Multi-class object layout with unsupervised image classification and object localization

Authors:
Ser-Nam Lim;Gianfranco Doretto;Jens Rittscher
Affiliations:
Computer Vision Lab, GE Global Research, Niskayuna, NY;Dept. of CS & EE, West Virginia University, Morgantown, WV;Computer Vision Lab, GE Global Research, Niskayuna, NY
Venue:
ISVC'11 Proceedings of the 7th international conference on Advances in visual computing - Volume Part I
Year:
2011

Citing 15
Cited 0

Conditional Random Fields: Probabilistic Models for Segmenting and Labeling Sequence Data

ICML '01 Proceedings of the Eighteenth International Conference on Machine Learning
Robust Real-Time Face Detection

International Journal of Computer Vision
Distinctive Image Features from Scale-Invariant Keypoints

International Journal of Computer Vision
Histograms of Oriented Gradients for Human Detection

CVPR '05 Proceedings of the 2005 IEEE Computer Society Conference on Computer Vision and Pattern Recognition (CVPR'05) - Volume 1 - Volume 01
Discriminative Random Fields

International Journal of Computer Vision
Efficient Belief Propagation for Early Vision

International Journal of Computer Vision
Scalable Recognition with a Vocabulary Tree

CVPR '06 Proceedings of the 2006 IEEE Computer Society Conference on Computer Vision and Pattern Recognition - Volume 2
Animals on the Web

CVPR '06 Proceedings of the 2006 IEEE Computer Society Conference on Computer Vision and Pattern Recognition - Volume 2
Local Features and Kernels for Classification of Texture and Object Categories: A Comprehensive Study

International Journal of Computer Vision
Universal and Adapted Vocabularies for Generic Visual Categorization

IEEE Transactions on Pattern Analysis and Machine Intelligence
Object Class Recognition and Localization Using Sparse Features with Limited Receptive Fields

International Journal of Computer Vision
Learning Spatial Context: Using Stuff to Find Things

ECCV '08 Proceedings of the 10th European Conference on Computer Vision: Part I
Object Detection with Discriminatively Trained Part-Based Models

IEEE Transactions on Pattern Analysis and Machine Intelligence
What, where and how many? combining object detectors and CRFs

ECCV'10 Proceedings of the 11th European conference on Computer vision: Part IV
Detecting people using mutually consistent poselet activations

ECCV'10 Proceedings of the 11th European conference on Computer vision: Part VI

Quantified Score

Hi-index	0.00

Visualization

Abstract

Recognizing the presence of object classes in an image, or image classification, has become an increasingly important topic of interest. Equally important, however, is also the capability to locate these object classes in the image. We consider in this paper an approach to these two related problems with the primary goal of minimizing the training requirements so as to allow for ease of adding new object classes, as opposed to approaches that favor training a suite of object-specific classifiers. To this end, we provide the analysis of an exemplar-based approach that leverages unsupervised clustering for classification purpose, and sliding window matching for localization. While such exemplar based approach by itself is brittle towards intraclass and viewpoint variations, we achieve robustness by introducing a novel Conditional Random Field model that facilitates a straightforward accept/reject decision of the localized object classes. Performance of our approach on the PASCAL Visual Object Challenge 2007 dataset demonstrates its efficacy.