Harmonic Networks: Deep Translation and Rotation Equivariance
Harmonic Networks: Deep Translation and Rotation Equivariance
Translating or rotating an input image should not affect the results of many computer vision tasks. Convolutional neural networks (CNNs) are already translation equivariant: input image translations produce proportionate feature map translations. This is not the case for rotations. Global rotation equivariance is typically sought through data augmentation, but patch-wise …