Self-Masking Networks for Unsupervised Adaptation
With the advent of billion-parameter foundation models, efficient fine-tuning has become increasingly important for the adaptation of models to downstream tasks. However, especially in computer vision, it can be hard to achieve good performance when access to quality labeled data is lacking. In this...
Gespeichert in:
Veröffentlicht in: | arXiv.org 2024-09 |
---|---|
Hauptverfasser: | , , |
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 | Alfonso Taboada Warmerdam Caron, Mathilde Asano, Yuki M |
description | With the advent of billion-parameter foundation models, efficient fine-tuning has become increasingly important for the adaptation of models to downstream tasks. However, especially in computer vision, it can be hard to achieve good performance when access to quality labeled data is lacking. In this work, we propose a method adapting pretrained generalist models in a self-supervised manner by learning binary masks. These self-supervised masking networks (SMNs) are up to 79x more efficient to store and significantly improve performance on label-efficient downstream tasks. We validate the usefulness of learning binary masks as a fine-tuning method on 8 datasets and 3 model architectures, and we demonstrate the effectiveness of SMNs in 3 label-efficient settings. |
format | Article |
fullrecord | <record><control><sourceid>proquest</sourceid><recordid>TN_cdi_proquest_journals_3104279200</recordid><sourceformat>XML</sourceformat><sourcesystem>PC</sourcesystem><sourcerecordid>3104279200</sourcerecordid><originalsourceid>FETCH-proquest_journals_31042792003</originalsourceid><addsrcrecordid>eNpjYuA0MjY21LUwMTLiYOAtLs4yMDAwMjM3MjU15mQwDE7NSdP1TSzOzsxLV_BLLSnPL8ouVkjLL1IIzSsuLUgtKsssTk1RcExJLChJLMnMz-NhYE1LzClO5YXS3AzKbq4hzh66BUX5haWpxSXxWfmlRXlAqXhjQwMTI3NLIwMDY-JUAQC60TOl</addsrcrecordid><sourcetype>Aggregation Database</sourcetype><iscdi>true</iscdi><recordtype>article</recordtype><pqid>3104279200</pqid></control><display><type>article</type><title>Self-Masking Networks for Unsupervised Adaptation</title><source>Free E- Journals</source><creator>Alfonso Taboada Warmerdam ; Caron, Mathilde ; Asano, Yuki M</creator><creatorcontrib>Alfonso Taboada Warmerdam ; Caron, Mathilde ; Asano, Yuki M</creatorcontrib><description>With the advent of billion-parameter foundation models, efficient fine-tuning has become increasingly important for the adaptation of models to downstream tasks. However, especially in computer vision, it can be hard to achieve good performance when access to quality labeled data is lacking. In this work, we propose a method adapting pretrained generalist models in a self-supervised manner by learning binary masks. These self-supervised masking networks (SMNs) are up to 79x more efficient to store and significantly improve performance on label-efficient downstream tasks. We validate the usefulness of learning binary masks as a fine-tuning method on 8 datasets and 3 model architectures, and we demonstrate the effectiveness of SMNs in 3 label-efficient settings.</description><identifier>EISSN: 2331-8422</identifier><language>eng</language><publisher>Ithaca: Cornell University Library, arXiv.org</publisher><subject>Adaptation ; Computer vision ; Labels ; Learning ; Masking ; Masks ; Performance enhancement</subject><ispartof>arXiv.org, 2024-09</ispartof><rights>2024. This work is published under http://creativecommons.org/licenses/by/4.0/ (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>780,784</link.rule.ids></links><search><creatorcontrib>Alfonso Taboada Warmerdam</creatorcontrib><creatorcontrib>Caron, Mathilde</creatorcontrib><creatorcontrib>Asano, Yuki M</creatorcontrib><title>Self-Masking Networks for Unsupervised Adaptation</title><title>arXiv.org</title><description>With the advent of billion-parameter foundation models, efficient fine-tuning has become increasingly important for the adaptation of models to downstream tasks. However, especially in computer vision, it can be hard to achieve good performance when access to quality labeled data is lacking. In this work, we propose a method adapting pretrained generalist models in a self-supervised manner by learning binary masks. These self-supervised masking networks (SMNs) are up to 79x more efficient to store and significantly improve performance on label-efficient downstream tasks. We validate the usefulness of learning binary masks as a fine-tuning method on 8 datasets and 3 model architectures, and we demonstrate the effectiveness of SMNs in 3 label-efficient settings.