Results 1 - 10
of
107
Learning globally-consistent local distance functions for shape-based image retrieval and classification
- In ICCV
, 2007
"... We address the problem of visual category recognition by learning an image-to-image distance function that attempts to satisfy the following property: the distance between images from the same category should be less than the distance between images from different categories. We use patch-based feat ..."
Abstract
-
Cited by 149 (3 self)
- Add to MetaCart
(Show Context)
We address the problem of visual category recognition by learning an image-to-image distance function that attempts to satisfy the following property: the distance between images from the same category should be less than the distance between images from different categories. We use patch-based feature vectors common in object recognition work as a basis for our image-to-image distance functions. Our large-margin formulation for learning the distance functions is similar to formulations used in the machine learning literature on distance metric learning, however we differ in that we learn local distance functions— a different parameterized function for every image of our training set—whereas typically a single global distance function is learned. This was a novel approach first introduced in Frome, Singer, & Malik, NIPS 2006. In that work we learned the local distance functions independently, and the outputs of these functions could not be compared at test time without the use of additional heuristics or training. Here we introduce a different approach that has the advantage that it learns distance functions that are globally consistent in that they can be directly compared for purposes of retrieval and classification. The output of the learning algorithm are weights assigned to the image features, which is intuitively appealing in the computer vision setting: some features are more salient than others, and which are more salient depends on the category, or image, being considered. We train and test using the Caltech 101 object recognition benchmark. Using fifteen training images per category, we achieved a mean recognition rate of 63.2 % and
Recognition using Regions
"... This paper presents a unified framework for object detection, segmentation, and classification using regions. Region features are appealing in this context because: (1) they encode shape and scale information of objects naturally; (2) they are only mildly affected by background clutter. Regions have ..."
Abstract
-
Cited by 106 (5 self)
- Add to MetaCart
(Show Context)
This paper presents a unified framework for object detection, segmentation, and classification using regions. Region features are appealing in this context because: (1) they encode shape and scale information of objects naturally; (2) they are only mildly affected by background clutter. Regions have not been popular as features due to their sensitivity to segmentation errors. In this paper, we start by producing a robust bag of overlaid regions for each image using Arbeláez et al., CVPR 2009. Each region is represented by a rich set of image cues (shape, color and texture). We then learn region weights using a max-margin framework. In detection and segmentation, we apply a generalized Hough voting scheme to generate hypotheses of object locations, scales and support, followed by a verification classifier and a constrained segmenter on each hypothesis. The proposed approach significantly outperforms the state of the art on the ETHZ shape database (87.1 % average detection rate compared to Ferrari et al.’s 67.2%), and achieves competitive performance on the Caltech 101 database.
Learning visual similarity measures for comparing never seen objects
- Proc. IEEE CVPR
, 2007
"... In this paper we propose and evaluate an algorithm that learns a similarity measure for comparing never seen objects. The measure is learned from pairs of training images labeled “same ” or “different”. This is far less informative than the commonly used individual image labels (e.g. “car model X”), ..."
Abstract
-
Cited by 82 (0 self)
- Add to MetaCart
In this paper we propose and evaluate an algorithm that learns a similarity measure for comparing never seen objects. The measure is learned from pairs of training images labeled “same ” or “different”. This is far less informative than the commonly used individual image labels (e.g. “car model X”), but it is cheaper to obtain. The proposed algorithm learns the characteristic differences between local descriptors sampled from pairs of “same ” and “different” images. These differences are vector quantized by an ensemble of extremely randomized binary trees, and the similarity measure is computed from the quantized differences. The extremely randomized trees are fast to learn, robust due to the redundant information they carry and they have been proved to be very good clusterers. Furthermore, the trees efficiently combine different feature types (SIFT and geometry). We evaluate our innovative similarity measure on four very different datasets and consistantly outperform the state-of-the-art competitive approaches. 1.
Randomized clustering forests for image classification
- Pattern Analysis and Machine Intelligence
"... Abstract—This paper introduces three new contributions to the problems of image classification and image search. First, we propose a new image patch quantization algorithm. Other competitive approaches require a large code book and the sampling of many local regions for accurate image description, a ..."
Abstract
-
Cited by 82 (3 self)
- Add to MetaCart
(Show Context)
Abstract—This paper introduces three new contributions to the problems of image classification and image search. First, we propose a new image patch quantization algorithm. Other competitive approaches require a large code book and the sampling of many local regions for accurate image description, at the expense of a prohibitive processing time. We introduce Extremely Randomized Clustering Forests—ensembles of randomly created clustering trees—that are more accurate, much faster to train and test, and more robust to background clutter compared to state-of-the-art methods. Second, we propose an efficient image classification method that combines ERC-Forests and saliency maps very closely with image information sampling. For a given image, a classifier builds a saliency map online, which it uses for classification. We demonstrate speed and accuracy improvement in several state-of-the-art image classification tasks. Finally, we show that our ERC-Forests are used very successfully for learning distances between images of never-seen objects. Our algorithm learns the characteristic differences between local descriptors sampled from pairs of the “same ” or “different ” objects, quantizes these differences with ERC-Forests, and computes the similarity from this quantization. We show significant improvement over state-of-the-art competitive approaches. Index Terms—Randomized trees, image classification, object recognition, similarity measure. Ç 1
Nonparametric Scene Parsing via Label Transfer
, 2011
"... While there has been a lot of recent work on object recognition and image understanding, the focus has been on carefully establishing mathematical models for images, scenes, and objects. In this paper, we propose a novel, nonparametric approach for object recognition and scene parsing using a new t ..."
