Dual Progressive Transformations for Weakly Supervised Semantic Segmentation

Weakly supervised semantic segmentation (WSSS), which aims to mine the object regions by merely using class-level labels, is a challenging task in computer vision. The current state-of-the-art CNN-based methods usually adopt Class-Activation-Maps (CAMs) to highlight the potential areas of the object...

Ausführliche Beschreibung

Gespeichert in:
Bibliographische Detailangaben
Hauptverfasser: Huo, Dongjian, Su, Yukun, Wu, Qingyao
Format: Artikel
Sprache:eng
Schlagworte:
Online-Zugang:Volltext bestellen
Tags: Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
container_end_page
container_issue
container_start_page
container_title
container_volume
creator Huo, Dongjian
Su, Yukun
Wu, Qingyao
description Weakly supervised semantic segmentation (WSSS), which aims to mine the object regions by merely using class-level labels, is a challenging task in computer vision. The current state-of-the-art CNN-based methods usually adopt Class-Activation-Maps (CAMs) to highlight the potential areas of the object, however, they may suffer from the part-activated issues. To this end, we try an early attempt to explore the global feature attention mechanism of vision transformer in WSSS task. However, since the transformer lacks the inductive bias as in CNN models, it can not boost the performance directly and may yield the over-activated problems. To tackle these drawbacks, we propose a Convolutional Neural Networks Refined Transformer (CRT) to mine a globally complete and locally accurate class activation maps in this paper. To validate the effectiveness of our proposed method, extensive experiments are conducted on PASCAL VOC 2012 and CUB-200-2011 datasets. Experimental evaluations show that our proposed CRT achieves the new state-of-the-art performance on both the weakly supervised semantic segmentation task the weakly supervised object localization task, which outperform others by a large margin.
doi_str_mv 10.48550/arxiv.2209.15211
format Article
fullrecord <record><control><sourceid>arxiv_GOX</sourceid><recordid>TN_cdi_arxiv_primary_2209_15211</recordid><sourceformat>XML</sourceformat><sourcesystem>PC</sourcesystem><sourcerecordid>2209_15211</sourcerecordid><originalsourceid>FETCH-LOGICAL-a671-93f1bd3ec2cc46b32fc0715264efba7e598fe46da6aeea2deee169f5c9e9d6cf3</originalsourceid><addsrcrecordid>eNotj8tqwzAURLXJoqT9gK6iH7BrSZYcLUvSFxgSiKFLcy1dBVE_guSY5u_rul3NWQzDHEIeWZbmWymzJwjffko5z3TKJGfsjpT7K7T0GIZzwBj9hLQK0Ec3hA5GP_SRzkg_Eb7aGz1dLxgmH9HSE3bQj97McO6wH5fyPVk5aCM-_OeaVK8v1e49KQ9vH7vnMgFVsEQLxxor0HBjctUI7kxWzHdUjq6BAqXeOsyVBQWIwC0iMqWdNBq1VcaJNdn8zS469SX4DsKt_tWqFy3xA_yESs0</addsrcrecordid><sourcetype>Open Access Repository</sourcetype><iscdi>true</iscdi><recordtype>article</recordtype></control><display><type>article</type><title>Dual Progressive Transformations for Weakly Supervised Semantic Segmentation</title><source>arXiv.org</source><creator>Huo, Dongjian ; Su, Yukun ; Wu, Qingyao</creator><creatorcontrib>Huo, Dongjian ; Su, Yukun ; Wu, Qingyao</creatorcontrib><description>Weakly supervised semantic segmentation (WSSS), which aims to mine the object regions by merely using class-level labels, is a challenging task in computer vision. The current state-of-the-art CNN-based methods usually adopt Class-Activation-Maps (CAMs) to highlight the potential areas of the object, however, they may suffer from the part-activated issues. To this end, we try an early attempt to explore the global feature attention mechanism of vision transformer in WSSS task. However, since