An adaptive sampling scheme to efficiently train fully convolutional networks for semantic segmentation

Lorenz Berger*, Hyde Eoin, M. Jorge Cardoso, Sébastien Ourselin

*Corresponding author for this work

Research output: Chapter in Book/Report/Conference proceedingConference contributionpeer-review

18 Citations (Scopus)

Abstract

Deep convolutional neural networks (CNNs) have shown excellent performance in object recognition tasks and dense classification problems such as semantic segmentation. However, training deep neural networks on large and sparse datasets is still challenging and can require large amounts of computation and memory. In this work, we address the task of performing semantic segmentation on large data sets, such as three-dimensional medical images. We propose an adaptive sampling scheme that uses a-posterior error maps, generated throughout training, to focus sampling on difficult regions, resulting in improved learning. Our contribution is threefold: (1) We give a detailed description of the proposed sampling algorithm to speed up and improve learning performance on large images. (2) We propose a deep dual path CNN that captures information at fine and coarse scales, resulting in a network with a large field of view and high resolution outputs. (3) We show that our method is able to attain new state-of-the-art results on the VISCERAL Anatomy benchmark.

Original languageEnglish
Title of host publicationMedical Image Understanding and Analysis - 22nd Conference, Proceedings
PublisherSpringer Verlag
Pages277-286
Number of pages10
ISBN (Print)9783319959207
DOIs
Publication statusE-pub ahead of print - 21 Aug 2018
Event22nd Conference on Medical Image Understanding and Analysis, MIUA 2018 - Southampton, United Kingdom
Duration: 9 Jul 201811 Jul 2018

Publication series

NameCommunications in Computer and Information Science
Volume894
ISSN (Print)1865-0929

Conference

Conference22nd Conference on Medical Image Understanding and Analysis, MIUA 2018
Country/TerritoryUnited Kingdom
CitySouthampton
Period9/07/201811/07/2018

Fingerprint

Dive into the research topics of 'An adaptive sampling scheme to efficiently train fully convolutional networks for semantic segmentation'. Together they form a unique fingerprint.

Cite this