</description><subject>Adaptation</subject><subject>Computer vision</subject><subject>Labels</subject><subject>Learning</subject><subject>Masking</subject><subject>Masks</subject><subject>Performance enhancement</subject><issn>2331-8422</issn><fulltext>true</fulltext><rsrctype>article</rsrctype><creationdate>2024</creationdate><recordtype>article</recordtype><sourceid>ABUWG</sourceid><sourceid>AFKRA</sourceid><sourceid>AZQEC</sourceid><sourceid>BENPR</sourceid><sourceid>CCPQU</sourceid><sourceid>DWQXO</sourceid><recordid>eNpjYuA0MjY21LUwMTLiYOAtLs4yMDAwMjM3MjU15mQwDE7NSdP1TSzOzsxLV_BLLSnPL8ouVkjLL1IIzSsuLUgtKsssTk1RcExJLChJLMnMz-NhYE1LzClO5YXS3AzKbq4hzh66BUX5haWpxSXxWfmlRXlAqXhjQwMTI3NLIwMDY-JUAQC60TOl</recordid><startdate>20240911</startdate><enddate>20240911</enddate><creator>Alfonso Taboada Warmerdam</creator><creator>Caron, Mathilde</creator><creator>Asano, Yuki M</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>20240911</creationdate><title>Self-Masking Networks for Unsupervised Adaptation</title><author>Alfonso Taboada Warmerdam ; Caron, Mathilde ; Asano, Yuki M</author></sort><facets><frbrtype>5</frbrtype><frbrgroupid>cdi_FETCH-proquest_journals_31042792003</frbrgroupid><rsrctype>articles</rsrctype><prefilter>articles</prefilter><language>eng</language><creationdate>2024</creationdate><topic>Adaptation</topic><topic>Computer vision</topic><topic>Labels</topic><topic>Learning</topic><topic>Masking</topic><topic>Masks</topic><topic>Performance enhancement</topic><toplevel>online_resources</toplevel><creatorcontrib>Alfonso Taboada Warmerdam</creatorcontrib><creatorcontrib>Caron, Mathilde</creatorcontrib><creatorcontrib>Asano, Yuki M</creatorcontrib><collection>ProQuest SciTech Collection</collection><collection>ProQuest Technology Collection</collection><collection>Materials Science & 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>Access via ProQuest (Open Access)</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>Alfonso Taboada Warmerdam</au><au>Caron, Mathilde</au><au>Asano, Yuki M</au><format>book</format><genre>document</genre><ristype>GEN</ristype><atitle>Self-Masking Networks for Unsupervised Adaptation</atitle><jtitle>arXiv.org</jtitle><date>2024-09-11</date><risdate>2024</risdate><eissn>2331-8422</eissn><abstract>With the advent of billion-parameter foundation models, efficient fine-tuning has become increasingly important for the adaptation of models to downstream tasks. However, especially in computer vision, it can be hard to achieve good performance when access to quality labeled data is lacking. In this work, we propose a method adapting pretrained generalist models in a self-supervised manner by learning binary masks. These self-supervised masking networks (SMNs) are up to 79x more efficient to store and significantly improve performance on label-efficient downstream tasks. We validate the usefulness of learning binary masks as a fine-tuning method on 8 datasets and 3 model architectures, and we demonstrate the effectiveness of SMNs in 3 label-efficient settings.</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, 2024-09 |
issn | 2331-8422 |
language | eng |
recordid | cdi_proquest_journals_3104279200 |
source | Free E- Journals |
subjects | Adaptation Computer vision Labels Learning Masking Masks Performance enhancement |
title | Self-Masking Networks for Unsupervised Adaptation |
url | https://sfx.bib-bvb.de/sfx_tum?ctx_ver=Z39.88-2004&ctx_enc=info:ofi/enc:UTF-8&ctx_tim=2024-12-23T18%3A18%3A42IST&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=Self-Masking%20Networks%20for%20Unsupervised%20Adaptation&rft.jtitle=arXiv.org&rft.au=Alfonso%20Taboada%20Warmerdam&rft.date=2024-09-11&rft.eissn=2331-8422&rft_id=info:doi/&rft_dat=%3Cproquest%3E3104279200%3C/proquest%3E%3Curl%3E%3C/url%3E&disable_directlink=true&sfx.directlink=off&sfx.report_link=0&rft_id=info:oai/&rft_pqid=3104279200&rft_id=info:pmid/&rfr_iscdi=true |