CyCNN: A Rotation Invariant CNN using Polar Mapping and Cylindrical Convolution Layers

1 code implementation • 21 Jul 2020 • Jinpyo Kim, Wooekun Jung, Hyungmo Kim, Jaejin Lee

Deep Convolutional Neural Networks (CNNs) are empirically known to be invariant to moderate translation but not to rotation in image classification.

Classification Data Augmentation +4