Loading…

Dual selective knowledge transfer for few-shot classification

Few-shot learning aims at recognizing novel visual categories from very few labelled examples. Different from the existing few-shot classification methods that are mainly based on metric learning or meta-learning, in this work we focus on improving the representation capacity of feature extractors....

Full description

Saved in:
Bibliographic Details
Published in:Applied intelligence (Dordrecht, Netherlands) Netherlands), 2023-11, Vol.53 (22), p.27779-27789
Main Authors: He, Kai, Pu, Nan, Lao, Mingrui, Bakker, Erwin M., Lew, Michael S.
Format: Article
Language:English
Subjects:
Citations: Items that this one cites
Online Access:Get full text
Tags: Add Tag
No Tags, Be the first to tag this record!
cited_by
cites cdi_FETCH-LOGICAL-c314t-aa9125bd9348575f18d74dd0a4c3428874e09f662c0557f87234a14f0d482bc83
container_end_page 27789
container_issue 22
container_start_page 27779
container_title Applied intelligence (Dordrecht, Netherlands)
container_volume 53
creator He, Kai
Pu, Nan
Lao, Mingrui
Bakker, Erwin M.
Lew, Michael S.
description Few-shot learning aims at recognizing novel visual categories from very few labelled examples. Different from the existing few-shot classification methods that are mainly based on metric learning or meta-learning, in this work we focus on improving the representation capacity of feature extractors. For this purpose, we propose a new two-stage dual selective knowledge transfer (DSKT) framework, to guide models towards better optimization. Specifically, we first exploit an improved multi-task learning approach to train a feature extractor with robust representation capability as a teacher model. Then, we design an effective dual selective knowledge distillation method, which enables the student model to selectively learn knowledge from the teacher model and current samples, thereby improving the student model’s ability to generalize on unseen classes. Extensive experimental results show that our DSKT achieves competitive performances on four well-known few-shot classification benchmarks.
doi_str_mv 10.1007/s10489-023-04994-7
format article
fullrecord <record><control><sourceid>proquest_cross</sourceid><recordid>TN_cdi_proquest_journals_2881542624</recordid><sourceformat>XML</sourceformat><sourcesystem>PC</sourcesystem><sourcerecordid>2881542624</sourcerecordid><originalsourceid>FETCH-LOGICAL-c314t-aa9125bd9348575f18d74dd0a4c3428874e09f662c0557f87234a14f0d482bc83</originalsourceid><addsrcrecordid>eNp9kMFKAzEURYMoWKs_4GrAdfQleZkkCxdSrQoFNwruQppJ6tRxpiZTi3_v6AjuXDzu5p774BByyuCcAaiLzAC1ocAFBTQGqdojEyaVoAqN2icTMBxpWZrnQ3KU8xoAhAA2IZfXW9cUOTTB9_VHKF7bbteEahWKPrk2x5CK2A0XdjS_dH3hG5dzHWvv-rprj8lBdE0OJ785JU_zm8fZHV083N7PrhbUC4Y9dc4wLpeVEailkpHpSmFVgUMvkGutMICJZck9SKmiVlygYxihQs2XXospORt3N6l734bc23W3Te3w0g44k8hLjkOLjy2fupxTiHaT6jeXPi0D-63JjprsoMn-aLJqgMQI5aHcrkL6m_6H-gJ1WGm9</addsrcrecordid><sourcetype>Aggregation Database</sourcetype><iscdi>true</iscdi><recordtype>article</recordtype><pqid>2881542624</pqid></control><display><type>article</type><title>Dual selective knowledge transfer for few-shot classification</title><source>ABI/INFORM global</source><source>Springer Nature</source><creator>He, Kai ; Pu, Nan ; Lao, Mingrui ; Bakker, Erwin M. ; Lew, Michael S.</creator><creatorcontrib>He, Kai ; Pu, Nan ; Lao, Mingrui ; Bakker, Erwin M. ; Lew, Michael S.</creatorcontrib><description>Few-shot learning aims at recognizing novel visual categories from very few labelled examples. Different from the existing few-shot classification methods that are mainly based on metric learning or meta-learning, in this work we focus on improving the representation capacity of feature extractors. For this purpose, we propose a new two-stage dual selective knowledge transfer (DSKT) framework, to guide models towards better optimization. Specifically, we first exploit an improved multi-task learning approach to train a feature extractor with robust representation capability as a teacher model. Then, we design an effective dual selective knowledge distillation method, which enables the student model to selectively learn knowledge from the teacher model and current samples, thereby improving the student model’s ability to generalize on unseen classes. Extensive experimental results show that our DSKT achieves competitive performances on four well-known few-shot classification benchmarks.