Skip to main content
placeholder image

Efficient Pre-Designed Convolutional Front-End for Deep Learning

Conference Paper


Abstract


  • 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


  • Baali, H., & Bouzerdoum, A. (2019). Efficient Pre-Designed Convolutional Front-End for Deep Learning. In IEEE International Workshop on Machine Learning for Signal Processing, MLSP Vol. 2019-October. doi:10.1109/MLSP.2019.8918881

Scopus Eid


  • 2-s2.0-85077709737

Web Of Science Accession Number


Volume


  • 2019-October

Abstract


  • 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


  • Baali, H., & Bouzerdoum, A. (2019). Efficient Pre-Designed Convolutional Front-End for Deep Learning. In IEEE International Workshop on Machine Learning for Signal Processing, MLSP Vol. 2019-October. doi:10.1109/MLSP.2019.8918881

Scopus Eid


  • 2-s2.0-85077709737

Web Of Science Accession Number


Volume


  • 2019-October