Results 1 - 10
of
52
Object-Graphs for Context-Aware 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 object-level 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 appearance-based baselines. 1.
Shape discovery from unlabeled image collections
- CVPR
, 2009
"... Can we discover common object shapes within unlabeled multi-category collections of images? While often a critical cue at the category-level, 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 multi-category collections of images? While often a critical cue at the category-level, 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 within-cluster 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 multi-modal 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 heteroge-neous 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 heteroge-neous features has become an increasing critical problem. In this paper, we propose a novel approach to unsupervised integrate such heterogeneous features by performing multi-modal spectral clustering on unlabeled images and unseg-mented images. Considering each type of feature as one modal, our new multi-modal spectral clustering (MMSC) algorithm is to learn a commonly shared graph Laplacian matrix by unifying different modals (image features). A non-negative relaxation is also added in our method to improve the robustness and efficiency of image clustering. We ap-plied our MMSC method to integrate five types of popu-larly used image features, including SIFT, HOG, GIST, LBP, CENTRIST and evaluated the performance by two bench-mark data sets: Caltech-101 andMSRC-v1. Compared with existing unsupervised scene and object categorization meth-ods, our approach always achieves superior performances measured by three standard clustering evaluation metrices. 1.
Cost-Sensitive 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 long-term. 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 large-scale machine learning problems (such as clustering, non-parametric 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 large-scale machine learning problems (such as clustering, non-parametric 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 large-scale 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, two-stage 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 exemplar-based 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 row-sparsity 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 row-sparsity 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 metric-based 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 real-world 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, Stream-Greedy, which is guaranteed to obtain a constant fraction of the value achieved by the optimal solution to this NP-hard optimization problem. We extensively evaluate our algorithm on large real-world 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 high-dimensional 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 high-dimensional 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 MKL-DR) 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 semi-supervised ones. Index Terms—Dimensionality reduction, multiple kernel learning, object categorization, image clustering, face recognition. Ç 1
Flexible Priors for Exemplar-based Clustering
"... Exemplar-based clustering methods have been shown to produce state-of-the-art results on a number of synthetic and real-world clustering problems. They are appealing because they offer computational benefits over latent-mean models and can handle arbitrary pairwise similarity measures between data p ..."
Abstract
-
Cited by 10 (3 self)
- Add to MetaCart
(Show Context)
Exemplar-based clustering methods have been shown to produce state-of-the-art results on a number of synthetic and real-world clustering problems. They are appealing because they offer computational benefits over latent-mean 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 exemplar-based 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., k-means, 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-
