Results 1 - 10
of
226
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 large-scale 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 157 (6 self)
- Add to MetaCart
(Show Context)
This paper addresses the problem of learning similaritypreserving binary codes for efficient retrieval in large-scale 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 zero-centered binary hypercube. This method, dubbed iterative quantization (ITQ), has connections to multi-class 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 state-of-the-art methods. 1.
Large-scale image retrieval with compressed Fisher vectors
- IN: CVPR PERRONNIN F, SÁNCHEZ J, LIU Y (2010B) LARGE-SCALE
, 2010
"... The problem of large-scale image search has been traditionally addressed with the bag-of-visual-words (BOV). In this article, we propose to use as an alternative the Fisher kernel framework. We first show why the Fisher representation is well-suited to the retrieval problem: it describes an image by ..."
Abstract
-
Cited by 100 (8 self)
- Add to MetaCart
The problem of large-scale image search has been traditionally addressed with the bag-of-visual-words (BOV). In this article, we propose to use as an alternative the Fisher kernel framework. We first show why the Fisher representation is well-suited to the retrieval problem: it describes an image by what makes it different from other images. One drawback of the Fisher vector is that it is high-dimensional and, as opposed to the BOV, it is dense. The resulting memory and computational costs do not make Fisher vectors directly amenable to large-scale retrieval. Therefore, we compress Fisher vectors to reduce their memory footprint and speed-up the retrieval. We compare three binarization approaches: a simple approach devised for this representation and two standard compression techniques. We show on two publicly available datasets that compressed Fisher vectors perform very well using as little as a few hundreds of bits per image, and significantly better than a very recent compressed BOV approach.
BSupervised hashing with kernels
- in Proc. IEEE Conf. Comput. Vis. Pattern Recognit
, 2012
"... Recent years have witnessed the growing popularity of hashing in large-scale vision problems. It has been shown that the hashing quality could be boosted by leveraging supervised information into hash function learning. However, the existing supervised methods either lack adequate performance or oft ..."
Abstract
-
Cited by 84 (24 self)
- Add to MetaCart
(Show Context)
Recent years have witnessed the growing popularity of hashing in large-scale vision problems. It has been shown that the hashing quality could be boosted by leveraging supervised information into hash function learning. However, the existing supervised methods either lack adequate performance or often incur cumbersome model training. In this paper, we propose a novel kernel-based supervised hashing model which requires a limited amount of supervised information, i.e., similar and dissimilar data pairs, and a feasible training cost in achieving high quality hashing. The idea is to map the data to compact binary codes whose Hamming distances are minimized on similar pairs and simultaneously maximized on dissimilar pairs. Our approach is distinct from prior works by utilizing the equivalence between optimizing the code inner products and the Hamming distances. This enables us to sequentially and efficiently train the hash functions one bit at a time, yielding very short yet discriminative codes. We carry out extensive experiments on two image benchmarks with up to one million samples, demonstrating that our approach significantly outperforms the state-of-the-arts in searching both metric distance neighbors and semantically similar neighbors, with accuracy gains ranging from 13 % to 46%. 1.
Ask the locals: multi-way local pooling for image recognition
- in ICCV’11. IEEE
, 2011
"... ..."
(Show Context)
Image retrieval with geometry-preserving visual phrases
- in CVPR, 2011
"... The most popular approach to large scale image re-trieval is based on the bag-of-visual-word (BoV) represen-tation of images. The spatial information is usually re-introduced as a post-processing step to re-rank the retrieved images, through a spatial verification like RANSAC. Since the spatial veri ..."
Abstract
-
Cited by 52 (1 self)
- Add to MetaCart
(Show Context)
The most popular approach to large scale image re-trieval is based on the bag-of-visual-word (BoV) represen-tation of images. The spatial information is usually re-introduced as a post-processing step to re-rank the retrieved images, through a spatial verification like RANSAC. Since the spatial verification techniques are computationally ex-pensive, they can be applied only to the top images in the initial ranking. In this paper, we propose an approach that can encode more spatial information into BoV representa-tion and that is efficient enough to be applied to large-scale databases. Other works pursuing the same purpose have proposed exploring the word co-occurrences in the neigh-borhood areas. Our approach encodes more spatial in-formation through the geometry-preserving visual phrases (GVP). In addition to co-occurrences, the GVP method also captures the local and long-range spatial layouts of the words. Our GVP based searching algorithm increases little memory usage or computational time compared to the BoV method. Moreover, we show that our approach can also be integrated to the min-hash method to improve its retrieval accuracy. The experiment results on Oxford 5K and Flicker 1M dataset show that our approach outperforms the BoV method even following a RANSAC verification. 1.
Searching and mining trillions of time series subsequences under dynamic time warping
- In SIGKDD
, 2012
"... Most time series data mining algorithms use similarity search as a core subroutine, and thus the time taken for similarity search is the bottleneck for virtually all time series data mining algorithms. The difficulty of scaling search to large datasets largely explains why most academic work on time ..."
