Multi-Task Learning by a Top-Down Control Network

As the range of tasks performed by a general vision system expands, executing multiple tasks accurately and efficiently in a single network has become an important and still open problem. Recent computer vision approaches address this problem by branching networks, or by a channel-wise modulation of...

Ausführliche Beschreibung

Gespeichert in:
Bibliographische Detailangaben
Hauptverfasser: Levi, Hila, Ullman, Shimon
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 Levi, Hila
Ullman, Shimon
description As the range of tasks performed by a general vision system expands, executing multiple tasks accurately and efficiently in a single network has become an important and still open problem. Recent computer vision approaches address this problem by branching networks, or by a channel-wise modulation of the network feature-maps with task specific vectors. We present a novel architecture that uses a dedicated top-down control network to modify the activation of all the units in the main recognition network in a manner that depends on the selected task, image content, and spatial location. We show the effectiveness of our scheme by achieving significantly better results than alternative state-of-the-art approaches on four datasets. We further demonstrate our advantages in terms of task selectivity, scaling the number of tasks and interpretability.
doi_str_mv 10.48550/arxiv.2002.03335
format Article
fullrecord <record><control><sourceid>arxiv_GOX</sourceid><recordid>TN_cdi_arxiv_primary_2002_03335</recordid><sourceformat>XML</sourceformat><sourcesystem>PC</sourcesystem><sourcerecordid>2002_03335</sourcerecordid><originalsourceid>FETCH-LOGICAL-a675-39212274861294cc0d4dde6fed58064901288d9b2f54365ff65abc6118dfab503</originalsourceid><addsrcrecordid>eNotzrtOwzAUgGEvDKjlAZjwCzgcX47rjFW4SgGW7NFJbFdR07hy05a-PaIw_duvj7F7CYVxiPBI-Xs4FQpAFaC1xlsmP47jPIiGDlteB8rTMG14d-HEm7QXT-k88SpNc04j_wzzOeXtkt1EGg_h7r8L1rw8N9WbqL9e36t1LciuUOhSSaVWxlmpStP34I33wcbg0YE1JUjlnC87FdFoizFapK63UjofqUPQC_bwt72a230edpQv7a-9vdr1D7fFPNE</addsrcrecordid><sourcetype>Open Access Repository</sourcetype><iscdi>true</iscdi><recordtype>article</recordtype></control><display><type>article</type><title>Multi-Task Learning by a Top-Down Control Network</title><source>arXiv.org</source><creator>Levi, Hila ; Ullman, Shimon</creator><creatorcontrib>Levi, Hila ; Ullman, Shimon</creatorcontrib><description>As the range of tasks performed by a general vision system expands, executing multiple tasks accurately and efficiently in a single network has become an important and still open problem. Recent computer vision approaches address this problem by branching networks, or by a channel-wise modulation of the network feature-maps with task specific vectors. We present a novel architecture that uses a dedicated top-down control network to modify the activation of all the units in the main recognition network in a manner that depends on the selected task, image content, and spatial location. We show the effectiveness of our scheme by achieving significantly better results than alternative state-of-the-art approaches on four datasets. We further demonstrate our advantages in terms of task selectivity, scaling the number of tasks and interpretability.</description><identifier>DOI: 10.48550/arxiv.2002.03335</identifier><language>eng</language><subject>Computer Science - Computer Vision and Pattern Recognition ; Computer Science - Learning ; Statistics - Machine Learning</subject><creationdate>2020-02</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/2002.03335$$EView_record_in_Cornell_University$$FView_record_in_$$GCornell_University$$Hfree_for_read</linktorsrc><backlink>$$Uhttps://doi.org/10.48550/arXiv.2002.03335$$DView paper in arXiv$$Hfree_for_read</backlink></links><search><creatorcontrib>Levi, Hila</creatorcontrib><creatorcontrib>Ullman, Shimon</creatorcontrib><title>Multi-Task Learning by a Top-Down Control Network</title><description>As the range of tasks performed by a general vision system expands, executing multiple tasks accurately and efficiently in a single network has become an important and still open problem. Recent computer vision approaches address this problem by branching networks, or by a channel-wise modulation of the network feature-maps with task specific vectors. We present a novel architecture that uses a dedicated top-down control network to modify the activation of all the units in the main recognition network in a manner that depends on the selected task, image content, and spatial location. We show the effectiveness of our scheme by achieving significantly better results than alternative state-of-the-art approaches on four datasets. We further demonstrate our advantages in terms of task selectivity, scaling the number of tasks and interpretability.