Class-specific mid-level feature learning with the discriminative group-wise Beta-Bernoulli process restricted Boltzmann machiines
SCIE
SCOPUS
- Title
- Class-specific mid-level feature learning with the discriminative group-wise Beta-Bernoulli process restricted Boltzmann machiines
- Authors
- Lee, Hui-Jin; Hong, Ki-Sang
- Date Issued
- 2016-09-01
- Publisher
- ELSEVIER SCIENCE BV
- Abstract
- In this paper, we propose a Discriminative Group-wise Beta-Bernoulli process restricted Boltzmann machine (DG-BBP RBM), an approach to learn class-specific mid-level features based on the Beta-Bernoulli process restricted Boltzmann machine (BBP RBM), which imposes class-specific sparsity that has discriminative characteristics across different classes to eliminate redundancy among extracted features. With this method, we learn mid-level features that are characteristic of each class and that are shared rarely or not at all with other classes (i.e., are discriminative of that class). In experiments on image classification tasks, our DG-BBP RBM showed much better results than did BBP RBM and related methods and could capture semantic attributes that can be used to discriminate between classes.
- Keywords
- Mid-level feature; Restricted Boltzman machine; Beta-Bernoulli process; Deep belief networks; Discriminative group-wise sparsity; Image classification
- URI
- https://oasis.postech.ac.kr/handle/2014.oak/50125
- DOI
- 10.1016/j.patrec.2016.05.011
- ISSN
- 0167-8655
- Article Type
- Article
- Citation
- PATTERN RECOGNITION LETTERS, vol. 80, no. 1, page. 8 - 14, 2016-09-01
- Files in This Item:
- There are no files associated with this item.
Items in DSpace are protected by copyright, with all rights reserved, unless otherwise indicated.