Iteratively Trained Interactive Segmentation

Deep learning requires large amounts of training data to be effective. For the task of object segmentation, manually labeling data is very expensive, and hence interactive methods are needed. Following recent approaches, we develop an interactive object segmentation system which uses user input in t...

Full description

Saved in:
Bibliographic Details
Published in:arXiv.org 2018-05
Main Authors: Mahadevan, Sabarinath, Voigtlaender, Paul, Leibe, Bastian
Format: Article
Language:English
Subjects:
Artificial neural networks
Heuristic methods
Interactive systems
Machine learning
Sampling methods
Segmentation
Training
Online Access:Get full text
Tags: Add Tag
No Tags, Be the first to tag this record!
cited_by
cites
container_end_page
container_issue
container_start_page
container_title arXiv.org
container_volume
creator Mahadevan, Sabarinath
Voigtlaender, Paul
Leibe, Bastian
description Deep learning requires large amounts of training data to be effective. For the task of object segmentation, manually labeling data is very expensive, and hence interactive methods are needed. Following recent approaches, we develop an interactive object segmentation system which uses user input in the form of clicks as the input to a convolutional network. While previous methods use heuristic click sampling strategies to emulate user clicks during training, we propose a new iterative training strategy. During training, we iteratively add clicks based on the errors of the currently predicted segmentation. We show that our iterative training strategy together with additional improvements to the network architecture results in improved results over the state-of-the-art.
format article
fullrecord <record><control><sourceid>proquest</sourceid><recordid>TN_cdi_proquest_journals_2073746037</recordid><sourceformat>XML</sourceformat><sourcesystem>PC</sourcesystem><sourcerecordid>2073746037</sourcerecordid><originalsourceid>FETCH-proquest_journals_20737460373</originalsourceid><addsrcrecordid>eNpjYuA0MjY21LUwMTLiYOAtLs4yMDAwMjM3MjU15mTQ8SxJLUosySxLzalUCClKzMxLTVHwzAMJJoNEFYJT03NT80qASvLzeBhY0xJzilN5oTQ3g7Kba4izh25BUX5haWpxSXxWfmlRHlAq3sjA3NjcxMzA2NyYOFUAwmMyJA</addsrcrecordid><sourcetype>Aggregation Database</sourcetype><iscdi>true</iscdi><recordtype>article</recordtype><pqid>2073746037</pqid></control><display><type>article</type><title>Iteratively Trained Interactive Segmentation</title><source>Publicly Available Content Database</source><creator>Mahadevan, Sabarinath ; Voigtlaender, Paul ; Leibe, Bastian</creator><creatorcontrib>Mahadevan, Sabarinath ; Voigtlaender, Paul ; Leibe, Bastian</creatorcontrib><description>Deep learning requires large amounts of training data to be effective. For the task of object segmentation, manually labeling data is very expensive, and hence interactive methods are needed. Following recent approaches, we develop an interactive object segmentation system which uses user input in the form of clicks as the input to a convolutional network. While previous methods use heuristic click sampling strategies to emulate user clicks during training, we propose a new iterative training strategy. During training, we iteratively add clicks based on the errors of the currently predicted segmentation. We show that our iterative training strategy together with additional improvements to the network architecture results in improved results over the state-of-the-art.</description><identifier>EISSN: 2331-8422</identifier><language>eng</language><publisher>Ithaca: Cornell University Library, arXiv.org</publisher><subject>Artificial neural networks ; Heuristic methods ; Interactive systems ; Machine learning ; Sampling methods ; Segmentation ; Training</subject><ispartof>arXiv.org, 2018-05</ispartof><rights>2018. This work is published under http://arxiv.org/licenses/nonexclusive-distrib/1.0/ (the “License”). Notwithstanding the ProQuest Terms and Conditions, you may use this content in accordance with the terms of the License.</rights><oa>free_for_read</oa><woscitedreferencessubscribed>false</woscitedreferencessubscribed></display><links><openurl>$$Topenurl_article</openurl><openurlfulltext>$$Topenurlfull_article</openurlfulltext><thumbnail>$$Tsyndetics_thumb_exl</thumbnail><linktohtml>$$Uhttps://www.proquest.com/docview/2073746037?pq-origsite=primo$$EHTML$$P50$$Gproquest$$Hfree_for_read</linktohtml><link.rule.ids>776,780,25731,36989,44566</link.rule.ids></links><search><creatorcontrib>Mahadevan, Sabarinath</creatorcontrib><creatorcontrib>Voigtlaender, Paul</creatorcontrib><creatorcontrib>Leibe, Bastian</creatorcontrib><title>Iteratively Trained Interactive Segmentation</title><title>arXiv.org</title><description>Deep learning requires large amounts of training data to be effective. For the task of object segmentation, manually labeling data is very expensive, and hence interactive methods are needed. Following recent approaches, we develop an interactive object segmentation system which uses user input in the form of clicks as the input to a convolutional network. While previous methods use heuristic click sampling strategies to emulate user clicks during training, we propose a new iterative training strategy. During training, we iteratively add clicks based on the errors of the currently predicted segmentation. We show that our iterative training strategy together with additional improvements to the network architecture results in improved results over the state-of-the-art.