</description><identifier>ISSN: 0924-669X</identifier><identifier>EISSN: 1573-7497</identifier><identifier>DOI: 10.1007/s10489-023-04994-7</identifier><language>eng</language><publisher>New York: Springer US</publisher><subject>Artificial Intelligence ; Classification ; Computer Science ; Datasets ; Deep learning ; Distillation ; Feature extraction ; Knowledge ; Knowledge management ; Learning ; Machines ; Manufacturing ; Mechanical Engineering ; Optimization ; Processes ; Representations ; Teachers</subject><ispartof>Applied intelligence (Dordrecht, Netherlands), 2023-11, Vol.53 (22), p.27779-27789</ispartof><rights>The Author(s) 2023</rights><rights>The Author(s) 2023. 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><lds50>peer_reviewed</lds50><oa>free_for_read</oa><woscitedreferencessubscribed>false</woscitedreferencessubscribed><cites>FETCH-LOGICAL-c314t-aa9125bd9348575f18d74dd0a4c3428874e09f662c0557f87234a14f0d482bc83</cites><orcidid>0000-0002-6035-7787</orcidid></display><links><openurl>$$Topenurl_article</openurl><openurlfulltext>$$Topenurlfull_article</openurlfulltext><thumbnail>$$Tsyndetics_thumb_exl</thumbnail><linktopdf>$$Uhttps://www.proquest.com/docview/2881542624/fulltextPDF?pq-origsite=primo$$EPDF$$P50$$Gproquest$$H</linktopdf><linktohtml>$$Uhttps://www.proquest.com/docview/2881542624?pq-origsite=primo$$EHTML$$P50$$Gproquest$$H</linktohtml><link.rule.ids>314,780,784,11688,27924,27925,36060,44363,74895</link.rule.ids></links><search><creatorcontrib>He, Kai</creatorcontrib><creatorcontrib>Pu, Nan</creatorcontrib><creatorcontrib>Lao, Mingrui</creatorcontrib><creatorcontrib>Bakker, Erwin M.</creatorcontrib><creatorcontrib>Lew, Michael S.</creatorcontrib><title>Dual selective knowledge transfer for few-shot classification</title><title>Applied intelligence (Dordrecht, Netherlands)</title><addtitle>Appl Intell</addtitle><description>Few-shot learning aims at recognizing novel visual categories from very few labelled examples. Different from the existing few-shot classification methods that are mainly based on metric learning or meta-learning, in this work we focus on improving the representation capacity of feature extractors. For this purpose, we propose a new two-stage dual selective knowledge transfer (DSKT) framework, to guide models towards better optimization. Specifically, we first exploit an improved multi-task learning approach to train a feature extractor with robust representation capability as a teacher model. Then, we design an effective dual selective knowledge distillation method, which enables the student model to selectively learn knowledge from the teacher model and current samples, thereby improving the student model’s ability to generalize on unseen classes. Extensive experimental results show that our DSKT achieves competitive performances on four well-known few-shot classification benchmarks.</description><subject>Artificial Intelligence</subject><subject>Classification</subject><subject>Computer Science</subject><subject>Datasets</subject><subject>Deep learning</subject><subject>Distillation</subject><subject>Feature extraction</subject><subject>Knowledge</subject><subject>Knowledge management</subject><subject>Learning</subject><subject>Machines</subject><subject>Manufacturing</subject><subject>Mechanical Engineering</subject><subject>Optimization</subject><subject>Processes</subject><subject>Representations</subject><subject>Teachers</subject><issn>0924-669X</issn><issn>1573-7497</issn><fulltext>true</fulltext><rsrctype>article</rsrctype><creationdate>2023</creationdate><recordtype>article</recordtype><sourceid>M0C</sourceid><recordid>eNp9kMFKAzEURYMoWKs_4GrAdfQleZkkCxdSrQoFNwruQppJ6tRxpiZTi3_v6AjuXDzu5p774BByyuCcAaiLzAC1ocAFBTQGqdojEyaVoAqN2icTMBxpWZrnQ3KU8xoAhAA2IZfXW9cUOTTB9_VHKF7bbteEahWKPrk2x5CK2A0XdjS_dH3hG5dzHWvv-rprj8lBdE0OJ785JU_zm8fZHV083N7PrhbUC4Y9dc4wLpeVEailkpHpSmFVgUMvkGutMICJZck9SKmiVlygYxihQs2XXospORt3N6l734bc23W3Te3w0g44k8hLjkOLjy2fupxTiHaT6jeXPi0D-63JjprsoMn-aLJqgMQI5aHcrkL6m_6H-gJ1WGm9</recordid><startdate>20231101</startdate><enddate>20231101</enddate><creator>He, Kai</creator><creator>Pu, Nan</creator><creator>Lao, Mingrui</creator><creator>Bakker, Erwin M.