Rotation Invariant Local Binary Convolution Neural Networks

Abstract

Convolutional neural networks (CNNs) have achieved unprecedented successes in computer vision fields, but they remain challenged by the problem about how to effectively process the orientation transformation of objects with fewer parameters. In this paper, we propose a new convolutional module, local binary orientation module (LBoM), which takes advantages of both local binary convolutional and active rotating filters to effectively deal with the rotation variations with fewer parameters. LBoM can be naturally inserted to popular CNN models and upgrade them to be rotation invariant local binary CNNs (RI-LBCNNs). RI-LBCNNs can be learned with off-the-shelf optimization approaches in an end-to-end manner and fulfill image classification tasks. Extensive experiments on four benchmarks show that RI-LBCNNs can perform image classification with fewer network parameters and significantly outperform the baseline LBCNN when processing images with large rotation variations.