Multigrid Neural Architectures

11/23/2016
by   Tsung-Wei Ke, et al.
0

We propose a multigrid extension of convolutional neural networks (CNNs). Rather than manipulating representations living on a single spatial grid, our network layers operate across scale space, on a pyramid of grids. They consume multigrid inputs and produce multigrid outputs; convolutional filters themselves have both within-scale and cross-scale extent. This aspect is distinct from simple multiscale designs, which only process the input at different scales. Viewed in terms of information flow, a multigrid network passes messages across a spatial pyramid. As a consequence, receptive field size grows exponentially with depth, facilitating rapid integration of context. Most critically, multigrid structure enables networks to learn internal attention and dynamic routing mechanisms, and use them to accomplish tasks on which modern CNNs fail. Experiments demonstrate wide-ranging performance advantages of multigrid. On CIFAR and ImageNet classification tasks, flipping from a single grid to multigrid within the standard CNN paradigm improves accuracy, while being compute and parameter efficient. Multigrid is independent of other architectural choices; we show synergy in combination with residual connections. Multigrid yields dramatic improvement on a synthetic semantic segmentation dataset. Most strikingly, relatively shallow multigrid networks can learn to directly perform spatial transformation tasks, where, in contrast, current CNNs fail. Together, our results suggest that continuous evolution of features on a multigrid pyramid is a more powerful alternative to existing CNN designs on a flat grid.

READ FULL TEXT
research
03/16/2016

Understanding and Improving Convolutional Neural Networks via Concatenated Rectified Linear Units

Recently, convolutional neural networks (CNNs) have been used as a power...
research
03/03/2023

PPCR: Learning Pyramid Pixel Context Recalibration Module for Medical Image Classification

Spatial attention mechanism has been widely incorporated into deep convo...
research
11/08/2017

Revealing structure components of the retina by deep learning networks

Deep convolutional neural networks (CNNs) have demonstrated impressive p...
research
05/23/2021

Revisiting 2D Convolutional Neural Networks for Graph-based Applications

Graph convolutional networks (GCNs) are widely used in graph-based appli...
research
12/12/2022

A novel feature-scrambling approach reveals the capacity of convolutional neural networks to learn spatial relations

Convolutional neural networks (CNNs) are one of the most successful comp...
research
04/10/2023

Scale-Equivariant UNet for Histopathology Image Segmentation

Digital histopathology slides are scanned and viewed under different mag...
research
11/20/2018

Recurrent Iterative Gating Networks for Semantic Segmentation

In this paper, we present an approach for Recurrent Iterative Gating cal...

Please sign up or login with your details

Forgot password? Click here to reset