of a submodular function that captures the informativeness of a set of exemplars, over a data stream. We develop an efficient algorithm, StreamGreedy, which is guaranteed to obtain a constant fraction of the value achieved by the optimal solution to this NPhard optimization problem. We extensively evaluate our algorithm on large realworld data sets. 1.
Multiple kernel learning for dimensionality reduction
 Pattern Analysis and Machine Intelligence, IEEE Transactions on
"... Abstract—In solving complex visual learning tasks, adopting multiple descriptors to more precisely characterize the data has been a feasible way for improving performance. The resulting data representations are typically highdimensional and assume diverse forms. Hence, finding a way of transforming ..."
Abstract

Cited by 10 (1 self)
 Add to MetaCart
(Show Context)
Abstract—In solving complex visual learning tasks, adopting multiple descriptors to more precisely characterize the data has been a feasible way for improving performance. The resulting data representations are typically highdimensional and assume diverse forms. Hence, finding a way of transforming them into a unified space of lower dimension generally facilitates the underlying tasks such as object recognition or clustering. To this end, the proposed approach (termed MKLDR) generalizes the framework of multiple kernel learning for dimensionality reduction, and distinguishes itself with the following three main contributions: First, our method provides the convenience of using diverse image descriptors to describe useful characteristics of various aspects about the underlying data. Second, it extends a broad set of existing dimensionality reduction techniques to consider multiple kernel learning, and consequently improves their effectiveness. Third, by focusing on the techniques pertaining to dimensionality reduction, the formulation introduces a new class of applications with the multiple kernel learning framework to address not only the supervised learning problems but also the unsupervised and semisupervised ones. Index Terms—Dimensionality reduction, multiple kernel learning, object categorization, image clustering, face recognition. Ç 1
Flexible Priors for Exemplarbased Clustering
"... Exemplarbased clustering methods have been shown to produce stateoftheart results on a number of synthetic and realworld clustering problems. They are appealing because they offer computational benefits over latentmean models and can handle arbitrary pairwise similarity measures between data p ..."
Abstract

Cited by 10 (3 self)
 Add to MetaCart
(Show Context)
Exemplarbased clustering methods have been shown to produce stateoftheart results on a number of synthetic and realworld clustering problems. They are appealing because they offer computational benefits over latentmean models and can handle arbitrary pairwise similarity measures between data points. However, when trying to recover underlying structure in clustering problems, tailored similarity measures are often not enough; we also desire control over the distribution of cluster sizes. Priors such as Dirichlet process priors allow the number of clusters to be unspecified while expressing priors over data partitions. To our knowledge, they have not been applied to exemplarbased models. We show how to incorporate priors, including Dirichlet process priors, into the recently introduced affinity propagation algorithm. We develop an efficient maxproduct belief propagation algorithm for our new model and demonstrate experimentally how the expanded range of clustering priors allows us to better recover true clusterings in situations where we have some information about the generating process. 1
Comparing Clusterings in Space
"... This paper proposes a new method for comparing clusterings both partitionally and geometrically. Our approach is motivated by the following observation: the vast majority of previous techniques for comparing clusterings are entirely partitional, i.e., they examine assignments of points in set theore ..."
Abstract

Cited by 10 (1 self)
 Add to MetaCart
This paper proposes a new method for comparing clusterings both partitionally and geometrically. Our approach is motivated by the following observation: the vast majority of previous techniques for comparing clusterings are entirely partitional, i.e., they examine assignments of points in set theoretic terms after they have been partitioned. In doing so, these methods ignore the spatial layout of the data, disregarding the fact that this information is responsible for generating the clusterings to begin with. We demonstrate that this leads to a variety of failure modes. Previous comparison techniques often fail to differentiate between significant changes made in data being clustered. We formulate a new measure for comparing clusterings that combines spatial and partitional information into a single measure using optimization theory. Doing so eliminates pathological conditions in previous approaches. It also simultaneously removes common limitations, such as that each clustering must have the same number of clusters or they are over identical datasets. This approach is stable, easily implemented, and has strong intuitive appeal. spatial properties as well as their cluster membership assignments. We view a clustering as a partition of a set of points located in a space with an associated distance function. This view is natural, since popular clustering algorithms, e.g., kmeans, spectral clustering, affinity propagation, etc., take as input not only a collection of points to be clustered but also a distance function on the space in which the points lie. This distance function may be specified implicitly and it may be transformed by a kernel, but it must be defined one way or another and its properties are crucial to a clustering algorithm’s output. In contrast, almost all existing clustering comparison techniques ignore the distances between points, treating clusterings as partitions of disembodied atoms. While this approach has merit under some circumstances, it seems surprising to ignore the distance func