</creator><creator>Lew, Michael S.</creator><general>Springer US</general><general>Springer Nature B.V</general><scope>C6C</scope><scope>AAYXX</scope><scope>CITATION</scope><scope>3V.</scope><scope>7SC</scope><scope>7WY</scope><scope>7WZ</scope><scope>7XB</scope><scope>87Z</scope><scope>8AL</scope><scope>8FD</scope><scope>8FE</scope><scope>8FG</scope><scope>8FK</scope><scope>8FL</scope><scope>ABJCF</scope><scope>ABUWG</scope><scope>AFKRA</scope><scope>ARAPS</scope><scope>AZQEC</scope><scope>BENPR</scope><scope>BEZIV</scope><scope>BGLVJ</scope><scope>CCPQU</scope><scope>DWQXO</scope><scope>FRNLG</scope><scope>F~G</scope><scope>GNUQQ</scope><scope>HCIFZ</scope><scope>JQ2</scope><scope>K60</scope><scope>K6~</scope><scope>K7-</scope><scope>L.-</scope><scope>L6V</scope><scope>L7M</scope><scope>L~C</scope><scope>L~D</scope><scope>M0C</scope><scope>M0N</scope><scope>M7S</scope><scope>P5Z</scope><scope>P62</scope><scope>PQBIZ</scope><scope>PQBZA</scope><scope>PQEST</scope><scope>PQQKQ</scope><scope>PQUKI</scope><scope>PSYQQ</scope><scope>PTHSS</scope><scope>Q9U</scope><orcidid>https://orcid.org/0000-0002-6035-7787</orcidid></search><sort><creationdate>20231101</creationdate><title>Dual selective knowledge transfer for few-shot classification</title><author>He, Kai ; Pu, Nan ; Lao, Mingrui ; Bakker, Erwin M. ; Lew, Michael S.</author></sort><facets><frbrtype>5</frbrtype><frbrgroupid>cdi_FETCH-LOGICAL-c314t-aa9125bd9348575f18d74dd0a4c3428874e09f662c0557f87234a14f0d482bc83</frbrgroupid><rsrctype>articles</rsrctype><prefilter>articles</prefilter><language>eng</language><creationdate>2023</creationdate><topic>Artificial Intelligence</topic><topic>Classification</topic><topic>Computer Science</topic><topic>Datasets</topic><topic>Deep learning</topic><topic>Distillation</topic><topic>Feature extraction</topic><topic>Knowledge</topic><topic>Knowledge management</topic><topic>Learning</topic><topic>Machines</topic><topic>Manufacturing</topic><topic>Mechanical Engineering</topic><topic>Optimization</topic><topic>Processes</topic><topic>Representations</topic><topic>Teachers</topic><toplevel>peer_reviewed</toplevel><toplevel>online_resources</toplevel><creatorcontrib>He, Kai</creatorcontrib><creatorcontrib>Pu, Nan</creatorcontrib><creatorcontrib>Lao, Mingrui</creatorcontrib><creatorcontrib>Bakker, Erwin M.</creatorcontrib><creatorcontrib>Lew, Michael S.</creatorcontrib><collection>SpringerOpen</collection><collection>CrossRef</collection><collection>ProQuest Central (Corporate)</collection><collection>Computer and Information Systems Abstracts</collection><collection>ProQuest_ABI/INFORM Collection</collection><collection>ABI/INFORM Global (PDF only)</collection><collection>ProQuest Central (purchase pre-March 2016)</collection><collection>ABI/INFORM Collection</collection><collection>Computing Database (Alumni Edition)</collection><collection>Technology Research Database</collection><collection>ProQuest SciTech Collection</collection><collection>ProQuest Technology Collection</collection><collection>ProQuest Central (Alumni) (purchase pre-March 2016)</collection><collection>ABI/INFORM Collection (Alumni Edition)</collection><collection>Materials Science &amp; Engineering Collection</collection><collection>ProQuest Central (Alumni)</collection><collection>ProQuest Central</collection><collection>Advanced Technologies &amp; Aerospace Database‎ (1962 - current)</collection><collection>ProQuest Central</collection><collection>AUTh Library subscriptions: ProQuest Central</collection><collection>ProQuest Business Premium Collection</collection><collection>Technology Collection</collection><collection>ProQuest One Community College</collection><collection>ProQuest Central</collection><collection>Business Premium Collection (Alumni)</collection><collection>ABI/INFORM Global (Corporate)</collection><collection>ProQuest Central Student</collection><collection>SciTech Premium Collection</collection><collection>ProQuest Computer Science Collection</collection><collection>ProQuest Business Collection (Alumni Edition)</collection><collection>ProQuest Business Collection</collection><collection>Computer science database</collection><collection>ABI/INFORM Professional Advanced</collection><collection>ProQuest