</description><subject>Computer Science - Computer Vision and Pattern Recognition</subject><subject>Computer Science - Learning</subject><subject>Statistics - Machine Learning</subject><fulltext>true</fulltext><rsrctype>article</rsrctype><creationdate>2020</creationdate><recordtype>article</recordtype><sourceid>GOX</sourceid><recordid>eNotzrtOwzAUgGEvDKjlAZjwCzgcX47rjFW4SgGW7NFJbFdR07hy05a-PaIw_duvj7F7CYVxiPBI-Xs4FQpAFaC1xlsmP47jPIiGDlteB8rTMG14d-HEm7QXT-k88SpNc04j_wzzOeXtkt1EGg_h7r8L1rw8N9WbqL9e36t1LciuUOhSSaVWxlmpStP34I33wcbg0YE1JUjlnC87FdFoizFapK63UjofqUPQC_bwt72a230edpQv7a-9vdr1D7fFPNE</recordid><startdate>20200209</startdate><enddate>20200209</enddate><creator>Levi, Hila</creator><creator>Ullman, Shimon</creator><scope>AKY</scope><scope>EPD</scope><scope>GOX</scope></search><sort><creationdate>20200209</creationdate><title>Multi-Task Learning by a Top-Down Control Network</title><author>Levi, Hila ; Ullman, Shimon</author></sort><facets><frbrtype>5</frbrtype><frbrgroupid>cdi_FETCH-LOGICAL-a675-39212274861294cc0d4dde6fed58064901288d9b2f54365ff65abc6118dfab503</frbrgroupid><rsrctype>articles</rsrctype><prefilter>articles</prefilter><language>eng</language><creationdate>2020</creationdate><topic>Computer Science - Computer Vision and Pattern Recognition</topic><topic>Computer Science - Learning</topic><topic>Statistics - Machine Learning</topic><toplevel>online_resources</toplevel><creatorcontrib>Levi, Hila</creatorcontrib><creatorcontrib>Ullman, Shimon</creatorcontrib><collection>arXiv Computer Science</collection><collection>arXiv Statistics</collection><collection>arXiv.org</collection></facets><delivery><delcategory>Remote Search Resource</delcategory><fulltext>fulltext_linktorsrc</fulltext></delivery><addata><au>Levi, Hila</au><au>Ullman, Shimon</au><format>journal</format><genre>article</genre><ristype>JOUR</ristype><atitle>Multi-Task Learning by a Top-Down Control Network</atitle><date>2020-02-09</date><risdate>2020</risdate><abstract>As the range of tasks performed by a general vision system expands, executing multiple tasks accurately and efficiently in a single network has become an important and still open problem. Recent computer vision approaches address this problem by branching networks, or by a channel-wise modulation of the network feature-maps with task specific vectors. We present a novel architecture that uses a dedicated top-down control network to modify the activation of all the units in the main recognition network in a manner that depends on the selected task, image content, and spatial location. We show the effectiveness of our scheme by achieving significantly better results than alternative state-of-the-art approaches on four datasets. We further demonstrate our advantages in terms of task selectivity, scaling the number of tasks and interpretability.</abstract><doi>10.48550/arxiv.2002.03335</doi><oa>free_for_read</oa></addata></record>
fulltext fulltext_linktorsrc
identifier DOI: 10.48550/arxiv.2002.03335
ispartof
issn
language eng
recordid cdi_arxiv_primary_2002_03335
source arXiv.org
subjects Computer Science - Computer Vision and Pattern Recognition
Computer Science - Learning
Statistics - Machine Learning
title Multi-Task Learning by a Top-Down Control Network
url https://sfx.bib-bvb.de/sfx_tum?ctx_ver=Z39.88-2004&ctx_enc=info:ofi/enc:UTF-8&ctx_tim=2025-01-11T12%3A17%3A34IST&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=Multi-Task%20Learning%20by%20a%20Top-Down%20Control%20Network&rft.au=Levi,%20Hila&rft.date=2020-02-09&rft_id=info:doi/10.48550/arxiv.2002.03335&rft_dat=%3Carxiv_GOX%3E2002_03335%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