Home 9 Publications 9 An Optimization for Convolutional Network Layers Using the Viola-Jones Framework and Ternary Weight Networks

An Optimization for Convolutional Network Layers Using the Viola-Jones Framework and Ternary Weight Networks

Author: R. Agombar, C. Bauckhage, M. Lübbering, R. Sifa
Journal: LION 2021: Learning and Intelligent Optimization
Year: 2021

Citation information

R. Agombar, C. Bauckhage, M. Lübbering, R. Sifa,
LION 2021: Learning and Intelligent Optimization,
2021,
1-6,
Springer, Cham,
https://doi.org/10.1007/978-3-030-92121-7_1

Neural networks have the potential to be extremely powerful for computer vision related tasks, but can be computationally expensive. Classical methods, by comparison, tend to be relatively light weight, albeit not as powerful. In this paper, we propose a method of combining parts from a classical system, called the Viola-Jones Object Detection Framework, with a modern ternary neural network to improve the efficiency of a convolutional neural net by replacing convolutional filters with a set of custom ones inspired by the framework. This reduces the number of operations needed for computing feature values with negligible effects on overall accuracy, allowing for a more optimized network.