Generating Classification Weights With GNN Denoising Autoencoders for Few-Shot Learning

Given an initial recognition model already trained on a set of base classes, the goal of this work is to develop a meta-model for few-shot learning. The meta-model, given as input some novel classes with few training examples per class, must properly adapt the existing recognition model into a new m...

Full description

Saved in:
Bibliographic Details
Published in:Proceedings (IEEE Computer Society Conference on Computer Vision and Pattern Recognition. Online) pp. 21 - 30
Main Authors: Gidaris, Spyros, Komodakis, Nikos
Format: Conference Proceeding
Language:English
Published: IEEE 01.06.2019
Subjects:
ISSN:1063-6919
Online Access:Get full text
Tags: Add Tag
No Tags, Be the first to tag this record!
Abstract Given an initial recognition model already trained on a set of base classes, the goal of this work is to develop a meta-model for few-shot learning. The meta-model, given as input some novel classes with few training examples per class, must properly adapt the existing recognition model into a new model that can correctly classify in a unified way both the novel and the base classes. To accomplish this goal it must learn to output the appropriate classification weight vectors for those two types of classes. To build our meta-model we make use of two main innovations: we propose the use of a Denoising Autoencoder network (DAE) that (during training) takes as input a set of classification weights corrupted with Gaussian noise and learns to reconstruct the target-discriminative classification weights. In this case, the injected noise on the classification weights serves the role of regularizing the weight generating meta-model. Furthermore, in order to capture the co-dependencies between different classes in a given task instance of our meta-model, we propose to implement the DAE model as a Graph Neural Network (GNN). In order to verify the efficacy of our approach, we extensively evaluate it on ImageNet based few-shot benchmarks and we report state-of-the-art results.
AbstractList Given an initial recognition model already trained on a set of base classes, the goal of this work is to develop a meta-model for few-shot learning. The meta-model, given as input some novel classes with few training examples per class, must properly adapt the existing recognition model into a new model that can correctly classify in a unified way both the novel and the base classes. To accomplish this goal it must learn to output the appropriate classification weight vectors for those two types of classes. To build our meta-model we make use of two main innovations: we propose the use of a Denoising Autoencoder network (DAE) that (during training) takes as input a set of classification weights corrupted with Gaussian noise and learns to reconstruct the target-discriminative classification weights. In this case, the injected noise on the classification weights serves the role of regularizing the weight generating meta-model. Furthermore, in order to capture the co-dependencies between different classes in a given task instance of our meta-model, we propose to implement the DAE model as a Graph Neural Network (GNN). In order to verify the efficacy of our approach, we extensively evaluate it on ImageNet based few-shot benchmarks and we report state-of-the-art results.
Author Komodakis, Nikos
Gidaris, Spyros
Author_xml – sequence: 1
  givenname: Spyros
  surname: Gidaris
  fullname: Gidaris, Spyros
  organization: valeo.ai
– sequence: 2
  givenname: Nikos
  surname: Komodakis
  fullname: Komodakis, Nikos
  organization: ENPC, France
