AI RESEARCH
Accurate Shift Invariant Convolutional Neural Networks Using Gaussian-Hermite Moments
arXiv CS.CV
•
ArXi:2603.17098v1 Announce Type: new The convolutional neural networks (CNNs) are not inherently shift invariant or equivariant. The downsampling operation, used in CNNs, is one of the key reasons which breaks the shift invariant property of a CNN. Conversely, downsampling operation is important to improve computational efficiency and increase the area of the receptive field for contextual information. In this work, we propose Gaussian-Hermite Sampling (GHS), a novel downsampling strategy designed to achieve accurate shift invariance.