Learning Pixel-wise Labeling from the Internet without Human Interaction

Deep learning stands at the forefront in many computer vision tasks. However, deep neural networks are usually data-hungry and require a huge amount of well-annotated training samples. Collecting sufficient annotated data is very expensive in many applications, especially for pixel-level prediction...

Ausführliche Beschreibung

Gespeichert in:
Bibliographische Detailangaben
Veröffentlicht in:arXiv.org 2018-05
Hauptverfasser: Liu, Yun, Shi, Yujun, Bian, JiaWang, Zhang, Le, Ming-Ming, Cheng, Feng, Jiashi
Format: Artikel
Sprache:eng
Schlagworte:
Online-Zugang:Volltext
Tags: Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
container_end_page
container_issue
container_start_page
container_title arXiv.org
container_volume
creator Liu, Yun
Shi, Yujun
Bian, JiaWang
Zhang, Le
Ming-Ming, Cheng
Feng, Jiashi
description Deep learning stands at the forefront in many computer vision tasks. However, deep neural networks are usually data-hungry and require a huge amount of well-annotated training samples. Collecting sufficient annotated data is very expensive in many applications, especially for pixel-level prediction tasks such as semantic segmentation. To solve this fundamental issue, we consider a new challenging vision task, Internetly supervised semantic segmentation, which only uses Internet data with noisy image-level supervision of corresponding query keywords for segmentation model training. We address this task by proposing the following solution. A class-specific attention model unifying multiscale forward and backward convolutional features is proposed to provide initial segmentation "ground truth". The model trained with such noisy annotations is then improved by an online fine-tuning procedure. It achieves state-of-the-art performance under the weakly-supervised setting on PASCAL VOC2012 dataset. The proposed framework also paves a new way towards learning from the Internet without human interaction and could serve as a strong baseline therein. Code and data will be released upon the paper acceptance.
format Article
fullrecord <record><control><sourceid>proquest</sourceid><recordid>TN_cdi_proquest_journals_2073520289</recordid><sourceformat>XML</sourceformat><sourcesystem>PC</sourcesystem><sourcerecordid>2073520289</sourcerecordid><originalsourceid>FETCH-proquest_journals_20735202893</originalsourceid><addsrcrecordid>eNqNikEKwjAQAIMgWLR_CHguxI2x9SxKhR48eC9RtjalTTTZUJ-vog_wNDAzE5aAlKusWAPMWBpCJ4SATQ5KyYSVFWpvjb3xk3lin40mIK_0BfuPa7wbOLXIj5bQWyQ-GmpdJF7GQduv1lcyzi7YtNF9wPTHOVse9uddmd29e0QMVHcuevtONYhcKhBQbOV_1wtFJzwZ</addsrcrecordid><sourcetype>Aggregation Database</sourcetype><iscdi>true</iscdi><recordtype>article</recordtype><pqid>2073520289</pqid></control><display><type>article</type><title>Learning Pixel-wise Labeling from the Internet without Human Interaction</title><source>Free E- Journals</source><creator>Liu, Yun ; Shi, Yujun ; Bian, JiaWang ; Zhang, Le ; Ming-Ming, Cheng ; Feng, Jiashi</creator><creatorcontrib>Liu, Yun ; Shi, Yujun ; Bian, JiaWang ; Zhang, Le ; Ming-Ming, Cheng ; Feng, Jiashi</creatorcontrib><description>Deep learning stands at the forefront in many computer vision tasks. However, deep neural networks are usually data-hungry and require a huge amount of well-annotated training samples. Collecting sufficient annotated data is very expensive in many applications, especially for pixel-level prediction tasks such as semantic segmentation. To solve this fundamental issue, we consider a new challenging vision task, Internetly supervised semantic segmentation, which only uses Internet data with noisy image-level supervision of corresponding query keywords for segmentation model training. We address this task by proposing the following solution. A class-specific attention model unifying multiscale forward and backward convolutional features is proposed to provide initial segmentation "ground truth". The model trained with such noisy annotations is then improved by an online fine-tuning procedure. It achieves state-of-the-art performance under the weakly-supervised setting on PASCAL VOC2012 dataset. The proposed framework also paves a new way towards learning from the Internet without human interaction and could serve as a strong baseline therein. Code and data will be released upon the paper acceptance.