Please use this identifier to cite or link to this item: http://hdl.handle.net/2440/105526
Citations
Scopus Web of Science® Altmetric
?
?
Type: Conference paper
Title: Efficient piecewise training of deep structured models for semantic segmentation
Author: Lin, G.
Shen, C.
Van Den Hengel, A.
Reid, I.
Citation: Proceedings of the 29th IEEE Conference on Computer Vision and Pattern Recognition (CVPR 2016), 2016 / vol.2016-December, pp.3194-3203
Publisher: IEEE
Issue Date: 2016
Series/Report no.: IEEE Conference on Computer Vision and Pattern Recognition
ISBN: 9781467388511
ISSN: 1063-6919
Conference Name: 29th IEEE Conference on Computer Vision and Pattern Recognition (CVPR 2016) (26 Jun 2016 - 01 Jul 2016 : Las Vegas, NV)
Statement of
Responsibility: 
Guosheng Lin, Chunhua Shen, Anton van den Hengel, Ian Reid
Abstract: Recent advances in semantic image segmentation have mostly been achieved by training deep convolutional neural networks (CNNs). We show how to improve semantic segmentation through the use of contextual information, specifically, we explore 'patch-patch' context between image regions, and 'patch-background' context. For learning from the patch-patch context, we formulate Conditional Random Fields (CRFs) with CNN-based pairwise potential functions to capture semantic correlations between neighboring patches. Efficient piecewise training of the proposed deep structured model is then applied to avoid repeated expensive CRF inference for back propagation. For capturing the patch-background context, we show that a network design with traditional multi-scale image input and sliding pyramid pooling is effective for improving performance. Our experimental results set new state-of-the-art performance on a number of popular semantic segmentation datasets, including NYUDv2, PASCAL VOC 2012, PASCAL-Context, and SIFT-flow. In particular, we achieve an intersection-overunion score of 78:0 on the challenging PASCAL VOC 2012 dataset.
Rights: © 2016 IEEE
RMID: 0030056400
DOI: 10.1109/CVPR.2016.348
Grant ID: http://purl.org/au-research/grants/arc/CE140100016
http://purl.org/au-research/grants/arc/FT120100969
http://purl.org/au-research/grants/arc/FL130100102
Appears in Collections:Computer Science publications

Files in This Item:
File Description SizeFormat 
RA_hdl_105526.pdfRestricted Access412.76 kBAdobe PDFView/Open


Items in DSpace are protected by copyright, with all rights reserved, unless otherwise indicated.