Truly shift-equivariant convolutional neural networks with adaptive polyphase upsampling

05/09/2021
by   Anadi Chaman, et al.
0

Convolutional neural networks lack shift equivariance due to the presence of downsampling layers. In image classification, adaptive polyphase downsampling (APS-D) was recently proposed to make CNNs perfectly shift invariant. However, in networks used for image reconstruction tasks, it can not by itself restore shift equivariance. We address this problem by proposing adaptive polyphase upsampling (APS-U), a non-linear extension of conventional upsampling, which allows CNNs to exhibit perfect shift equivariance. With MRI and CT reconstruction experiments, we show that networks containing APS-D/U layers exhibit state of the art equivariance performance without sacrificing on image reconstruction quality. In addition, unlike prior methods like data augmentation and anti-aliasing, the gains in equivariance obtained from APS-D/U also extend to images outside the training distribution.

READ FULL TEXT

page 1

page 2

page 3

page 4

research
11/28/2020

Truly shift-invariant convolutional neural networks

Thanks to the use of convolution and pooling layers, convolutional neura...
research
12/14/2016

Astronomical image reconstruction with convolutional neural networks

State of the art methods in astronomical image reconstruction rely on th...
research
03/14/2023

Alias-Free Convnets: Fractional Shift Invariance via Polynomial Activations

Although CNNs are believed to be invariant to translations, recent works...
research
09/24/2021

Frequency Pooling: Shift-Equivalent and Anti-Aliasing Downsampling

Convolution utilizes a shift-equivalent prior of images, thus leading to...
research
02/07/2022

A comprehensive benchmark analysis for sand dust image reconstruction

Numerous sand dust image enhancement algorithms have been proposed in re...
research
10/14/2022

Learnable Polyphase Sampling for Shift Invariant and Equivariant Convolutional Networks

We propose learnable polyphase sampling (LPS), a pair of learnable down/...
research
01/18/2019

Adapting Convolutional Neural Networks for Geographical Domain Shift

We present the winning solution for the Inclusive Images Competition org...

Please sign up or login with your details

Forgot password? Click here to reset