Edinburgh Research Explorer

Region-Based Semantic Segmentation with End-to-End Training

Research output: Chapter in Book/Report/Conference proceedingConference contribution

Related Edinburgh Organisations

Open Access permissions

Open

Documents

http://link.springer.com/chapter/10.1007%2F978-3-319-46448-0_23
Original languageEnglish
Title of host publicationComputer Vision -- ECCV 2016
Subtitle of host publication14th European Conference, Amsterdam, The Netherlands, October 11--14, 2016, Proceedings, Part I
EditorsBastian Leibe, Jiri Matas, Nicu Sebe, Max Welling
Place of PublicationCham
PublisherSpringer International Publishing
Pages381-397
Number of pages17
ISBN (Electronic)978-3-319-46448-0
ISBN (Print)978-3-319-46447-3
DOIs
Publication statusPublished - 17 Sep 2016
Event14th European Conference on Computer Vision 2016 - Amsterdam, Netherlands
Duration: 8 Oct 201616 Oct 2016
http://www.eccv2016.org/

Publication series

NameLecture Notes in Computer Science
PublisherSpringer International Publishing
Volume9905
ISSN (Print)0302-9743

Conference

Conference14th European Conference on Computer Vision 2016
Abbreviated titleECCV 2016
CountryNetherlands
CityAmsterdam
Period8/10/1616/10/16
Internet address

Abstract

We propose a novel method for semantic segmentation, the task of labeling each pixel in an image with a semantic class. Our method combines the advantages of the two main competing paradigms. Methods based on region classification offer proper spatial support for appearance measurements, but typically operate in two separate stages, none of which targets pixel labeling performance at the end of the pipeline. More recent fully convolutional methods are capable of end-to-end training for the final pixel labeling, but resort to fixed patches as spatial support. We show how to modify modern region-based approaches to enable end-to-end training for semantic segmentation. This is achieved via a differentiable region-to-pixel layer and a differentiable free-form Region-of-Interest pooling layer. Our method improves the state-of-the-art in terms of class-average accuracy with 64.0%64.0% on SIFT Flow and 49.9%49.9% on PASCAL Context, and is particularly accurate at object boundaries.

Event

14th European Conference on Computer Vision 2016

8/10/1616/10/16

Amsterdam, Netherlands

Event: Conference

Download statistics

No data available

ID: 28562178