Global information is essential for dense prediction problems, whose goal is to compute adiscrete or continuous label for each pixel in the images. Traditional convolutional layers in neural networks, initially designed for image classification, are restrictive in these problems since the filter size limits their receptive fields. In this work, we propose to replace any traditional convolutional layer with an autoregressivemoving-average (ARMA) layer,anovelmodule with an adjustable receptive field controlled by the learnable autoregressive coefficients.

We study characteristics of receptive fields of units in deep convolutional networks.

In other words, we fit an under-parameterized "student" network with

"Green", "Orange", and "Blue" denote the results from models trained on