Back to Search
Start Over
Regularized Deep Belief Network for Image Attribute Detection.
- Source :
- IEEE Transactions on Circuits & Systems for Video Technology; Jul2017, Vol. 27 Issue 7, p1464-1477, 14p
- Publication Year :
- 2017
-
Abstract
- In general, an image attribute is a human-nameable visual property that has a semantic connotation. Appropriate modeling of the intrinsic contextual correlations among attributes plays a fundamental role in attribute detection. In this paper, we consider image attribute detection from the perspective of regularized deep learning. In particular, we propose a regularized deep belief network (rDBN) to perform the image attribute detection task, which is composed of two parts: 1) a detection DBN (dDBN) that models the joint distribution of images and their corresponding attributes, which acts as an attribute detector and 2) a contextual restricted Boltzmann machine that explicitly models the correlations among attributes acting as a regularizer that restraints the output detection result given by the dDBN to meet the contextual prior of attributes. Furthermore, we propose an efficient fine-tuning scheme that can further optimize the performance of the dDBN by backpropagation. Experimental results show that the proposed rDBN obtains improvements over the state-of-the-art methods for attribute detection on the benchmark data sets. [ABSTRACT FROM PUBLISHER]
Details
- Language :
- English
- ISSN :
- 10518215
- Volume :
- 27
- Issue :
- 7
- Database :
- Complementary Index
- Journal :
- IEEE Transactions on Circuits & Systems for Video Technology
- Publication Type :
- Academic Journal
- Accession number :
- 124027454
- Full Text :
- https://doi.org/10.1109/TCSVT.2016.2539604