The Importance of Skip Connections in Biomedical Image Segmentation

In this paper, we study the influence of both long and short skip connections on Fully Convolutional Networks (FCN) for biomedical image segmentation. In standard FCNs, only long skip connections are used to skip features from the contracting path to the expanding path in order to recover spatial in...

Full description

Saved in:
Bibliographic Details
Published inDeep Learning and Data Labeling for Medical Applications Vol. 10008; pp. 179 - 187
Main Authors Drozdzal, Michal, Vorontsov, Eugene, Chartrand, Gabriel, Kadoury, Samuel, Pal, Chris
Format Book Chapter
LanguageEnglish
Published Switzerland Springer International Publishing AG 2016
Springer International Publishing
SeriesLecture Notes in Computer Science
Subjects
Artificial intelligence
FCN
Image processing
Pattern recognition
ResNet
Semantic segmentation
Skip connections
Online AccessGet full text

Cover

More Information
Summary:In this paper, we study the influence of both long and short skip connections on Fully Convolutional Networks (FCN) for biomedical image segmentation. In standard FCNs, only long skip connections are used to skip features from the contracting path to the expanding path in order to recover spatial information lost during downsampling. We extend FCNs by adding short skip connections, that are similar to the ones introduced in residual networks, in order to build very deep FCNs (of hundreds of layers). A review of the gradient flow confirms that for a very deep FCN it is beneficial to have both long and short skip connections. Finally, we show that a very deep FCN can achieve near-to-state-of-the-art results on the EM dataset without any further post-processing.
Bibliography:M. Drozdzal and E. Vorontsov—Equal contribution.
ISBN:9783319469751
3319469754
ISSN:0302-9743
1611-3349
DOI:10.1007/978-3-319-46976-8_19