21 July 2017 Classifying images using restricted Boltzmann machines and convolutional neural networks
Author Affiliations +
Proceedings Volume 10420, Ninth International Conference on Digital Image Processing (ICDIP 2017); 104202U (2017) https://doi.org/10.1117/12.2281994
Event: Ninth International Conference on Digital Image Processing (ICDIP 2017), 2017, Hong Kong, China
Abstract
To improve the feature recognition ability of deep model transfer learning, we propose a hybrid deep transfer learning method for image classification based on restricted Boltzmann machines (RBM) and convolutional neural networks (CNNs). It integrates learning abilities of two models, which conducts subject classification by exacting structural higher-order statistics features of images. While the method transfers the trained convolutional neural networks to the target datasets, fully-connected layers can be replaced by restricted Boltzmann machine layers; then the restricted Boltzmann machine layers and Softmax classifier are retrained, and BP neural network can be used to fine-tuned the hybrid model. The restricted Boltzmann machine layers has not only fully integrated the whole feature maps, but also learns the statistical features of target datasets in the view of the biggest logarithmic likelihood, thus removing the effects caused by the content differences between datasets. The experimental results show that the proposed method has improved the accuracy of image classification, outperforming other methods on Pascal VOC2007 and Caltech101 datasets.
© (2017) COPYRIGHT Society of Photo-Optical Instrumentation Engineers (SPIE). Downloading of the abstract is permitted for personal use only.
Zhijun Zhao, Zhijun Zhao, Tongde Xu, Tongde Xu, Chenyu Dai, Chenyu Dai, } "Classifying images using restricted Boltzmann machines and convolutional neural networks", Proc. SPIE 10420, Ninth International Conference on Digital Image Processing (ICDIP 2017), 104202U (21 July 2017); doi: 10.1117/12.2281994; https://doi.org/10.1117/12.2281994
PROCEEDINGS
9 PAGES


SHARE
RELATED CONTENT

Deep ear biometrics
Proceedings of SPIE (May 08 2018)
Neural network for invariant recognition
Proceedings of SPIE (December 26 1996)
Remote sensing as a support for urban and land use...
Proceedings of SPIE (September 23 2002)

Back to Top