</description><identifier>EISSN: 2331-8422</identifier><language>eng</language><publisher>Ithaca: Cornell University Library, arXiv.org</publisher><subject>Computer vision ; Ground truth ; Image annotation ; Image segmentation ; Internet ; Machine learning ; Neural networks ; Pixels ; Semantic segmentation ; Semantics ; 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><link.rule.ids>777,781</link.rule.ids></links><search><creatorcontrib>Liu, Yun</creatorcontrib><creatorcontrib>Shi, Yujun</creatorcontrib><creatorcontrib>Bian, JiaWang</creatorcontrib><creatorcontrib>Zhang, Le</creatorcontrib><creatorcontrib>Ming-Ming, Cheng</creatorcontrib><creatorcontrib>Feng, Jiashi</creatorcontrib><title>Learning Pixel-wise Labeling from the Internet without Human Interaction</title><title>arXiv.org</title><description>Deep learning stands at the forefront in many computer vision tasks. However, deep neural networks are usually data-hungry and require a huge amount of well-annotated training samples. Collecting sufficient annotated data is very expensive in many applications, especially for pixel-level prediction tasks such as semantic segmentation. To solve this fundamental issue, we consider a new challenging vision task, Internetly supervised semantic segmentation, which only uses Internet data with noisy image-level supervision of corresponding query keywords for segmentation model training. We address this task by proposing the following solution. A class-specific attention model unifying multiscale forward and backward convolutional features is proposed to provide initial segmentation "ground truth". The model trained with such noisy annotations is then improved by an online fine-tuning procedure. It achieves state-of-the-art performance under the weakly-supervised setting on PASCAL VOC2012 dataset. The proposed framework also paves a new way towards learning from the Internet without human interaction and could serve as a strong baseline therein. Code and data will be released upon the paper acceptance.</description><subject>Computer vision</subject><subject>Ground truth</subject><subject>Image annotation</subject><subject>Image segmentation</subject><subject>Internet</subject><subject>Machine learning</subject><subject>Neural networks</subject><subject>Pixels</subject><subject>Semantic segmentation</subject><subject>Semantics</subject><subject>Training</subject><issn>2331-8422</issn><fulltext>true</fulltext><rsrctype>article</rsrctype><creationdate>2018</creationdate><recordtype>article</recordtype><sourceid>ABUWG</sourceid><sourceid>AFKRA</sourceid><sourceid>AZQEC</sourceid><sourceid>BENPR</sourceid><sourceid>CCPQU</sourceid><sourceid>DWQXO</sourceid><recordid>eNqNikEKwjAQAIMgWLR_CHguxI2x9SxKhR48eC9RtjalTTTZUJ-vog_wNDAzE5aAlKusWAPMWBpCJ4SATQ5KyYSVFWpvjb3xk3lin40mIK_0BfuPa7wbOLXIj5bQWyQ-GmpdJF7GQduv1lcyzi7YtNF9wPTHOVse9uddmd29e0QMVHcuevtONYhcKhBQbOV_1wtFJzwZ</recordid><startdate>20180519</startdate><enddate>20180519</enddate><creator>Liu, Yun</creator><creator>Shi, Yujun</creator><creator>Bian, JiaWang</creator><creator>Zhang, Le</creator><creator>Ming-Ming, Cheng</creator><creator>Feng, Jiashi</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>20180519</creationdate><title>Learning Pixel-wise Labeling from the Internet without Human Interaction</title><author>Liu, Yun ; Shi, Yujun ; Bian, JiaWang ; Zhang, Le ; Ming-Ming, Cheng ; Feng, Jiashi</author></sort><facets><frbrtype>5</frbrtype><frbrgroupid>cdi_FETCH-proquest_journals_20735202893</frbrgroupid><rsrctype>articles</rsrctype><prefilter>articles</prefilter><language>eng</language><creationdate>2018</creationdate><topic>Computer vision</topic><topic>Ground truth</topic><topic>Image annotation</topic><topic>Image segmentation</topic><topic>Internet</topic><topic>Machine learning</topic><topic>Neural networks</topic><topic>Pixels</topic><topic>Semantic segmentation</topic><topic>Semantics</topic><topic>Training</topic><toplevel>online_resources</toplevel><creatorcontrib>Liu, Yun</creatorcontrib><creatorcontrib>Shi, Yujun</creatorcontrib><creatorcontrib>Bian, JiaWang</creatorcontrib><creatorcontrib>Zhang, Le</creatorcontrib><creatorcontrib>Ming-Ming, Cheng</creatorcontrib><creatorcontrib>Feng, Jiashi</creatorcontrib><collection>ProQuest SciTech Collection</collection><collection>ProQuest Technology Collection</collection><collection>Materials Science &amp; Engineering Collection</collection><collection>ProQuest Central (Alumni Edition)</collection><collection>ProQuest Central UK/Ireland</collection><collection>ProQuest Central Essentials</collection><collection>ProQuest Central</collection><collection>Technology Collection</collection><collection>ProQuest One Community College</collection><collection>ProQuest Central Korea</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>Liu, Yun</au><au>Shi, Yujun</au><au>Bian, JiaWang</au><au>Zhang, Le</au><au>Ming-Ming, Cheng</au><au>Feng, Jiashi</au><format>book</format><genre>document</genre><ristype>GEN</ristype><atitle>Learning Pixel-wise Labeling from the Internet without Human Interaction</atitle><jtitle>arXiv.org</jtitle><date>2018-05-19</date><risdate>2018</risdate><eissn>2331-8422</eissn><abstract>Deep learning stands at the forefront in many computer vision tasks. However, deep neural networks are usually data-hungry and require a huge amount of well-annotated training samples. Collecting sufficient annotated data is very expensive in many applications, especially for pixel-level prediction tasks such as semantic segmentation. To solve this fundamental issue, we consider a new challenging vision task, Internetly supervised semantic segmentation, which only uses Internet data with noisy image-level supervision of corresponding query keywords for segmentation model training. We address this task by proposing the following solution. A class-specific attention model unifying multiscale forward and backward convolutional features is proposed to provide initial segmentation "ground truth". The model trained with such noisy annotations is then improved by an online fine-tuning procedure. It achieves state-of-the-art performance under the weakly-supervised setting on PASCAL VOC2012 dataset. The proposed framework also paves a new way towards learning from the Internet without human interaction and could serve as a strong baseline therein. Code and data will be released upon the paper acceptance.</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_2073520289
source Free E- Journals
subjects Computer vision
Ground truth
Image annotation
Image segmentation
Internet
Machine learning
Neural networks
Pixels
Semantic segmentation
Semantics
Training
title Learning Pixel-wise Labeling from the Internet without Human Interaction
url https://sfx.bib-bvb.de/sfx_tum?ctx_ver=Z39.88-2004&ctx_enc=info:ofi/enc:UTF-8&ctx_tim=2025-01-19T16%3A29%3A19IST&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=Learning%20Pixel-wise%20Labeling%20from%20the%20Internet%20without%20Human%20Interaction&rft.jtitle=arXiv.org&rft.au=Liu,%20Yun&rft.date=2018-05-19&rft.eissn=2331-8422&rft_id=info:doi/&rft_dat=%3Cproquest%3E2073520289%3C/proquest%3E%3Curl%3E%3C/url%3E&disable_directlink=true&sfx.directlink=off&sfx.report_link=0&rft_id=info:oai/&rft_pqid=2073520289&rft_id=info:pmid/&rfr_iscdi=true