Semi-Supervised Semantic Segmentation with Pixel-Level Contrastive Learning from a Class-wise Memory Bank

This work presents a novel approach for semi-supervised semantic segmentation. The key element of this approach is our contrastive learning module that enforces the segmentation network to yield similar pixel-level feature representations for same-class samples across the whole dataset. To achieve t...

Full description

Saved in:
Bibliographic Details
Main Authors: Alonso, Inigo, Sabater, Alberto, Ferstl, David, Montesano, Luis, Murillo, Ana C.
Format: Conference Proceeding
Language:English
Subjects:
Benchmark testing
Codes
Computer vision
Scene analysis and understanding
Semantics
Task analysis
Training
Transfer/Low-shot/Semi/Unsupervised Learning
Vision for robotics and autonomous vehicles
Online Access:Request full text
Tags: Add Tag
No Tags, Be the first to tag this record!
cited_by
cites
container_end_page 8208
container_issue
container_start_page 8199
container_title
container_volume
creator Alonso, Inigo
Sabater, Alberto
Ferstl, David
Montesano, Luis
Murillo, Ana C.
description This work presents a novel approach for semi-supervised semantic segmentation. The key element of this approach is our contrastive learning module that enforces the segmentation network to yield similar pixel-level feature representations for same-class samples across the whole dataset. To achieve this, we maintain a memory bank which is continuously updated with relevant and high-quality feature vectors from labeled data. In an end-to-end training, the features from both labeled and unlabeled data are optimized to be similar to same-class samples from the memory bank. Our approach not only outperforms the current state-of-the-art for semi-supervised semantic segmentation but also for semi-supervised domain adaptation on well-known public benchmarks, with larger improvements on the most challenging scenarios, i.e., less available labeled data. Code is available at https://github.com/Shathe/SemiSeg-Contrastive
doi_str_mv 10.1109/ICCV48922.2021.00811
format conference_proceeding
fullrecord <record><control><sourceid>ieee_CHZPO</sourceid><recordid>TN_cdi_ieee_primary_9710242</recordid><sourceformat>XML</sourceformat><sourcesystem>PC</sourcesystem><ieee_id>9710242</ieee_id><sourcerecordid>9710242</sourcerecordid><originalsourceid>FETCH-LOGICAL-i249t-9cdab9341863193126ab5e0ef7e07b5fd869ac2c1f0816c93bda1419f336ee083</originalsourceid><addsrcrecordid>eNotj8tOwzAUBQ0SEqX0C2DhH3DxtR3HXkLEo1IQSAW2lZPcFEMeyDYt_XsiwerMbEY6hFwCXwJwe7UqijdlrBBLwQUsOTcAR2RhcwNaZ0oYENkxmQlpOMszrk7JWYwfnEsrjJ4Rv8bes_X3F4adj9jQyd2QfD3BtschueTHge59eqfP_gc7VuIOO1qMQwouJr9DWqILgx-2tA1jTx0tOhcj2085-oj9GA70xg2f5-SkdV3Exf_Oyevd7UvxwMqn-1VxXTIvlE3M1o2rrFRgtAQrQWhXZcixzZHnVdY2RltXixra6amurawaBwpsK6VG5EbOycVf1yPi5iv43oXDxubAhRLyF72vWSA</addsrcrecordid><sourcetype>Publisher</sourcetype><iscdi>true</iscdi><recordtype>conference_proceeding</recordtype></control><display><type>conference_proceeding</type><title>Semi-Supervised Semantic Segmentation with Pixel-Level Contrastive Learning from a Class-wise Memory Bank</title><source>IEEE Xplore All Conference Series</source><creator>Alonso, Inigo ; Sabater, Alberto ; Ferstl, David ; Montesano, Luis ; Murillo, Ana C.</creator><creatorcontrib>Alonso, Inigo ; Sabater, Alberto ; Ferstl, David ; Montesano, Luis ; Murillo, Ana C.</creatorcontrib><description>This work presents a novel approach for semi-supervised semantic segmentation. The key element of this approach is our contrastive learning module that enforces the segmentation network to yield similar pixel-level feature representations for same-class samples across the whole dataset. To achieve this, we maintain a memory bank which is continuously updated with relevant and high-quality feature vectors from labeled data. In an end-to-end training, the features from both labeled and unlabeled data are optimized to be similar to same-class samples from the memory bank. Our approach not only outperforms the current state-of-the-art for semi-supervised semantic segmentation but also for semi-supervised domain adaptation on well-known public benchmarks, with larger improvements on the most challenging scenarios, i.e., less available labeled data. Code is available at