Results 1 - 10
of
125
Efficient Additive Kernels via Explicit Feature Maps
"... Maji and Berg [13] have recently introduced an explicit feature map approximating the intersection kernel. This enables efficient learning methods for linear kernels to be applied to the non-linear intersection kernel, expanding the applicability of this model to much larger problems. In this paper ..."
Abstract
-
Cited by 245 (9 self)
- Add to MetaCart
(Show Context)
Maji and Berg [13] have recently introduced an explicit feature map approximating the intersection kernel. This enables efficient learning methods for linear kernels to be applied to the non-linear intersection kernel, expanding the applicability of this model to much larger problems. In this paper we generalize this idea, and analyse a large family of additive kernels, called homogeneous, in a unified framework. The family includes the intersection, Hellinger’s, and χ2 kernels commonly employed in computer vision. Using the framework we are able to: (i) provide explicit feature maps for all homogeneous additive kernels along with closed form expression for all common kernels; (ii) derive corresponding approximate finitedimensional feature maps based on the Fourier sampling theorem; and (iii) quantify the extent of the approximation. We demonstrate that the approximations have indistinguishable performance from the full kernel on a number of standard datasets, yet greatly reduce the train/test times of SVM implementations. We show that the χ2 kernel, which has been found to yield the best performance in most applications, also has the most compact feature representation. Given these train/test advantages we are able to obtain a significant performance improvement over current state of the art results based on the intersection kernel. 1.
Discriminative models for multi-class object layout
"... Many state-of-the-art approaches for object recognition reduce the problem to a 0-1 classification task. Such reductions allow one to leverage sophisticated classifiers for learning. These models are typically trained independently for each class using positive and negative examples cropped from ima ..."
Abstract
-
Cited by 197 (6 self)
- Add to MetaCart
(Show Context)
Many state-of-the-art approaches for object recognition reduce the problem to a 0-1 classification task. Such reductions allow one to leverage sophisticated classifiers for learning. These models are typically trained independently for each class using positive and negative examples cropped from images. At test-time, various post-processing heuristics such as non-maxima suppression (NMS) are required to reconcile multiple detections within and between different classes for each image. Though crucial to good performance on benchmarks, this post-processing is usually defined heuristically. We introduce a unified model for multi-class object recognition that casts the problem as a structured prediction task. Rather than predicting a binary label for each image
Class Segmentation and Object Localization with Superpixel Neighborhoods
"... We propose a method to identify and localize object classes in images. Instead of operating at the pixel level, we advocate the use of superpixels as the basic unit of a class segmentation or pixel localization scheme. To this end, we construct a classifier on the histogram of local features found i ..."
Abstract
-
Cited by 123 (4 self)
- Add to MetaCart
(Show Context)
We propose a method to identify and localize object classes in images. Instead of operating at the pixel level, we advocate the use of superpixels as the basic unit of a class segmentation or pixel localization scheme. To this end, we construct a classifier on the histogram of local features found in each superpixel. We regularize this classifier by aggregating histograms in the neighborhood of each superpixel and then refine our results further by using the classifier in a conditional random field operating on the superpixel graph. Our proposed method exceeds the previously published state-of-the-art on two challenging datasets: Graz-02 and the PASCAL VOC 2007 Segmentation
Struck: Structured Output Tracking with Kernels
"... Adaptive tracking-by-detection methods are widely used in computer vision for tracking arbitrary objects. Current approaches treat the tracking problem as a classification task and use online learning techniques to update the object model. However, for these updates to happen one needs to convert th ..."
Abstract
-
Cited by 111 (4 self)
- Add to MetaCart
(Show Context)
Adaptive tracking-by-detection methods are widely used in computer vision for tracking arbitrary objects. Current approaches treat the tracking problem as a classification task and use online learning techniques to update the object model. However, for these updates to happen one needs to convert the estimated object position into a set of labelled training examples, and it is not clear how best to perform this intermediate step. Furthermore, the objective for the classifier (label prediction) is not explicitly coupled to the objective for the tracker (accurate estimation of object position). In this paper, we present a framework for adaptive visual object tracking based on structured output prediction. By explicitly allowing the output space to express the needs of the tracker, we are able to avoid the need for an intermediate classification step. Our method uses a kernelized structured output support vector machine (SVM), which is learned online to provide adaptive tracking. To allow for real-time application, we introduce a budgeting mechanism which prevents the unbounded growth in the number of support vectors which would otherwise occur during tracking. Experimentally, we show that our algorithm is able to outperform state-of-the-art trackers on various benchmark videos. Additionally, we show that we can easily incorporate additional features and kernels into our framework, which results in increased performance. 1.
Latent Hierarchical Structural Learning for Object Detection
, 2010
"... We present a latent hierarchical structural learning method for object detection. An object is represented by a mixture of hierarchical tree models where the nodes represent object parts. The nodes can move spatially to allow both local and global shape deformations. The models can be trained discri ..."
