Finding Task-Relevant Features for Few-Shot Learning by Category Traversal

Few-shot learning is an important area of research. Conceptually, humans are readily able to understand new concepts given just a few examples, while in more pragmatic terms, limited-example training situations are common practice. Recent effective approaches to few-shot learning employ a metric-lea...

Ausführliche Beschreibung

Gespeichert in:
Bibliographische Detailangaben
Veröffentlicht in:Proceedings (IEEE Computer Society Conference on Computer Vision and Pattern Recognition. Online) S. 1 - 10
Hauptverfasser: Li, Hongyang, Eigen, David, Dodge, Samuel, Zeiler, Matthew, Wang, Xiaogang
Format: Tagungsbericht
Sprache:Englisch
Veröffentlicht: IEEE 01.06.2019
Schlagworte:
ISSN:1063-6919
Online-Zugang:Volltext
Tags: Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
Abstract Few-shot learning is an important area of research. Conceptually, humans are readily able to understand new concepts given just a few examples, while in more pragmatic terms, limited-example training situations are common practice. Recent effective approaches to few-shot learning employ a metric-learning framework to learn a feature similarity comparison between a query (test) example, and the few support (training) examples. However, these approaches treat each support class independently from one another, never looking at the entire task as a whole. Because of this, they are constrained to use a single set of features for all possible test-time tasks, which hinders the ability to distinguish the most relevant dimensions for the task at hand. In this work, we introduce a Category Traversal Module that can be inserted as a plug-and-play module into most metric-learning based few-shot learners. This component traverses across the entire support set at once, identifying task-relevant features based on both intra-class commonality and inter-class uniqueness in the feature space. Incorporating our module improves performance considerably (5%-10% relative) over baseline systems on both miniImageNet and tieredImageNet benchmarks, with overall performance competitive with the most recent state-of-the-art systems.
AbstractList Few-shot learning is an important area of research. Conceptually, humans are readily able to understand new concepts given just a few examples, while in more pragmatic terms, limited-example training situations are common practice. Recent effective approaches to few-shot learning employ a metric-learning framework to learn a feature similarity comparison between a query (test) example, and the few support (training) examples. However, these approaches treat each support class independently from one another, never looking at the entire task as a whole. Because of this, they are constrained to use a single set of features for all possible test-time tasks, which hinders the ability to distinguish the most relevant dimensions for the task at hand. In this work, we introduce a Category Traversal Module that can be inserted as a plug-and-play module into most metric-learning based few-shot learners. This component traverses across the entire support set at once, identifying task-relevant features based on both intra-class commonality and inter-class uniqueness in the feature space. Incorporating our module improves performance considerably (5%-10% relative) over baseline systems on both miniImageNet and tieredImageNet benchmarks, with overall performance competitive with the most recent state-of-the-art systems.
Author Eigen, David
Wang, Xiaogang
Li, Hongyang
Dodge, Samuel
Zeiler, Matthew
Author_xml – sequence: 1
  givenname: Hongyang
  surname: Li
  fullname: Li, Hongyang
  organization: The Chinese Univ. of Hong Kong
– sequence: 2
  givenname: David
  surname: Eigen
  fullname: Eigen, David
  organization: Clarifai Inc
– sequence: 3
  givenname: Samuel
  surname: Dodge
  fullname: Dodge, Samuel
  organization: Clarifai Inc
– sequence: 4
  givenname: Matthew
  surname: Zeiler
  fullname: Zeiler, Matthew
  organization: Clarifai Inc
– sequence: 5
  givenname: Xiaogang
  surname: Wang
  fullname: Wang, Xiaogang
  organization: Chinese Univ. of Hong Kong
BookMark eNotjMFOhEAQREejievK2YMXfgCcnlmG6aMhsmpINCt63TROs6IIZsA1_L0YrUulXl7qVBx1fcdCnIOMASReZs8Pm1hJwFjOwQMRYGohVRa0Qm0PxQKk0ZFBwBMRDMPbbGkFYNAuxF3edK7pdmFJw3u04Zb31I1hzjR-eR7Cuvfz-I4eX_sxLJh89ytXU5jRyLveT2Hpac9-oPZMHNfUDhz891I85ddldhMV9-vb7KqIGiX1GNXGvBhCp5105BKLBKo2CitklKlcWTY25TpRypKuIHHOzTShxGisrU71Ulz8_TbMvP30zQf5aWsxWcHs_AAlkE5s