https://github.com/Shathe/SemiSeg-Contrastive</description><identifier>EISSN: 2380-7504</identifier><identifier>EISBN: 9781665428125</identifier><identifier>EISBN: 1665428120</identifier><identifier>DOI: 10.1109/ICCV48922.2021.00811</identifier><identifier>CODEN: IEEPAD</identifier><language>eng</language><publisher>IEEE</publisher><subject>Benchmark testing ; Codes ; Computer vision ; Scene analysis and understanding ; Semantics ; Task analysis ; Training ; Transfer/Low-shot/Semi/Unsupervised Learning ; Vision for robotics and autonomous vehicles</subject><ispartof>2021 IEEE/CVF International Conference on Computer Vision (ICCV), 2021, p.8199-8208</ispartof><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://ieeexplore.ieee.org/document/9710242$$EHTML$$P50$$Gieee$$H</linktohtml><link.rule.ids>310,311,786,790,795,796,27958,54906,55283</link.rule.ids><linktorsrc>$$Uhttps://ieeexplore.ieee.org/document/9710242$$EView_record_in_IEEE$$FView_record_in_$$GIEEE</linktorsrc></links><search><creatorcontrib>Alonso, Inigo</creatorcontrib><creatorcontrib>Sabater, Alberto</creatorcontrib><creatorcontrib>Ferstl, David</creatorcontrib><creatorcontrib>Montesano, Luis</creatorcontrib><creatorcontrib>Murillo, Ana C.</creatorcontrib><title>Semi-Supervised Semantic Segmentation with Pixel-Level Contrastive Learning from a Class-wise Memory Bank</title><title>2021 IEEE/CVF International Conference on Computer Vision (ICCV)</title><addtitle>ICCV</addtitle><description>This work presents a novel approach for semi-supervised semantic segmentation. The key element of this approach is our contrastive learning module that enforces the segmentation network to yield similar pixel-level feature representations for same-class samples across the whole dataset. To achieve this, we maintain a memory bank which is continuously updated with relevant and high-quality feature vectors from labeled data. In an end-to-end training, the features from both labeled and unlabeled data are optimized to be similar to same-class samples from the memory bank. Our approach not only outperforms the current state-of-the-art for semi-supervised semantic segmentation but also for semi-supervised domain adaptation on well-known public benchmarks, with larger improvements on the most challenging scenarios, i.e., less available labeled data. Code is available at https://github.com/Shathe/SemiSeg-Contrastive</description><subject>Benchmark testing</subject><subject>Codes</subject><subject>Computer vision</subject><subject>Scene analysis and understanding</subject><subject>Semantics</subject><subject>Task analysis</subject><subject>Training</subject><subject>Transfer/Low-shot/Semi/Unsupervised Learning</subject><subject>Vision for robotics and autonomous vehicles</subject><issn>2380-7504</issn><isbn>9781665428125</isbn><isbn>1665428120</isbn><fulltext>true</fulltext><rsrctype>conference_proceeding</rsrctype><creationdate>2021</creationdate><recordtype>conference_proceeding</recordtype><sourceid>6IE</sourceid><recordid>eNotj8tOwzAUBQ0SEqX0C2DhH3DxtR3HXkLEo1IQSAW2lZPcFEMeyDYt_XsiwerMbEY6hFwCXwJwe7UqijdlrBBLwQUsOTcAR2RhcwNaZ0oYENkxmQlpOMszrk7JWYwfnEsrjJ4Rv8bes_X3F4adj9jQyd2QfD3BtschueTHge59eqfP_gc7VuIOO1qMQwouJr9DWqILgx-2tA1jTx0tOhcj2085-oj9GA70xg2f5-SkdV3Exf_Oyevd7UvxwMqn-1VxXTIvlE3M1o2rrFRgtAQrQWhXZcixzZHnVdY2RltXixra6amurawaBwpsK6VG5EbOycVf1yPi5iv43oXDxubAhRLyF72vWSA</recordid><startdate>202110</startdate><enddate>202110</enddate><creator>Alonso, Inigo</creator><creator>Sabater, Alberto</creator><creator>Ferstl, David</creator><creator>Montesano, Luis</creator><creator>Murillo, Ana C.</creator><general>IEEE</general><scope>6IE</scope><scope>6IH</scope><scope>CBEJK</scope><scope>RIE</scope><scope>RIO</scope></search><sort><creationdate>202110</creationdate><title>Semi-Supervised Semantic Segmentation with Pixel-Level Contrastive Learning from a Class-wise Memory Bank</title><author>Alonso, Inigo ; Sabater, Alberto ; Ferstl, David ; Montesano, Luis ; Murillo, Ana C.