Engineering Collection</collection><collection>Advanced Technologies Database with Aerospace</collection><collection>Computer and Information Systems Abstracts – Academic</collection><collection>Computer and Information Systems Abstracts Professional</collection><collection>ABI/INFORM global</collection><collection>Computing Database</collection><collection>Engineering Database</collection><collection>ProQuest advanced technologies &amp; aerospace journals</collection><collection>ProQuest Advanced Technologies &amp; Aerospace Collection</collection><collection>One Business (ProQuest)</collection><collection>ProQuest One Business (Alumni)</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 One Psychology</collection><collection>Engineering collection</collection><collection>ProQuest Central Basic</collection><jtitle>Applied intelligence (Dordrecht, Netherlands)</jtitle></facets><delivery><delcategory>Remote Search Resource</delcategory><fulltext>fulltext</fulltext></delivery><addata><au>He, Kai</au><au>Pu, Nan</au><au>Lao, Mingrui</au><au>Bakker, Erwin M.</au><au>Lew, Michael S.</au><format>journal</format><genre>article</genre><ristype>JOUR</ristype><atitle>Dual selective knowledge transfer for few-shot classification</atitle><jtitle>Applied intelligence (Dordrecht, Netherlands)</jtitle><stitle>Appl Intell</stitle><date>2023-11-01</date><risdate>2023</risdate><volume>53</volume><issue>22</issue><spage>27779</spage><epage>27789</epage><pages>27779-27789</pages><issn>0924-669X</issn><eissn>1573-7497</eissn><abstract>Few-shot learning aims at recognizing novel visual categories from very few labelled examples. Different from the existing few-shot classification methods that are mainly based on metric learning or meta-learning, in this work we focus on improving the representation capacity of feature extractors. For this purpose, we propose a new two-stage dual selective knowledge transfer (DSKT) framework, to guide models towards better optimization. Specifically, we first exploit an improved multi-task learning approach to train a feature extractor with robust representation capability as a teacher model. Then, we design an effective dual selective knowledge distillation method, which enables the student model to selectively learn knowledge from the teacher model and current samples, thereby improving the student model’s ability to generalize on unseen classes. Extensive experimental results show that our DSKT achieves competitive performances on four well-known few-shot classification benchmarks.</abstract><cop>New York</cop><pub>Springer US</pub><doi>10.1007/s10489-023-04994-7</doi><tpages>11</tpages><orcidid>https://orcid.org/0000-0002-6035-7787</orcidid><oa>free_for_read</oa></addata></record>
fulltext fulltext
identifier ISSN: 0924-669X
ispartof Applied intelligence (Dordrecht, Netherlands), 2023-11, Vol.53 (22), p.27779-27789
issn 0924-669X
1573-7497
language eng
recordid cdi_proquest_journals_2881542624
source ABI/INFORM global; Springer Nature
subjects Artificial Intelligence
Classification
Computer Science
Datasets
Deep learning
Distillation
Feature extraction
Knowledge
Knowledge management
Learning
Machines
Manufacturing
Mechanical Engineering
Optimization
Processes
Representations
Teachers
title Dual selective knowledge transfer for few-shot classification
url http://sfxeu10.hosted.exlibrisgroup.com/loughborough?ctx_ver=Z39.88-2004&ctx_enc=info:ofi/enc:UTF-8&ctx_tim=2024-12-25T15%3A25%3A38IST&url_ver=Z39.88-2004&url_ctx_fmt=infofi/fmt:kev:mtx:ctx&rfr_id=info:sid/primo.exlibrisgroup.com:primo3-Article-proquest_cross&rft_val_fmt=info:ofi/fmt:kev:mtx:journal&rft.genre=article&rft.atitle=Dual%20selective%20knowledge%20transfer%20for%20few-shot%20classification&rft.jtitle=Applied%20intelligence%20(Dordrecht,%20Netherlands)&rft.au=He,%20Kai&rft.date=2023-11-01&rft.volume=53&rft.issue=22&rft.spage=27779&rft.epage=27789&rft.pages=27779-27789&rft.issn=0924-669X&rft.eissn=1573-7497&rft_id=info:doi/10.1007/s10489-023-04994-7&rft_dat=%3Cproquest_cross%3E2881542624%3C/proquest_cross%3E%3Cgrp_id%3Ecdi_FETCH-LOGICAL-c314t-aa9125bd9348575f18d74dd0a4c3428874e09f662c0557f87234a14f0d482bc83%3C/grp_id%3E%3Coa%3E%3C/oa%3E%3Curl%3E%3C/url%3E&rft_id=info:oai/&rft_pqid=2881542624&rft_id=info:pmid/&rfr_iscdi=true