Abstract
-
Cited by 43 (3 self)
- Add to MetaCart
(Show Context)
Most time series data mining algorithms use similarity search as a core subroutine, and thus the time taken for similarity search is the bottleneck for virtually all time series data mining algorithms. The difficulty of scaling search to large datasets largely explains why most academic work on time series data mining has plateaued at considering a few millions of time series objects, while much of industry and science sits on billions of time series objects waiting to be explored. In this work we show that by using a combination of four novel ideas we can search and mine truly massive time series for the first time. We demonstrate the following extremely unintuitive fact; in large datasets we can exactly search under DTW much more quickly than the current state-of-the-art Euclidean distance search algorithms. We demonstrate our work on the largest set of time series experiments ever attempted. In particular, the largest dataset we consider is larger than the combined size of all of the time series datasets considered in all data mining papers ever published. We show that our ideas allow us to solve higher-level time series data mining problem such as motif discovery and clustering at scales that would otherwise be untenable. In addition to mining massive datasets, we will show that our ideas also have implications for real-time monitoring of data streams, allowing us to handle much faster arrival rates and/or use cheaper and lower powered devices than are currently possible.
Attribute Discovery via Predictable Discriminative Binary Codes
- In ECCV
"... Abstract. We present images with binary codes in a way that balances discrimination and learnability of the codes. In our method, each image claims its own code in a way that maintains discrimination while being predictable from visual data. Category memberships are usually good proxies for visual s ..."
Abstract
-
Cited by 39 (7 self)
- Add to MetaCart
(Show Context)
Abstract. We present images with binary codes in a way that balances discrimination and learnability of the codes. In our method, each image claims its own code in a way that maintains discrimination while being predictable from visual data. Category memberships are usually good proxies for visual similarity but should not be enforced as a hard constraint. Our method learns codes that maximize separability of categories unless there is strong visual evidence against it. Simple linear SVMs can achieve state-of-the-art results with our short codes. In fact, our method produces state-of-the-art results on Caltech256 with only 128dimensional bit vectors and outperforms state of the art by using longer codes. We also evaluate our method on ImageNet and show that our method outperforms state-of-the-art binary code methods on this large scale dataset. Lastly, our codes can discover a discriminative set of attributes. 1
Picodes: Learning a compact code for novel-category recognition
- in NIPS, 2011
"... Abstract We introduce PICODES: a very compact image descriptor which nevertheless allows high performance on object category recognition. In particular, we address novel-category recognition: the task of defining indexing structures and image representations which enable a large collection of image ..."
Abstract
-
Cited by 33 (2 self)
- Add to MetaCart
(Show Context)
Abstract We introduce PICODES: a very compact image descriptor which nevertheless allows high performance on object category recognition. In particular, we address novel-category recognition: the task of defining indexing structures and image representations which enable a large collection of images to be searched for an object category, where the training images defining the category are supplied at query time. We explicitly learn descriptors of a target length (from as small as 16 bytes per image) which have good object-recognition performance. In contrast to previous work in the domain of object recognition, we do not choose an arbitrary intermediate representation, but explicitly learn short codes. In contrast to previous approaches to learn compact codes, we optimize explicitly for (an upper bound on) classification performance. Optimization directly for binary features is difficult and nonconvex, but we present an alternation scheme and convex upper bound which demonstrate excellent performance in practice. PICODES of 256 bytes match the accuracy of the current best known classifier for the Caltech256 benchmark, but they decrease the database storage size by a factor of 100 and speed-up the training and testing of novel classes by orders of magnitude.
Multi-Scale Orderless Pooling of Deep Convolutional Activation Features
"... Abstract. Deep convolutional neural networks (CNN) have shown their promise as a universal representation for recognition. However, global CNN activations lack geometric invariance, which limits their robustness for classification and matching of highly variable scenes. To improve the invariance of ..."
Abstract
-
Cited by 32 (2 self)
- Add to MetaCart
(Show Context)
Abstract. Deep convolutional neural networks (CNN) have shown their promise as a universal representation for recognition. However, global CNN activations lack geometric invariance, which limits their robustness for classification and matching of highly variable scenes. To improve the invariance of CNN activations without degrading their discriminative power, this paper presents a simple but effective scheme called multi-scale orderless pooling (MOP-CNN). This scheme extracts CNN activa-tions for local patches at multiple scale levels, performs orderless VLAD pooling of these activations at each level separately, and concatenates the result. The resulting MOP-CNN representation can be used as a generic feature for either supervised or unsupervised recognition tasks, from im-age classification to instance-level retrieval; it consistently outperforms global CNN activations without requiring any joint training of prediction layers for a particular target dataset. In absolute terms, it achieves state-of-the-art results on the challenging SUN397 and MIT Indoor Scenes clas-sification datasets, and competitive results on ILSVRC2012/2013 classi-fication and INRIA Holidays retrieval datasets. 1
