Learnable Polyphase Sampling for Shift Invariant and Equivariant Convolutional Networks Renan A. Rojas-Gomez T eck-Yian Lim Alexander G. Schwing Minh N. Do Raymond A. Y eh

LPS can be trained end-to-end from data and generalizes existing handcrafted downsampling layers. It is widely applicable as it can be integrated into any convolutional network by replacing down/upsampling layers. We evaluate LPS on image classification and semantic segmentation. Experiments show that LPS is on-par with or outperforms existing methods in both performance and shift consistency. For the first time, we achieve true shift-equivariance on semantic segmentation (P ASCAL VOC), i.e., 100% shift consistency, outperforming baselines by an absolute 3.3%.