Results 1  10
of
439
Fast approximate nearest neighbors with automatic algorithm configuration
 In VISAPP International Conference on Computer Vision Theory and Applications
, 2009
"... nearestneighbors search, randomized kdtrees, hierarchical kmeans tree, clustering. For many computer vision problems, the most time consuming component consists of nearest neighbor matching in highdimensional spaces. There are no known exact algorithms for solving these highdimensional problems ..."
Abstract

Cited by 448 (2 self)
 Add to MetaCart
(Show Context)
nearestneighbors search, randomized kdtrees, hierarchical kmeans tree, clustering. For many computer vision problems, the most time consuming component consists of nearest neighbor matching in highdimensional spaces. There are no known exact algorithms for solving these highdimensional problems that are faster than linear search. Approximate algorithms are known to provide large speedups with only minor loss in accuracy, but many such algorithms have been published with only minimal guidance on selecting an algorithm and its parameters for any given problem. In this paper, we describe a system that answers the question, “What is the fastest approximate nearestneighbor algorithm for my data? ” Our system will take any given dataset and desired degree of precision and use these to automatically determine the best algorithm and parameter values. We also describe a new algorithm that applies priority search on hierarchical kmeans trees, which we have found to provide the best known performance on many datasets. After testing a range of alternatives, we have found that multiple randomized kd trees provide the best performance for other datasets. We are releasing public domain code that implements these approaches. This library provides about one order of magnitude improvement in query time over the best previously available software and provides fully automated parameter selection. 1
Spectral hashing
, 2009
"... Semantic hashing [1] seeks compact binary codes of datapoints so that the Hamming distance between codewords correlates with semantic similarity. In this paper, we show that the problem of finding a best code for a given dataset is closely related to the problem of graph partitioning and can be sho ..."
Abstract

Cited by 275 (4 self)
 Add to MetaCart
(Show Context)
Semantic hashing [1] seeks compact binary codes of datapoints so that the Hamming distance between codewords correlates with semantic similarity. In this paper, we show that the problem of finding a best code for a given dataset is closely related to the problem of graph partitioning and can be shown to be NP hard. By relaxing the original problem, we obtain a spectral method whose solutions are simply a subset of thresholded eigenvectors of the graph Laplacian. By utilizing recent results on convergence of graph Laplacian eigenvectors to the LaplaceBeltrami eigenfunctions of manifolds, we show how to efficiently calculate the code of a novel datapoint. Taken together, both learning the code and applying it to a novel point are extremely simple. Our experiments show that our codes outperform the stateofthe art.
Small codes and large image databases for recognition
 In Proceedings of the IEEE Conf on Computer Vision and Pattern Recognition
, 2008
"... The Internet contains billions of images, freely available online. Methods for efficiently searching this incredibly rich resource are vital for a large number of applications. These include object recognition [2], computer graphics [11, 27], personal photo collections, online image search tools. In ..."
Abstract

Cited by 185 (7 self)
 Add to MetaCart
(Show Context)
The Internet contains billions of images, freely available online. Methods for efficiently searching this incredibly rich resource are vital for a large number of applications. These include object recognition [2], computer graphics [11, 27], personal photo collections, online image search tools. In this paper, our goal is to develop efficient image search and scene matching techniques that are not only fast, but also require very little memory, enabling their use on standard hardware or even on handheld devices. Our approach uses recently developed machine learning techniques to convert the Gist descriptor (a real valued vector that describes orientation energies at different scales and orientations within an image) to a compact binary code, with a few hundred bits per image. Using our scheme, it is possible to perform realtime searches with millions from the Internet using a single large PC and obtain recognition results comparable to the full descriptor. Using our codes on high quality labeled images from the LabelMe database gives surprisingly powerful recognition results using simple nearest neighbor techniques. Recent interest in object recognition has yielded a wide range of approaches to describing the contents of an image. One important application for this technology is the visual search of large collections of images, such as those on the Internet or on people’s home computers. Accordingly, a number of recognition papers have explored this area. Nister and Stewenius demonstrate the realtime specific object recognition using a database of 40,000 images [19]; Obdrzalek and Matas show sublinear indexing time on the COIL dataset [20]. A common theme is the representation of the image as a collection of feature vectors and the use of efficient data structures to handle the large num
Iterative quantization: A procrustean approach to learning binary codes
 In Proc. of the IEEE Int. Conf. on Computer Vision and Pattern Recognition (CVPR
, 2011
"... This paper addresses the problem of learning similaritypreserving binary codes for efficient retrieval in largescale image collections. We propose a simple and efficient alternating minimization scheme for finding a rotation of zerocentered data so as to minimize the quantization error of mapping t ..."
Abstract

Cited by 151 (7 self)
 Add to MetaCart
(Show Context)
This paper addresses the problem of learning similaritypreserving binary codes for efficient retrieval in largescale image collections. We propose a simple and efficient alternating minimization scheme for finding a rotation of zerocentered data so as to minimize the quantization error of mapping this data to the vertices of a zerocentered binary hypercube. This method, dubbed iterative quantization (ITQ), has connections to multiclass spectral clustering and to the orthogonal Procrustes problem, and it can be used both with unsupervised data embeddings such as PCA and supervised embeddings such as canonical correlation analysis (CCA). Our experiments show that the resulting binary coding schemes decisively outperform several other stateoftheart methods. 1.
What does classifying more than 10,000 image categories tell us?
"... Image classification is a critical task for both humans and computers. One of the challenges lies in the large scale of the semantic space. In particular, humans can recognize tens of thousands of object classes and scenes. No computer vision algorithm today has been tested at this scale. This pape ..."
Abstract

