公开(公告)号：US11048935B2

公开(公告)日：2021-06-29

申请号：US16258994

申请日：2019-01-28

Applicant: Adobe Inc.

Inventor： Richard Zhang

IPC: G06K9/00 ,  G06N3/08 ,  G06N20/10 ,  G06T5/00

Abstract: The present disclosure relates to systems, methods, and non-transitory computer readable media for generating shift-resilient neural network outputs based on utilizing a dense pooling layer, a low-pass filter layer, and a downsampling layer of a neural network. For example, the disclosed systems can generate a pooled feature map utilizing a dense pooling layer to densely pool feature values extracted from an input. The disclosed systems can further apply a low-pass filter to the pooled feature map to generate a shift-adaptive feature map. In addition, the disclosed systems can downsample the shift-adaptive feature map utilizing a downsampling layer. Based on the downsampled, shift-adaptive feature map, the disclosed systems can generate shift-resilient neural network outputs such as digital image classifications.