Efficient Smoothing of Dilated Convolutions for Image Segmentation

by   Thomas Ziegler, et al.
ETH Zurich

Dilated Convolutions have been shown to be highly useful for the task of image segmentation. By introducing gaps into convolutional filters, they enable the use of larger receptive fields without increasing the original kernel size. Even though this allows for the inexpensive capturing of features at different scales, the structure of the dilated convolutional filter leads to a loss of information. We hypothesise that inexpensive modifications to Dilated Convolutional Neural Networks, such as additional averaging layers, could overcome this limitation. In this project we test this hypothesis by evaluating the effect of these modifications for a state-of-the art image segmentation system and compare them to existing approaches with the same objective. Our experiments show that our proposed methods improve the performance of dilated convolutions for image segmentation. Crucially, our modifications achieve these results at a much lower computational cost than previous smoothing approaches.


page 2

page 4


Smoothed Dilated Convolutions for Improved Dense Prediction

Dilated convolutions, also known as atrous convolutions, have been widel...

Adaptive Convolutions with Per-pixel Dynamic Filter Atom

Applying feature dependent network weights have been proved to be effect...

Gaussian Dynamic Convolution for Efficient Single-Image Segmentation

Interactive single-image segmentation is ubiquitous in the scientific an...

Hyper-Convolution Networks for Biomedical Image Segmentation

The convolution operation is a central building block of neural network ...

Dilated Convolutions with Lateral Inhibitions for Semantic Image Segmentation

Dilated convolutions are widely used in deep semantic segmentation model...

1M parameters are enough? A lightweight CNN-based model for medical image segmentation

Convolutional neural networks (CNNs) and Transformer-based models are be...

DeepLab: Semantic Image Segmentation with Deep Convolutional Nets, Atrous Convolution, and Fully Connected CRFs

In this work we address the task of semantic image segmentation with Dee...

Please sign up or login with your details

Forgot password? Click here to reset