Abstract
-
Cited by 66 (3 self)
- Add to MetaCart
(Show Context)
While there has been a lot of recent work on object recognition and image understanding, the focus has been on carefully establishing mathematical models for images, scenes, and objects. In this paper, we propose a novel, nonparametric approach for object recognition and scene parsing using a new technology we name label transfer. For an input image, our system first retrieves its nearest neighbors from a large database containing fully annotated images. Then, the system establishes dense correspondences between the input image and each of the nearest neighbors using the dense SIFT flow algorithm [28], which aligns two images based on local image structures. Finally, based on the dense scene correspondences obtained from SIFT flow, our system warps the existing annotations and integrates multiple cues in a Markov random field framework to segment and recognize the query image. Promising experimental results have been achieved by our nonparametric scene parsing system on challenging databases. Compared to existing object recognition approaches that require training classifiers or appearance models for each object category, our system is easy to implement, has few parameters, and embeds contextual information naturally in the retrieval/alignment procedure.
Fast similarity search for learned metrics.
- IEEE Trans. Pattern Anal. Mach. Intell.,
, 2009
"... ..."
(Show Context)
Online Metric Learning and Fast Similarity Search
"... Metric learning algorithms can provide useful distance functions for a variety of domains, and recent work has shown good accuracy for problems where the learner can access all distance constraints at once. However, in many real applications, constraints are only available incrementally, thus necess ..."
Abstract
-
Cited by 58 (4 self)
- Add to MetaCart
Metric learning algorithms can provide useful distance functions for a variety of domains, and recent work has shown good accuracy for problems where the learner can access all distance constraints at once. However, in many real applications, constraints are only available incrementally, thus necessitating methods that can perform online updates to the learned metric. Existing online algorithms offer bounds on worst-case performance, but typically do not perform well in practice as compared to their offline counterparts. We present a new online metric learning algorithm that updates a learned Mahalanobis metric based on LogDet regularization and gradient descent. We prove theoretical worst-case performance bounds, and empirically compare the proposed method against existing online metric learning algorithms. To further boost the practicality of our approach, we develop an online locality-sensitive hashing scheme which leads to efficient updates to data structures used for fast approximate similarity search. We demonstrate our algorithm on multiple datasets and show that it outperforms relevant baselines. 1
Active Learning for Large Multi-class Problems
"... Scarcity and infeasibility of human supervision for large scale multi-class classification problems necessitates active learning. Unfortunately, existing active learning methods for multi-class problems are inherently binary methods and do not scale up to a large number of classes. In this paper, we ..."
Abstract
-
Cited by 53 (1 self)
- Add to MetaCart
(Show Context)
Scarcity and infeasibility of human supervision for large scale multi-class classification problems necessitates active learning. Unfortunately, existing active learning methods for multi-class problems are inherently binary methods and do not scale up to a large number of classes. In this paper, we introduce a probabilistic variant of the K-Nearest Neighbor method for classification that can be seamlessly used for active learning in multi-class scenarios. Given some labeled training data, our method learns an accurate metric/kernel function over the input space that can be used for classification and similarity search. Unlike existing metric/kernel learning methods, our scheme is highly scalable for classification problems and provides a natural notion of uncertainty over class labels. Further, we use this measure of uncertainty to actively sample training examples that maximize discriminating capabilities of the model. Experiments on benchmark datasets show that the proposed method learns appropriate distance metrics that lead to state-of-the-art performance for object categorization problems. Furthermore, our active learning method effectively samples training examples, resulting in significant accuracy gains over random sampling for multi-class problems involving a large number of classes. 1.
Sparse Distance Learning for Object Recognition Combining RGB and Depth Information
"... instance recognition in the context of RGB-D (depth) cameras. Motivated by local distance learning, where a novel view of an object is compared to individual views of previously seen objects, we define a view-to-object distance where a novel view is compared simultaneously to all views of a previous ..."
Abstract
-
Cited by 47 (1 self)
- Add to MetaCart
(Show Context)
instance recognition in the context of RGB-D (depth) cameras. Motivated by local distance learning, where a novel view of an object is compared to individual views of previously seen objects, we define a view-to-object distance where a novel view is compared simultaneously to all views of a previous object. This novel distance is based on a weighted combination of feature differences between views. We show, through jointly learning perview weights, that this measure leads to superior classification
Accurate image search using the contextual dissimilarity measure
- IEEE Trans. on Pattern Analysis and Machine Intell
, 2010
"... This paper introduces the contextual dissimilarity measure which significantly improves the accuracy of bag-of-features based image search. Our measure takes into account the local distribution of the vectors and iteratively estimates distance update terms in the spirit of Sinkhorn’s scaling algorit ..."
Abstract
-
Cited by 42 (5 self)
- Add to MetaCart
(Show Context)
This paper introduces the contextual dissimilarity measure which significantly improves the accuracy of bag-of-features based image search. Our measure takes into account the local distribution of the vectors and iteratively estimates distance update terms in the spirit of Sinkhorn’s scaling algorithm, thereby modifying the neighborhood structure. Experimental results show that our approach gives significantly better results than a standard distance and outperforms the state-of-the-art in terms of accuracy on the Nistér-Stewénius and Lola datasets. This paper also evaluates the impact of a large number of parameters, including the number of descriptors, the clustering method, the visual vocabulary size and the distance measure. The optimal parameter choice is shown to be quite context-dependent. In particular using a large number of descriptors is interesting only when using our dissimilarity measure. We have also evaluated two novel variants, multiple assignment and rank aggregation. They are shown to further improve accuracy, at the cost of higher memory usage and lower efficiency. 1