BookMark eNotzE1LAzEUheEoCtbatQs3-QNT700yk2RZRluFUsWvLktmetNGaiKTKeK_t6KrwwsP55ydxBSJsUuEMSLY6_rt8WksAO0YABCP2Mhqg1oYlMJKc8wGCJUsKov2jI1yfj8wKRArawZsOaNInetD3PB653IOPrSHTJEvKWy2febL0G_5bLHgNxRTyL9ysu8TxTatqcvcp45P6at43qaez8l18UAu2Kl3u0yj_x2y1-ntS31XzB9m9_VkXgQBsi_WxlOlpEMBrQIthFKtNSWZcq1N2ZgGwCjtG2UdSDJKKl36BtAr40B7L4fs6u83ENHqswsfrvteGVtKq4T8AenvUuo
ContentType Conference Proceeding
DBID 6IE
6IH
CBEJK
RIE
RIO
DOI 10.1109/CVPR.2019.00011
DatabaseName IEEE Electronic Library (IEL) Conference Proceedings
IEEE Proceedings Order Plan (POP) 1998-present by volume
IEEE Xplore All Conference Proceedings
IEEE Electronic Library (IEL)
IEEE Proceedings Order Plans (POP) 1998-present
DatabaseTitleList
Database_xml – sequence: 1
  dbid: RIE
  name: IEEE Electronic Library (IEL)
  url: https://ieeexplore.ieee.org/
  sourceTypes: Publisher
DeliveryMethod fulltext_linktorsrc
Discipline Applied Sciences
EISBN 9781728132938
1728132932
EISSN 1063-6919
EndPage 30
ExternalDocumentID 8953942
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-d8fe643a120c4072244c985e85d785b8b00847fb49a03e843475fb01f48a07ff3
IEDL.DBID RIE
ISICitedReferencesCount 201
ISICitedReferencesURI http://www.webofscience.com/api/gateway?GWVersion=2&SrcApp=Summon&SrcAuth=ProQuest&DestLinkType=CitingArticles&DestApp=WOS_CPL&KeyUT=000529484000003&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 07:44:55 EDT 2025
IsPeerReviewed false
IsScholarly true
Language English
LinkModel DirectLink
MergedId FETCHMERGED-LOGICAL-i203t-d8fe643a120c4072244c985e85d785b8b00847fb49a03e843475fb01f48a07ff3
PageCount 10
ParticipantIDs ieee_primary_8953942
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 2.563988
Snippet Given an initial recognition model already trained on a set of base classes, the goal of this work is to develop a meta-model for few-shot learning. The...
SourceID ieee
SourceType Publisher
StartPage 21
SubjectTerms Adaptation models
Autoencoders
Categorization
Computer architecture
Deep Learning
Few shot learning
Graph neural networks
Image reconstruction
Noise reduction
Recognition: Detection
Retrieval
Technological innovation
Training
Vectors
Title Generating Classification Weights With GNN Denoising Autoencoders for Few-Shot Learning
URI https://ieeexplore.ieee.org/document/8953942
WOSCitedRecordID wos000529484000003&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/eLvHCXMwlV09T8MwELVKxcBUoEV8ywMjpnbtxPaICoUpqvhqtyp2LjRLgtoU_j62ExUGFrbIimTpTuc7n9-9h9CV4QakZYJYChkR3IILqYwSBpxlYFLLQASxCZkkaj7X0w663s7CAEAAn8GN_wxv-VllN75VNlQ64lq4A3dHStnMam37KdzdZGKtWvYeRvVw_DZ98tgtT0hJvULQL_mUkD0mvf_tu48GP2N4eLpNMAeoA-Uh6rV1I26jct1Hs4Y72gOYcRC59PCfYHE8C53PNZ4V9RI_JAm-g7IqfH8A327qyrNYeiQzdqUrnsAXeV5WNW45V98H6HVy_zJ-JK1gAilGlNckUzm4CiNlI2o98ZlL3VarCFSUSRUZZTx7vsyN0CnloAQXMsoNZblQKZV5zo9Qt6xKOEbYec5FOjATRyNhdK7dv7GBWIGmPu-doL630-Kj4cRYtCY6_Xv5DO15RzQQq3PUrVcbuEC79rMu1qvL4Mhv06efmg
linkProvider IEEE
linkToHtml http://cvtisr.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwlV09T8MwELUqQIKpQIv4xgMjoXbtJPaICqWIElVQaLcqdi40S4LaFP4-thMVBha2yIpk6U7nO5_fvYfQpWIKQk25pwkkHmcaTEglxKPAaAIq1hS4E5sIo0hMp3LUQFfrWRgAcOAzuLaf7i0_KfTKtso6QvpMcnPgbvqcd2k1rbXuqDBzlwmkqPl7KJGd3tvo2aK3LCUlsRpBvwRUXP7oN_-38y5q_wzi4dE6xeyhBuT7qFlXjriOy2ULTSr2aAthxk7m0gKAnM3xxPU-l3iSlXN8H0X4FvIisx0CfLMqC8tjabHM2BSvuA9f3su8KHHNuvreRq_9u3Fv4NWSCV7WJaz0EpGCqTFi2iXaUp-Z5K2l8EH4SSh8JZTlzw9TxWVMGAjOeOinitCUi5iEacoO0EZe5HCIsPGdiXWgKvC7XMlUmn8DBYEASWzmO0Ita6fZR8WKMatNdPz38gXaHoyfhrPhQ_R4gnasUyrA1SnaKBcrOENb-rPMlotz59RvUR-i4Q
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=Generating+Classification+Weights+With+GNN+Denoising+Autoencoders+for+Few-Shot+Learning&rft.au=Gidaris%2C+Spyros&rft.au=Komodakis%2C+Nikos&rft.date=2019-06-01&rft.pub=IEEE&rft.eissn=1063-6919&rft.spage=21&rft.epage=30&rft_id=info:doi/10.1109%2FCVPR.2019.00011&rft.externalDocID=8953942