Interpolation consistency training for semi-supervised learning

Vikas Verma; Alex Lamb; Juho Kannala; Yoshua Bengio; David Lopez-Paz

doi:10.24963/ijcai.2019/504

Interpolation consistency training for semi-supervised learning

Vikas Verma
, Alex Lamb
, Juho Kannala
, Yoshua Bengio
, David Lopez-Paz

Montreal Institute for Learning Algorithms
Facebook AI Research

Tutkimustuotos: Artikkeli kirjassa/konferenssijulkaisussa › Conference article in proceedings › Scientific › vertaisarvioitu

241 Viittaukset (Web of Science)

Abstrakti

We introduce Interpolation Consistency Training (ICT), a simple and computation efficient algorithm for training Deep Neural Networks in the semi-supervised learning paradigm. ICT encourages the prediction at an interpolation of unlabeled points to be consistent with the interpolation of the predictions at those points. In classification problems, ICT moves the decision boundary to low-density regions of the data distribution. Our experiments show that ICT achieves state-of-the-art performance when applied to standard neural network architectures on the CIFAR-10 and SVHN benchmark datasets.

Alkuperäiskieli	Englanti
Otsikko	Proceedings of the Twenty-Eighth International Joint Conference on Artificial Intelligence (IJCAI-19)
Kustantaja	IJCAI
Sivut	3635-3641
ISBN (elektroninen)	978-0-9992411-4-1
DOI - pysyväislinkit	https://doi.org/10.24963/ijcai.2019/504
Tila	Julkaistu - 2019
OKM-julkaisutyyppi	A4 Artikkeli konferenssijulkaisussa
Tapahtuma	International Joint Conference on Artificial Intelligence - Venetian Macao Resort Hotel, Macao, Kiina Kesto: 10 elok. 2019 → 16 elok. 2019 Konferenssinumero: 28 https://ijcai19.org/ http://ijcai19.org/

Conference

Conference	International Joint Conference on Artificial Intelligence
Lyhennettä	IJCAI
Maa/Alue	Kiina
Kaupunki	Macao
Ajanjakso	10/08/2019 → 16/08/2019
www-osoite	https://ijcai19.org/ http://ijcai19.org/

Pääsy asiakirjaan

10.24963/ijcai.2019/504

https://arxiv.org/abs/1903.03825

Muut tiedostot ja linkit

https://www.ijcai.org/proceedings/2019/

Algorithms for Data-Efficient Training of Deep Neural Networks
Kannala, J.
25/11/2020
1 kohde/ Medianäkyvyys
Lehdistö/media: Esiintyminen mediassa

Siteeraa tätä

@inproceedings{ad3e4cf616bd42e8b4edd2b0918b3dda,

title = "Interpolation consistency training for semi-supervised learning",

abstract = "We introduce Interpolation Consistency Training (ICT), a simple and computation efficient algorithm for training Deep Neural Networks in the semi-supervised learning paradigm. ICT encourages the prediction at an interpolation of unlabeled points to be consistent with the interpolation of the predictions at those points. In classification problems, ICT moves the decision boundary to low-density regions of the data distribution. Our experiments show that ICT achieves state-of-the-art performance when applied to standard neural network architectures on the CIFAR-10 and SVHN benchmark datasets.",

keywords = "Deep Learning",

author = "Vikas Verma and Alex Lamb and Juho Kannala and Yoshua Bengio and David Lopez-Paz",

year = "2019",

doi = "10.24963/ijcai.2019/504",

language = "English",

pages = "3635--3641",

booktitle = "Proceedings of the Twenty-Eighth International Joint Conference on Artificial Intelligence (IJCAI-19)",

publisher = "IJCAI",

address = "United States",

note = "International Joint Conference on Artificial Intelligence, IJCAI ; Conference date: 10-08-2019 Through 16-08-2019",

url = "https://ijcai19.org/, http://ijcai19.org/",

}

Verma, V, Lamb, A, Kannala, J, Bengio, Y & Lopez-Paz, D 2019, Interpolation consistency training for semi-supervised learning. julkaisussa Proceedings of the Twenty-Eighth International Joint Conference on Artificial Intelligence (IJCAI-19). IJCAI, Sivut 3635-3641, International Joint Conference on Artificial Intelligence, Macao, Kiina, 10/08/2019. https://doi.org/10.24963/ijcai.2019/504

Interpolation consistency training for semi-supervised learning. / Verma, Vikas; Lamb, Alex; Kannala, Juho et al.
Proceedings of the Twenty-Eighth International Joint Conference on Artificial Intelligence (IJCAI-19). IJCAI, 2019. s. 3635-3641.

Tutkimustuotos: Artikkeli kirjassa/konferenssijulkaisussa › Conference article in proceedings › Scientific › vertaisarvioitu

TY - GEN

T1 - Interpolation consistency training for semi-supervised learning

AU - Verma, Vikas

AU - Lamb, Alex

AU - Kannala, Juho

AU - Bengio, Yoshua

AU - Lopez-Paz, David

N1 - Conference code: 28

PY - 2019

Y1 - 2019

N2 - We introduce Interpolation Consistency Training (ICT), a simple and computation efficient algorithm for training Deep Neural Networks in the semi-supervised learning paradigm. ICT encourages the prediction at an interpolation of unlabeled points to be consistent with the interpolation of the predictions at those points. In classification problems, ICT moves the decision boundary to low-density regions of the data distribution. Our experiments show that ICT achieves state-of-the-art performance when applied to standard neural network architectures on the CIFAR-10 and SVHN benchmark datasets.

AB - We introduce Interpolation Consistency Training (ICT), a simple and computation efficient algorithm for training Deep Neural Networks in the semi-supervised learning paradigm. ICT encourages the prediction at an interpolation of unlabeled points to be consistent with the interpolation of the predictions at those points. In classification problems, ICT moves the decision boundary to low-density regions of the data distribution. Our experiments show that ICT achieves state-of-the-art performance when applied to standard neural network architectures on the CIFAR-10 and SVHN benchmark datasets.

KW - Deep Learning

UR - https://www.ijcai.org/proceedings/2019/

U2 - 10.24963/ijcai.2019/504

DO - 10.24963/ijcai.2019/504

M3 - Conference article in proceedings

SP - 3635

EP - 3641

BT - Proceedings of the Twenty-Eighth International Joint Conference on Artificial Intelligence (IJCAI-19)

PB - IJCAI

T2 - International Joint Conference on Artificial Intelligence

Y2 - 10 August 2019 through 16 August 2019

ER -

Interpolation consistency training for semi-supervised learning

Abstrakti

Conference

Pääsy asiakirjaan

Muut tiedostot ja linkit

Sormenjälki

Lehtileikkeet

Algorithms for Data-Efficient Training of Deep Neural Networks

Siteeraa tätä