Skip to main content
placeholder image

Efficient Pre-Designed Convolutional Front-End for Deep Learning

Conference Paper


Abstract


  • © 2019 IEEE. This paper introduces a hierarchical learning paradigm based on a predesigned directional filter bank front-end analogous to the energy model for complex cells. The filter bank front-end is designed to extract common primitive features such as orientations and edges. Each energy response is subjected to a shunting inhibition operator to enhance contrast and reduce the effects of illumination variations. This is followed by a divisive-normalization, which bounds the responses of the feature maps. The normalized responses are then propagated through a two-layer convolutional neural network (CNN) back-end for classification. The efficiency of the proposed approach is demonstrated using the CIFAR-10 dataset, and its performance is compared against that of the DTCWT ScaterNet front-end.

Publication Date


  • 2019

Citation


  • H. Baali & A. Bouzerdoum, "Efficient Pre-Designed Convolutional Front-End for Deep Learning," in IEEE International Workshop on Machine Learning for Signal Processing, MLSP, 2019,

Scopus Eid


  • 2-s2.0-85077709737

Ro Metadata Url


  • http://ro.uow.edu.au/eispapers1/3597

Abstract


  • © 2019 IEEE. This paper introduces a hierarchical learning paradigm based on a predesigned directional filter bank front-end analogous to the energy model for complex cells. The filter bank front-end is designed to extract common primitive features such as orientations and edges. Each energy response is subjected to a shunting inhibition operator to enhance contrast and reduce the effects of illumination variations. This is followed by a divisive-normalization, which bounds the responses of the feature maps. The normalized responses are then propagated through a two-layer convolutional neural network (CNN) back-end for classification. The efficiency of the proposed approach is demonstrated using the CIFAR-10 dataset, and its performance is compared against that of the DTCWT ScaterNet front-end.

Publication Date


  • 2019

Citation


  • H. Baali & A. Bouzerdoum, "Efficient Pre-Designed Convolutional Front-End for Deep Learning," in IEEE International Workshop on Machine Learning for Signal Processing, MLSP, 2019,

Scopus Eid


  • 2-s2.0-85077709737

Ro Metadata Url


  • http://ro.uow.edu.au/eispapers1/3597