the transformer lacks the inductive bias as in CNN models, it can not boost the performance directly and may yield the over-activated problems. To tackle these drawbacks, we propose a Convolutional Neural Networks Refined Transformer (CRT) to mine a globally complete and locally accurate class activation maps in this paper. To validate the effectiveness of our proposed method, extensive experiments are conducted on PASCAL VOC 2012 and CUB-200-2011 datasets. Experimental evaluations show that our proposed CRT achieves the new state-of-the-art performance on both the weakly supervised semantic segmentation task the weakly supervised object localization task, which outperform others by a large margin.</description><identifier>DOI: 10.48550/arxiv.2209.15211</identifier><language>eng</language><subject>Computer Science - Computer Vision and Pattern Recognition</subject><creationdate>2022-09</creationdate><rights>http://arxiv.org/licenses/nonexclusive-distrib/1.0</rights><oa>free_for_read</oa><woscitedreferencessubscribed>false</woscitedreferencessubscribed></display><links><openurl>$$Topenurl_article</openurl><openurlfulltext>$$Topenurlfull_article</openurlfulltext><thumbnail>$$Tsyndetics_thumb_exl</thumbnail><link.rule.ids>228,230,780,885</link.rule.ids><linktorsrc>$$Uhttps://arxiv.org/abs/2209.15211$$EView_record_in_Cornell_University$$FView_record_in_$$GCornell_University$$Hfree_for_read</linktorsrc><backlink>$$Uhttps://doi.org/10.48550/arXiv.2209.15211$$DView paper in arXiv$$Hfree_for_read</backlink></links><search><creatorcontrib>Huo, Dongjian</creatorcontrib><creatorcontrib>Su, Yukun</creatorcontrib><creatorcontrib>Wu, Qingyao</creatorcontrib><title>Dual Progressive Transformations for Weakly Supervised Semantic Segmentation</title><description>Weakly supervised semantic segmentation (WSSS), which aims to mine the object regions by merely using class-level labels, is a challenging task in computer vision. The current state-of-the-art CNN-based methods usually adopt Class-Activation-Maps (CAMs) to highlight the potential areas of the object, however, they may suffer from the part-activated issues. To this end, we try an early attempt to explore the global feature attention mechanism of vision transformer in WSSS task. However, since the transformer lacks the inductive bias as in CNN models, it can not boost the performance directly and may yield the over-activated problems. To tackle these drawbacks, we propose a Convolutional Neural Networks Refined Transformer (CRT) to mine a globally complete and locally accurate class activation maps in this paper. To validate the effectiveness of our proposed method, extensive experiments are conducted on PASCAL VOC 2012 and CUB-200-2011 datasets. Experimental evaluations show that our proposed CRT achieves the new state-of-the-art performance on both the weakly supervised semantic segmentation task the weakly supervised object localization task, which outperform others by a large margin.</description><subject>Computer Science - Computer Vision and Pattern Recognition</subject><fulltext>true</fulltext><rsrctype>article</rsrctype><creationdate>2022</creationdate><recordtype>article</recordtype><sourceid>GOX</sourceid><recordid>eNotj8tqwzAURLXJoqT9gK6iH7BrSZYcLUvSFxgSiKFLcy1dBVE_guSY5u_rul3NWQzDHEIeWZbmWymzJwjffko5z3TKJGfsjpT7K7T0GIZzwBj9hLQK0Ec3hA5GP_SRzkg_Eb7aGz1dLxgmH9HSE3bQj97McO6wH5fyPVk5aCM-_OeaVK8v1e49KQ9vH7vnMgFVsEQLxxor0HBjctUI7kxWzHdUjq6BAqXeOsyVBQWIwC0iMqWdNBq1VcaJNdn8zS469SX4DsKt_tWqFy3xA_yESs0</recordid><startdate>20220929</startdate><enddate>20220929</enddate><creator>Huo, Dongjian</creator><creator>Su, Yukun</creator><creator>Wu, Qingyao</creator><scope>AKY</scope><scope>GOX</scope></search><sort><creationdate>20220929</creationdate><title>Dual