Exploring context with deep structured models for semantic segmentation
Date
2016
Authors
Lin, G.
Shen, C.
Hengel, A.
Reid, I.
Editors
Advisors
Journal Title
Journal ISSN
Volume Title
Type:
Journal article
Citation
IEEE Transactions on Pattern Analysis and Machine Intelligence, 2016; 40(6):1352-1366
Statement of Responsibility
Guosheng Lin, Chunhua Shen, Anton van den Hengel, and Ian Reid
Conference Name
Abstract
We propose an approach for exploiting contextual information in semantic image segmentation, and particularly investigate the use of patch-patch context and patch-background context in deep CNNs. We formulate deep structured models by combining CNNs and Conditional Random Fields (CRFs) for learning the patch-patch context between image regions. Specifically, we formulate CNN-based pairwise potential functions to capture semantic correlations between neighboring patches. Efficient piecewise training of the proposed deep structured model is then applied in order to avoid repeated expensive CRF inference during the course of back propagation. For capturing the patch-background context, we show that a network design with traditional multi-scale image inputs and sliding pyramid pooling is very effective for improving performance.We perform comprehensive evaluation of the proposed method.We achieve new state-of-the-art performance on a number of challenging semantic segmentation datasets.
School/Discipline
Dissertation Note
Provenance
Description
Date of publication 25 May 2017; date of current version 14 May 2018.
Access Status
Rights
© 2017 IEEE