Abstract
-
Cited by 87 (7 self)
- Add to MetaCart
We present a latent hierarchical structural learning method for object detection. An object is represented by a mixture of hierarchical tree models where the nodes represent object parts. The nodes can move spatially to allow both local and global shape deformations. The models can be trained discriminatively using latent structural SVM learning, where the latent variables are the node positions and the mixture component. But current learning methods are slow, due to the large number of parameters and latent variables, and have been restricted to hierarchies with two layers. In this paper we describe an incremental concaveconvex procedure (iCCCP) which allows us to learn both two and three layer models efficiently. We show that iCCCP leads to a simple training algorithm which avoids complex multi-stage layer-wise training, careful part selection, and achieves good performance without requiring elaborate initialization. We perform object detection using our learnt models and obtain performance comparable with state-ofthe-art methods when evaluated on challenging public PAS-CAL datasets. We demonstrate the advantages of three layer hierarchies – outperforming Felzenszwalb et al.’s two layer models on all 20 classes.
C.: Structured Forests for Fast Edge Detection
"... Edge detection is a critical component of many vision systems, including object detectors and image segmentation algorithms. Patches of edges exhibit well-known forms of local structure, such as straight lines or T-junctions. In this paper we take advantage of the structure present in local image pa ..."
Abstract
-
Cited by 66 (1 self)
- Add to MetaCart
(Show Context)
Edge detection is a critical component of many vision systems, including object detectors and image segmentation algorithms. Patches of edges exhibit well-known forms of local structure, such as straight lines or T-junctions. In this paper we take advantage of the structure present in local image patches to learn both an accurate and computation-ally efficient edge detector. We formulate the problem of predicting local edge masks in a structured learning frame-work applied to random decision forests. Our novel ap-proach to learning decision trees robustly maps the struc-tured labels to a discrete space on which standard infor-mation gain measures may be evaluated. The result is an approach that obtains realtime performance that is orders of magnitude faster than many competing state-of-the-art approaches, while also achieving state-of-the-art edge de-tection results on the BSDS500 Segmentation dataset and NYU Depth dataset. Finally, we show the potential of our approach as a general purpose edge detector by showing our learned edge models generalize well across datasets. 1.
Weakly supervised discriminative localization and classification: a joint learning process
, 2009
"... ..."
Object detection with grammar models
- In NIPS
, 2011
"... Compositional models provide an elegant formalism for representing the visual appearance of highly variable objects. While such models are appealing from a theoretical point of view, it has been difficult to demonstrate that they lead to performance advantages on challenging datasets. Here we develo ..."
Abstract
-
Cited by 59 (4 self)
- Add to MetaCart
(Show Context)
Compositional models provide an elegant formalism for representing the visual appearance of highly variable objects. While such models are appealing from a theoretical point of view, it has been difficult to demonstrate that they lead to performance advantages on challenging datasets. Here we develop a grammar model for person detection and show that it outperforms previous high-performance systems on the PASCAL benchmark. Our model represents people using a hierarchy of deformable parts, variable structure and an explicit model of occlusion for partially visible objects. To train the model, we introduce a new discriminative framework for learning structured prediction models from weakly-labeled data. 1
Object Recognition as Ranking Holistic Figure-Ground Hypotheses
- In CVPR, 2010. 7
"... We present an approach to visual object-class recognition and segmentation based on a pipeline that combines multiple, holistic figure-ground hypotheses generated in a bottom-up, object independent process. Decisions are performed based on continuous estimates of the spatial overlap between image se ..."
Abstract
-
Cited by 55 (13 self)
- Add to MetaCart
(Show Context)
We present an approach to visual object-class recognition and segmentation based on a pipeline that combines multiple, holistic figure-ground hypotheses generated in a bottom-up, object independent process. Decisions are performed based on continuous estimates of the spatial overlap between image segment hypotheses and each putative class. We differ from existing approaches not only in our seemingly unreasonable assumption that good object-level segments can be obtained in a feed-forward fashion, but also in framing recognition as a regression problem. Instead of focusing on a one-vs-all winning margin that can scramble ordering inside the non-maximum (non-winning) set, learning produces a globally consistent ranking with close ties to segment quality, hence to the extent entire object or part hypotheses spatially overlap with the ground truth. We demonstrate results beyond the current state of the art for image classification, object detection and semantic segmentation, in a number of challenging datasets including Caltech-101, ETHZ-Shape and PASCAL VOC 2009. 1.
P.: Cascaded pose regression
- In: IEEE Conference on Computer Vision and Pattern Recognition
, 2010
"... We present a fast and accurate algorithm for comput-ing the 2D pose of objects in images called cascaded pose regression (CPR). CPR progressively refines a loosely spec-ified initial guess, where each refinement is carried out by a different regressor. Each regressor performs simple image measuremen ..."
Abstract
-
Cited by 50 (2 self)
- Add to MetaCart
(Show Context)
We present a fast and accurate algorithm for comput-ing the 2D pose of objects in images called cascaded pose regression (CPR). CPR progressively refines a loosely spec-ified initial guess, where each refinement is carried out by a different regressor. Each regressor performs simple image measurements that are dependent on the output of the pre-vious regressors; the entire system is automatically learned from human annotated training examples. CPR is not re-stricted to rigid transformations: ‘pose ’ is any parameter-ized variation of the object’s appearance such as the de-grees of freedom of deformable and articulated objects. We compare CPR against both standard regression techniques and human performance (computed from redundant human annotations). Experiments on three diverse datasets (mice, faces, fish) suggest CPR is fast (2-3ms per pose estimate), accurate (approaching human performance), and easy to train from small amounts of labeled data. 1.