</author></sort><facets><frbrtype>5</frbrtype><frbrgroupid>cdi_FETCH-LOGICAL-i249t-9cdab9341863193126ab5e0ef7e07b5fd869ac2c1f0816c93bda1419f336ee083</frbrgroupid><rsrctype>conference_proceedings</rsrctype><prefilter>conference_proceedings</prefilter><language>eng</language><creationdate>2021</creationdate><topic>Benchmark testing</topic><topic>Codes</topic><topic>Computer vision</topic><topic>Scene analysis and understanding</topic><topic>Semantics</topic><topic>Task analysis</topic><topic>Training</topic><topic>Transfer/Low-shot/Semi/Unsupervised Learning</topic><topic>Vision for robotics and autonomous vehicles</topic><toplevel>online_resources</toplevel><creatorcontrib>Alonso, Inigo</creatorcontrib><creatorcontrib>Sabater, Alberto</creatorcontrib><creatorcontrib>Ferstl, David</creatorcontrib><creatorcontrib>Montesano, Luis</creatorcontrib><creatorcontrib>Murillo, Ana C.</creatorcontrib><collection>IEEE Electronic Library (IEL) Conference Proceedings</collection><collection>IEEE Proceedings Order Plan (POP) 1998-present by volume</collection><collection>IEEE Xplore All Conference Proceedings</collection><collection>IEEE Xplore</collection><collection>IEEE Proceedings Order Plans (POP) 1998-present</collection></facets><delivery><delcategory>Remote Search Resource</delcategory><fulltext>fulltext_linktorsrc</fulltext></delivery><addata><au>Alonso, Inigo</au><au>Sabater, Alberto</au><au>Ferstl, David</au><au>Montesano, Luis</au><au>Murillo, Ana C.</au><format>book</format><genre>proceeding</genre><ristype>CONF</ristype><atitle>Semi-Supervised Semantic Segmentation with Pixel-Level Contrastive Learning from a Class-wise Memory Bank</atitle><btitle>2021 IEEE/CVF International Conference on Computer Vision (ICCV)</btitle><stitle>ICCV</stitle><date>2021-10</date><risdate>2021</risdate><spage>8199</spage><epage>8208</epage><pages>8199-8208</pages><eissn>2380-7504</eissn><eisbn>9781665428125</eisbn><eisbn>1665428120</eisbn><coden>IEEPAD</coden><abstract>This work presents a novel approach for semi-supervised semantic segmentation. The key element of this approach is our contrastive learning module that enforces the segmentation network to yield similar pixel-level feature representations for same-class samples across the whole dataset. To achieve this, we maintain a memory bank which is continuously updated with relevant and high-quality feature vectors from labeled data. In an end-to-end training, the features from both labeled and unlabeled data are optimized to be similar to same-class samples from the memory bank. Our approach not only outperforms the current state-of-the-art for semi-supervised semantic segmentation but also for semi-supervised domain adaptation on well-known public benchmarks, with larger improvements on the most challenging scenarios, i.e., less available labeled data. Code is available at https://github.com/Shathe/SemiSeg-Contrastive</abstract><pub>IEEE</pub><doi>10.1109/ICCV48922.2021.00811</doi><tpages>10</tpages><oa>free_for_read</oa></addata></record>
fulltext fulltext_linktorsrc
identifier EISSN: 2380-7504
ispartof 2021 IEEE/CVF International Conference on Computer Vision (ICCV), 2021, p.8199-8208
issn 2380-7504
language eng
recordid cdi_ieee_primary_9710242
source IEEE Xplore All Conference Series
subjects Benchmark testing
Codes
Computer vision
Scene analysis and understanding
Semantics
Task analysis
Training
Transfer/Low-shot/Semi/Unsupervised Learning
Vision for robotics and autonomous vehicles
title Semi-Supervised Semantic Segmentation with Pixel-Level Contrastive Learning from a Class-wise Memory Bank
url http://sfxeu10.hosted.exlibrisgroup.com/loughborough?ctx_ver=Z39.88-2004&ctx_enc=info:ofi/enc:UTF-8&ctx_tim=2024-09-22T02%3A37%3A57IST&url_ver=Z39.88-2004&url_ctx_fmt=infofi/fmt:kev:mtx:ctx&rfr_id=info:sid/primo.exlibrisgroup.com:primo3-Article-ieee_CHZPO&rft_val_fmt=info:ofi/fmt:kev:mtx:book&rft.genre=proceeding&rft.atitle=Semi-Supervised%20Semantic%20Segmentation%20with%20Pixel-Level%20Contrastive%20Learning%20from%20a%20Class-wise%20Memory%20Bank&rft.btitle=2021%20IEEE/CVF%20International%20Conference%20on%20Computer%20Vision%20(ICCV)&rft.au=Alonso,%20Inigo&rft.date=2021-10&rft.spage=8199&rft.epage=8208&rft.pages=8199-8208&rft.eissn=2380-7504&rft.coden=IEEPAD&rft_id=info:doi/10.1109/ICCV48922.2021.00811&rft.eisbn=9781665428125&rft.eisbn_list=1665428120&rft_dat=%3Cieee_CHZPO%3E9710242%3C/ieee_CHZPO%3E%3Cgrp_id%3Ecdi_FETCH-LOGICAL-i249t-9cdab9341863193126ab5e0ef7e07b5fd869ac2c1f0816c93bda1419f336ee083%3C/grp_id%3E%3Coa%3E%3C/oa%3E%3Curl%3E%3C/url%3E&rft_id=info:oai/&rft_id=info:pmid/&rft_ieee_id=9710242&rfr_iscdi=true