Cited by 116 (12 self)
 Add to MetaCart
(Show Context)
Image classification is a critical task for both humans and computers. One of the challenges lies in the large scale of the semantic space. In particular, humans can recognize tens of thousands of object classes and scenes. No computer vision algorithm today has been tested at this scale. This paper presents a study of large scale categorization including a series of challenging experiments on classification with more than 10, 000 image classes. We find that a) computational issues become crucial in algorithm design; b) conventional wisdom from a couple of hundred image categories on relative performance of different classifiers does not necessarily hold when the number of categories increases; c) there is a surprisingly strong relationship between the structure of WordNet (developed for studying language) and the difficulty of visual categorization; d) classification can be improved by exploiting the semantic hierarchy. Toward the future goal of developing automatic vision algorithms to recognize tens of thousands or even millions of image categories, we make a series of observations and arguments about dataset scale, category density, and image hierarchy.
Building Rome on a Cloudless Day
"... Abstract. This paper introduces an approach for dense 3D reconstruction from unregistered Internetscale photo collections with about 3 million images within the span of a day on a single PC (“cloudless”). Our method advances image clustering, stereo, stereo fusion and structure from motion to achie ..."
Abstract

Cited by 89 (13 self)
 Add to MetaCart
(Show Context)
Abstract. This paper introduces an approach for dense 3D reconstruction from unregistered Internetscale photo collections with about 3 million images within the span of a day on a single PC (“cloudless”). Our method advances image clustering, stereo, stereo fusion and structure from motion to achieve high computational performance. We leverage geometric and appearance constraints to obtain a highly parallel implementation on modern graphics processors and multicore architectures. This leads to two orders of magnitude higher performance on an order of magnitude larger dataset than competing stateoftheart approaches. 1
Robust 1Bit Compressive Sensing via Binary Stable Embeddings of Sparse Vectors
, 2011
"... The Compressive Sensing (CS) framework aims to ease the burden on analogtodigital converters (ADCs) by reducing the sampling rate required to acquire and stably recover sparse signals. Practical ADCs not only sample but also quantize each measurement to a finite number of bits; moreover, there is ..."
Abstract

Cited by 85 (28 self)
 Add to MetaCart
The Compressive Sensing (CS) framework aims to ease the burden on analogtodigital converters (ADCs) by reducing the sampling rate required to acquire and stably recover sparse signals. Practical ADCs not only sample but also quantize each measurement to a finite number of bits; moreover, there is an inverse relationship between the achievable sampling rate and the bit depth. In this paper, we investigate an alternative CS approach that shifts the emphasis from the sampling rate to the number of bits per measurement. In particular, we explore the extreme case of 1bit CS measurements, which capture just their sign. Our results come in two flavors. First, we consider ideal reconstruction from noiseless 1bit measurements and provide a lower bound on the best achievable reconstruction error. We also demonstrate that a large class of measurement mappings achieve this optimal bound. Second, we consider reconstruction robustness to measurement errors and noise and introduce the Binary ɛStable Embedding (BɛSE) property, which characterizes the robustness measurement process to sign changes. We show the same class of matrices that provide optimal noiseless performance also enable such a robust mapping. On the practical side, we introduce the Binary Iterative Hard Thresholding (BIHT) algorithm for signal reconstruction from 1bit measurements that offers stateoftheart performance.
LocalitySensitive Binary Codes from ShiftInvariant Kernels,” Advances in neural information processing systems
, 2009
"... This paper addresses the problem of designing binary codes for highdimensional data such that vectors that are similar in the original space map to similar binary strings. We introduce a simple distributionfree encoding scheme based on random projections, such that the expected Hamming distance be ..."
Abstract

Cited by 81 (1 self)
 Add to MetaCart
(Show Context)
This paper addresses the problem of designing binary codes for highdimensional data such that vectors that are similar in the original space map to similar binary strings. We introduce a simple distributionfree encoding scheme based on random projections, such that the expected Hamming distance between the binary codes of two vectors is related to the value of a shiftinvariant kernel (e.g., a Gaussian kernel) between the vectors. We present a full theoretical analysis of the convergence properties of the proposed scheme, and report favorable experimental performance as compared to a recent stateoftheart method, spectral hashing. 1
Pairwise Document Similarity in Large Collections with MapReduce
"... This paper presents a MapReduce algorithm for computing pairwise document similarity in large document collections. MapReduce is an attractive framework because it allows us to decompose the inner products involved in computing document similarity into separate multiplication and summation stages in ..."
Abstract

Cited by 57 (6 self)
 Add to MetaCart
(Show Context)
This paper presents a MapReduce algorithm for computing pairwise document similarity in large document collections. MapReduce is an attractive framework because it allows us to decompose the inner products involved in computing document similarity into separate multiplication and summation stages in a way that is well matched to efficient disk access patterns across several machines. On a collection consisting of approximately 900,000 newswire articles, our algorithm exhibits linear growth in running time and space in terms of the number of documents. 1