Please use this identifier to cite or link to this item:
Title: Exploring context with deep structured models for semantic segmentation
Authors: van den Hengel, Anton
Lin, Guosheng
Shen, Chunhua
Reid, Ian
Keywords: Convolutional Neural Networks
DRNTU::Engineering::Computer science and engineering
Semantic Segmentation
Issue Date: 2017
Source: Lin, G., Shen, C., van den Hengel, A., & Reid, I. (2018). Exploring context with deep structured models for semantic segmentation. IEEE Transactions on Pattern Analysis and Machine Intelligence, 40(6), 1352-1366. doi:10.1109/TPAMI.2017.2708714
Series/Report no.: IEEE Transactions on Pattern Analysis and Machine Intelligence
Abstract: State-of-the-art semantic image segmentation methods are mostly based on training deep convolutional neural networks (CNNs). In this work, we proffer to improve semantic segmentation with the use of contextual information. In particular, we explore 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.
ISSN: 0162-8828
DOI: 10.1109/TPAMI.2017.2708714
Schools: School of Computer Science and Engineering 
Rights: © 2017 IEEE. Personal use of this material is permitted. Permission from IEEE must be obtained for all other uses, in any current or future media, including reprinting/republishing this material for advertising or promotional purposes, creating new collective works, for resale or redistribution to servers or lists, or reuse of any copyrighted component of this work in other works. The published version is available at:
Fulltext Permission: open
Fulltext Availability: With Fulltext
Appears in Collections:SCSE Journal Articles

Files in This Item:
File Description SizeFormat 
Exploring Context with Deep Structured Models for Semantic Segmentation.pdf6.25 MBAdobe PDFThumbnail

Citations 5

Updated on May 31, 2024

Web of ScienceTM
Citations 5

Updated on Oct 25, 2023

Page view(s)

Updated on Jun 15, 2024

Download(s) 20

Updated on Jun 15, 2024

Google ScholarTM




Items in DR-NTU are protected by copyright, with all rights reserved, unless otherwise indicated.