A Relational Model for One-Shot Classification

Arturs Polis; Alexander Ilin

doi:10.14428/esann/2021.es2021-75

A Relational Model for One-Shot Classification

Tutkimustuotos: Artikkeli kirjassa/konferenssijulkaisussa › Conference contribution › Scientific › vertaisarvioitu

Abstrakti

We show that a deep learning model with built-in relational inductive bias can bring benefits to sample-efficient learning, without rely-ing on extensive data augmentation. The proposed one-shot classification model performs relational matching of a pair of inputs in the form of local and pairwise attention. Our approach solves perfectly the one-shot image classification Omniglot challenge. Our model exceeds human level accuracy, as well as the previous state of the art, with no data augmentation.

Alkuperäiskieli	Englanti
Otsikko	ESANN 2021 proceedings
Sivut	647-652
ISBN (elektroninen)	9782875870827
DOI - pysyväislinkit	https://doi.org/10.14428/esann/2021.es2021-75
Tila	Julkaistu - 2021
OKM-julkaisutyyppi	A4 Artikkeli konferenssijulkaisuussa
Tapahtuma	European Symposium on Artificial Neural Networks, Computational Intelligence and Machine Learning - Virtual, Online, Bruges, Belgia Kesto: 6 lokakuuta 2021 → 8 lokakuuta 2021 Konferenssinumero: 29

Conference

Conference	European Symposium on Artificial Neural Networks, Computational Intelligence and Machine Learning
Lyhennettä	ESANN
Maa/Alue	Belgia
Kaupunki	Bruges
Ajanjakso	06/10/2021 → 08/10/2021

Pääsy asiakirjaan

10.14428/esann/2021.es2021-75

https://arxiv.org/abs/2111.04313Lisenssi: CC BY

Muut tiedostot ja linkit

Science-IT
Mikko Hakala (Manager)
Perustieteiden korkeakoulu
Laitteistot/tilat: Facility

Siteeraa tätä

@inproceedings{c8c85ae777c646b5bc995eca3e0d86e1,

title = "A Relational Model for One-Shot Classification",

abstract = "We show that a deep learning model with built-in relational inductive bias can bring benefits to sample-efficient learning, without rely-ing on extensive data augmentation. The proposed one-shot classification model performs relational matching of a pair of inputs in the form of local and pairwise attention. Our approach solves perfectly the one-shot image classification Omniglot challenge. Our model exceeds human level accuracy, as well as the previous state of the art, with no data augmentation.",

author = "Arturs Polis and Alexander Ilin",

year = "2021",

doi = "10.14428/esann/2021.es2021-75",

language = "English",

pages = "647--652",

booktitle = "ESANN 2021 proceedings",

note = "European Symposium on Artificial Neural Networks, Computational Intelligence and Machine Learning, ESANN ; Conference date: 06-10-2021 Through 08-10-2021",

}

TY - GEN

T1 - A Relational Model for One-Shot Classification

AU - Polis, Arturs

AU - Ilin, Alexander

N1 - Conference code: 29

PY - 2021

Y1 - 2021

N2 - We show that a deep learning model with built-in relational inductive bias can bring benefits to sample-efficient learning, without rely-ing on extensive data augmentation. The proposed one-shot classification model performs relational matching of a pair of inputs in the form of local and pairwise attention. Our approach solves perfectly the one-shot image classification Omniglot challenge. Our model exceeds human level accuracy, as well as the previous state of the art, with no data augmentation.

AB - We show that a deep learning model with built-in relational inductive bias can bring benefits to sample-efficient learning, without rely-ing on extensive data augmentation. The proposed one-shot classification model performs relational matching of a pair of inputs in the form of local and pairwise attention. Our approach solves perfectly the one-shot image classification Omniglot challenge. Our model exceeds human level accuracy, as well as the previous state of the art, with no data augmentation.

UR - http://dx.doi.org/10.14428/esann/2021.es2021-75

UR - https://arxiv.org/abs/2111.04313

U2 - 10.14428/esann/2021.es2021-75

DO - 10.14428/esann/2021.es2021-75

M3 - Conference contribution

SP - 647

EP - 652

BT - ESANN 2021 proceedings

T2 - European Symposium on Artificial Neural Networks, Computational Intelligence and Machine Learning

Y2 - 6 October 2021 through 8 October 2021

ER -

A Relational Model for One-Shot Classification

Abstrakti

Conference

Pääsy asiakirjaan

Muut tiedostot ja linkit

Sormenjälki

Laitteet

Science-IT

Siteeraa tätä