ContentType Conference Proceeding
DBID 6IE
6IH
CBEJK
RIE
RIO
DOI 10.1109/CVPR.2019.00009
DatabaseName IEEE Electronic Library (IEL) Conference Proceedings
IEEE Proceedings Order Plan (POP) 1998-present by volume
IEEE Xplore All Conference Proceedings
IEEE/IET Electronic Library (IEL) (UW System Shared)
IEEE Proceedings Order Plans (POP) 1998-present
DatabaseTitleList
Database_xml – sequence: 1
  dbid: RIE
  name: IEEE/IET Electronic Library
  url: https://ieeexplore.ieee.org/
  sourceTypes: Publisher
DeliveryMethod fulltext_linktorsrc
Discipline Applied Sciences
EISBN 9781728132938
1728132932
EISSN 1063-6919
EndPage 10
ExternalDocumentID 8954156
Genre orig-research
GroupedDBID 6IE
6IH
6IL
6IN
AAWTH
ABLEC
ADZIZ
ALMA_UNASSIGNED_HOLDINGS
BEFXN
BFFAM
BGNUA
BKEBE
BPEOZ
CBEJK
CHZPO
IEGSK
IJVOP
OCL
RIE
RIL
RIO
ID FETCH-LOGICAL-i203t-f66c6a9d3d0dad589a12f629b9e907048e687ef5228a3b15ddd7045a5639f8373
IEDL.DBID RIE
ISICitedReferencesCount 239
ISICitedReferencesURI http://www.webofscience.com/api/gateway?GWVersion=2&SrcApp=Summon&SrcAuth=ProQuest&DestLinkType=CitingArticles&DestApp=WOS_CPL&KeyUT=000529484000001&url=https%3A%2F%2Fcvtisr.summon.serialssolutions.com%2F%23%21%2Fsearch%3Fho%3Df%26include.ft.matches%3Dt%26l%3Dnull%26q%3D
IngestDate Wed Aug 27 07:39:11 EDT 2025
IsPeerReviewed false
IsScholarly true
Language English
LinkModel DirectLink
MergedId FETCHMERGED-LOGICAL-i203t-f66c6a9d3d0dad589a12f629b9e907048e687ef5228a3b15ddd7045a5639f8373
PageCount 10
ParticipantIDs ieee_primary_8954156
PublicationCentury 2000
PublicationDate 2019-June
PublicationDateYYYYMMDD 2019-06-01
PublicationDate_xml – month: 06
  year: 2019
  text: 2019-June
PublicationDecade 2010
PublicationTitle Proceedings (IEEE Computer Society Conference on Computer Vision and Pattern Recognition. Online)
PublicationTitleAbbrev CVPR
PublicationYear 2019
Publisher IEEE
Publisher_xml – name: IEEE
SSID ssj0003211698
Score 2.6121964
Snippet Few-shot learning is an important area of research. Conceptually, humans are readily able to understand new concepts given just a few examples, while in more...
SourceID ieee
SourceType Publisher
StartPage 1
SubjectTerms Benchmark testing
Computer vision
Deep Learning
Feature extraction
Few shot learning
Hands
Pattern recognition
Pragmatics
Training
Title Finding Task-Relevant Features for Few-Shot Learning by Category Traversal
URI https://ieeexplore.ieee.org/document/8954156
WOSCitedRecordID wos000529484000001&url=https%3A%2F%2Fcvtisr.summon.serialssolutions.com%2F%23%21%2Fsearch%3Fho%3Df%26include.ft.matches%3Dt%26l%3Dnull%26q%3D
hasFullText 1
inHoldings 1
isFullTextHit
isPrint
link http://cvtisr.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwlV3LSgMxFL20xYUrH634JguXxs4zj3WxiEgptUp3JcnNaFE6MjNV-vcm06EiuHE3ySZwhpBzknvOBbiSoeEmRKQ-nY4mhmmqRWYpYyJCxQOjs9oo_MBHIzGbyXELrrdeGGttXXxmb_xn_ZaPuVn5q7K-kKnXG21oc843Xq3tfUrslAyToknvCQPZHzyPJ752S9YZhfJX-5T69Bju_W_dfej92PDIeHvAHEDLLg9hr-GNpNmVZRfuh4vam0KmqnyjE-8Yd3gRz-5WTk0Tx0vd4Is-vuYVaQJVX4hek4GPiciLNZn6JkRFqd578DS8nQ7uaNMjgS6iIK5oxphhSmKMASpMhVRhlLFIammd7HXb0zLBbeZYllCxDlNEdLOpSh0zyZw4jY-gs8yX9hiIUcyhaJSS3CZOhWgnhiwyTHiqZBLgCXQ9NPOPTQzGvEHl9O_pM9j12G-qqs6hUxUrewE75rNalMVl_e--AXvmm3Q
linkProvider IEEE
linkToHtml http://cvtisr.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwlV1NSwMxEB1qFfRUtRW_zcGjsfuVbHIulqq1lLpKbyWbZHVRurK7VfrvTbZLRfDiLcklMCHMe8m8NwCX3JWhdJXC1p0OB5LGOGaJxpQyT4nQkXFSCYWH4WjEplM-bsDVWgujta6Kz_S1HVZ_-SqTC_tU1mWcWL6xAZskCDx3pdZav6j4hstQzmr_Htfh3d7zeGKrt3jlUsh_NVCp8ke_9b-dd6HzI8RD43WK2YOGnu9Dq0aOqL6XRRvu-mmlTkGRKN7wxGrGTcSQxXcLw6eRQaZm8oUfX7MS1ZaqLyheop41isjyJYpsG6K8EO8deOrfRL0Brrsk4NRz_BInlEoquPKVo4QijAvXS6jHY64N8TUXVFMW6sTgLCb82CVKKbNKBDHYJDH01D-A5jyb60NAUlATRSkED3VgeEhs6JBWVAUhETxw1BG0bWhmHysjjFkdleO_ly9gexA9DGfD29H9CezYc1jVWJ1Cs8wX-gy25GeZFvl5dY7fwlCeuw
openUrl ctx_ver=Z39.88-2004&ctx_enc=info%3Aofi%2Fenc%3AUTF-8&rfr_id=info%3Asid%2Fsummon.serialssolutions.com&rft_val_fmt=info%3Aofi%2Ffmt%3Akev%3Amtx%3Abook&rft.genre=proceeding&rft.title=Proceedings+%28IEEE+Computer+Society+Conference+on+Computer+Vision+and+Pattern+Recognition.+Online%29&rft.atitle=Finding+Task-Relevant+Features+for+Few-Shot+Learning+by+Category+Traversal&rft.au=Li%2C+Hongyang&rft.au=Eigen%2C+David&rft.au=Dodge%2C+Samuel&rft.au=Zeiler%2C+Matthew&rft.date=2019-06-01&rft.pub=IEEE&rft.eissn=1063-6919&rft.spage=1&rft.epage=10&rft_id=info:doi/10.1109%2FCVPR.2019.00009&rft.externalDocID=8954156