Progressive Transformations for Weakly Supervised Semantic Segmentation</title><author>Huo, Dongjian ; Su, Yukun ; Wu, Qingyao</author></sort><facets><frbrtype>5</frbrtype><frbrgroupid>cdi_FETCH-LOGICAL-a671-93f1bd3ec2cc46b32fc0715264efba7e598fe46da6aeea2deee169f5c9e9d6cf3</frbrgroupid><rsrctype>articles</rsrctype><prefilter>articles</prefilter><language>eng</language><creationdate>2022</creationdate><topic>Computer Science - Computer Vision and Pattern Recognition</topic><toplevel>online_resources</toplevel><creatorcontrib>Huo, Dongjian</creatorcontrib><creatorcontrib>Su, Yukun</creatorcontrib><creatorcontrib>Wu, Qingyao</creatorcontrib><collection>arXiv Computer Science</collection><collection>arXiv.org</collection></facets><delivery><delcategory>Remote Search Resource</delcategory><fulltext>fulltext_linktorsrc</fulltext></delivery><addata><au>Huo, Dongjian</au><au>Su, Yukun</au><au>Wu, Qingyao</au><format>journal</format><genre>article</genre><ristype>JOUR</ristype><atitle>Dual Progressive Transformations for Weakly Supervised Semantic Segmentation</atitle><date>2022-09-29</date><risdate>2022</risdate><abstract>Weakly supervised semantic segmentation (WSSS), which aims to mine the object regions by merely using class-level labels, is a challenging task in computer vision. The current state-of-the-art CNN-based methods usually adopt Class-Activation-Maps (CAMs) to highlight the potential areas of the object, however, they may suffer from the part-activated issues. To this end, we try an early attempt to explore the global feature attention mechanism of vision transformer in WSSS task. However, since the transformer lacks the inductive bias as in CNN models, it can not boost the performance directly and may yield the over-activated problems. To tackle these drawbacks, we propose a Convolutional Neural Networks Refined Transformer (CRT) to mine a globally complete and locally accurate class activation maps in this paper. To validate the effectiveness of our proposed method, extensive experiments are conducted on PASCAL VOC 2012 and CUB-200-2011 datasets. Experimental evaluations show that our proposed CRT achieves the new state-of-the-art performance on both the weakly supervised semantic segmentation task the weakly supervised object localization task, which outperform others by a large margin.</abstract><doi>10.48550/arxiv.2209.15211</doi><oa>free_for_read</oa></addata></record>
fulltext fulltext_linktorsrc
identifier DOI: 10.48550/arxiv.2209.15211
ispartof
issn
language eng
recordid cdi_arxiv_primary_2209_15211
source arXiv.org
subjects Computer Science - Computer Vision and Pattern Recognition
title Dual Progressive Transformations for Weakly Supervised Semantic Segmentation
url https://sfx.bib-bvb.de/sfx_tum?ctx_ver=Z39.88-2004&ctx_enc=info:ofi/enc:UTF-8&ctx_tim=2025-01-04T13%3A51%3A46IST&url_ver=Z39.88-2004&url_ctx_fmt=infofi/fmt:kev:mtx:ctx&rfr_id=info:sid/primo.exlibrisgroup.com:primo3-Article-arxiv_GOX&rft_val_fmt=info:ofi/fmt:kev:mtx:journal&rft.genre=article&rft.atitle=Dual%20Progressive%20Transformations%20for%20Weakly%20Supervised%20Semantic%20Segmentation&rft.au=Huo,%20Dongjian&rft.date=2022-09-29&rft_id=info:doi/10.48550/arxiv.2209.15211&rft_dat=%3Carxiv_GOX%3E2209_15211%3C/arxiv_GOX%3E%3Curl%3E%3C/url%3E&disable_directlink=true&sfx.directlink=off&sfx.report_link=0&rft_id=info:oai/&rft_id=info:pmid/&rfr_iscdi=true