Foundations and Trends® in Computer Graphics and Vision
Hybrid Generative-Discriminative Visual Categorization
International Journal of Computer Vision
Efficient Learning of Relational Object Class Models
International Journal of Computer Vision
Distinctive and compact features
Image and Vision Computing
Two-Step Tracking by Parts Using Multiple Kernels
Proceedings of the 2006 conference on Artificial Intelligence Research and Development
Object classification by fusing SVMs and Gaussian mixtures
Pattern Recognition
Aspects of semi-supervised and active learning in conditional random fields
ECML PKDD'11 Proceedings of the 2011 European conference on Machine learning and knowledge discovery in databases - Volume Part III
Pedestrian detection based on kernel discriminative sparse representation
Transactions on Edutainment IX
| Hi-index | 0.00 |
Here we explore a discriminative learning method on underlying generative models for the purpose of discriminating between object categories. Visual recognition algorithms learn models from a set of training examples. Generative models learn their representations by considering data from a single class. Generative models are popular in computer vision for many reasons, including their ability to elegantly incorporate prior knowledge and to handle correspondences between object parts and detected features. However, generative models are often inferior to discriminative models during classification tasks. We study a discriminative approach to learning object categories which maintains the representational power of generative learning, but trains the generative models in a discriminative manner. The discriminatively trained models perform better during classification tasks as a result of selecting discriminative sets of features. We conclude by proposing a multi-class object recognition system which initially trains object classes in a generative manner, identifies subsets of similar classes with high confusion, and finally trains models for these subsets in a discriminative manner to realize gains in classification performance.