</description><subject>Artificial neural networks</subject><subject>Heuristic methods</subject><subject>Interactive systems</subject><subject>Machine learning</subject><subject>Sampling methods</subject><subject>Segmentation</subject><subject>Training</subject><issn>2331-8422</issn><fulltext>true</fulltext><rsrctype>article</rsrctype><creationdate>2018</creationdate><recordtype>article</recordtype><sourceid>PIMPY</sourceid><recordid>eNpjYuA0MjY21LUwMTLiYOAtLs4yMDAwMjM3MjU15mTQ8SxJLUosySxLzalUCClKzMxLTVHwzAMJJoNEFYJT03NT80qASvLzeBhY0xJzilN5oTQ3g7Kba4izh25BUX5haWpxSXxWfmlRHlAq3sjA3NjcxMzA2NyYOFUAwmMyJA</recordid><startdate>20180511</startdate><enddate>20180511</enddate><creator>Mahadevan, Sabarinath</creator><creator>Voigtlaender, Paul</creator><creator>Leibe, Bastian</creator><general>Cornell University Library, arXiv.org</general><scope>8FE</scope><scope>8FG</scope><scope>ABJCF</scope><scope>ABUWG</scope><scope>AFKRA</scope><scope>AZQEC</scope><scope>BENPR</scope><scope>BGLVJ</scope><scope>CCPQU</scope><scope>DWQXO</scope><scope>HCIFZ</scope><scope>L6V</scope><scope>M7S</scope><scope>PIMPY</scope><scope>PQEST</scope><scope>PQQKQ</scope><scope>PQUKI</scope><scope>PRINS</scope><scope>PTHSS</scope></search><sort><creationdate>20180511</creationdate><title>Iteratively Trained Interactive Segmentation</title><author>Mahadevan, Sabarinath ; Voigtlaender, Paul ; Leibe, Bastian</author></sort><facets><frbrtype>5</frbrtype><frbrgroupid>cdi_FETCH-proquest_journals_20737460373</frbrgroupid><rsrctype>articles</rsrctype><prefilter>articles</prefilter><language>eng</language><creationdate>2018</creationdate><topic>Artificial neural networks</topic><topic>Heuristic methods</topic><topic>Interactive systems</topic><topic>Machine learning</topic><topic>Sampling methods</topic><topic>Segmentation</topic><topic>Training</topic><toplevel>online_resources</toplevel><creatorcontrib>Mahadevan, Sabarinath</creatorcontrib><creatorcontrib>Voigtlaender, Paul</creatorcontrib><creatorcontrib>Leibe, Bastian</creatorcontrib><collection>ProQuest SciTech Collection</collection><collection>ProQuest Technology Collection</collection><collection>Materials Science &amp; Engineering Collection</collection><collection>ProQuest Central (Alumni)</collection><collection>ProQuest Central</collection><collection>ProQuest Central Essentials</collection><collection>ProQuest Central</collection><collection>Technology Collection</collection><collection>ProQuest One Community College</collection><collection>ProQuest Central</collection><collection>SciTech Premium Collection</collection><collection>ProQuest Engineering Collection</collection><collection>Engineering Database</collection><collection>Publicly Available Content Database</collection><collection>ProQuest One Academic Eastern Edition (DO NOT USE)</collection><collection>ProQuest One Academic</collection><collection>ProQuest One Academic UKI Edition</collection><collection>ProQuest Central China</collection><collection>Engineering Collection</collection></facets><delivery><delcategory>Remote Search Resource</delcategory><fulltext>fulltext</fulltext></delivery><addata><au>Mahadevan, Sabarinath</au><au>Voigtlaender, Paul</au><au>Leibe, Bastian</au><format>book</format><genre>document</genre><ristype>GEN</ristype><atitle>Iteratively Trained Interactive Segmentation</atitle><jtitle>arXiv.org</jtitle><date>2018-05-11</date><risdate>2018</risdate><eissn>2331-8422</eissn><abstract>Deep learning requires large amounts of training data to be effective. For the task of object segmentation, manually labeling data is very expensive, and hence interactive methods are needed. Following recent approaches, we develop an interactive object segmentation system which uses user input in the form of clicks as the input to a convolutional network. While previous methods use heuristic click sampling strategies to emulate user clicks during training, we propose a new iterative training strategy. During training, we iteratively add clicks based on the errors of the currently predicted segmentation. We show that our iterative training strategy together with additional improvements to the network architecture results in improved results over the state-of-the-art.</abstract><cop>Ithaca</cop><pub>Cornell University Library, arXiv.org</pub><oa>free_for_read</oa></addata></record>
fulltext fulltext
identifier EISSN: 2331-8422
ispartof arXiv.org, 2018-05
issn 2331-8422
language eng
recordid cdi_proquest_journals_2073746037
source Publicly Available Content Database
subjects Artificial neural networks
Heuristic methods
Interactive systems
Machine learning
Sampling methods
Segmentation
Training
title Iteratively Trained Interactive Segmentation
url http://sfxeu10.hosted.exlibrisgroup.com/loughborough?ctx_ver=Z39.88-2004&ctx_enc=info:ofi/enc:UTF-8&ctx_tim=2025-01-30T03%3A18%3A10IST&url_ver=Z39.88-2004&url_ctx_fmt=infofi/fmt:kev:mtx:ctx&rfr_id=info:sid/primo.exlibrisgroup.com:primo3-Article-proquest&rft_val_fmt=info:ofi/fmt:kev:mtx:book&rft.genre=document&rft.atitle=Iteratively%20Trained%20Interactive%20Segmentation&rft.jtitle=arXiv.org&rft.au=Mahadevan,%20Sabarinath&rft.date=2018-05-11&rft.eissn=2331-8422&rft_id=info:doi/&rft_dat=%3Cproquest%3E2073746037%3C/proquest%3E%3Cgrp_id%3Ecdi_FETCH-proquest_journals_20737460373%3C/grp_id%3E%3Coa%3E%3C/oa%3E%3Curl%3E%3C/url%3E&rft_id=info:oai/&rft_pqid=2073746037&rft_id=info:pmid/&rfr_iscdi=true