Collabonet

Collaboration of generative models by unsupervised classification

Hyeongmin Lee, Taeoh Kim, Eungyeol Song, Sang Youn Lee

Research output: Chapter in Book/Report/Conference proceedingConference contribution

Abstract

Designing models for learning dataset with complex distributions is one of the main challenges that still remains in machine learning areas. We propose CollaboNet, which can divide a large dataset into sub-datasets, train two generative models separately, and let two models work together to achieve better performance. The proposed algorithm divides a large dataset without label since the capability difference between two generative models in performing tasks on each data is the main criterion for dividing a large dataset. In other words, the classification model can be trained by unsupervised manner. Autoencoder experiments for pure MNIST and the datasets combined artificially from two image sets shows that CollaboNet successfully splits large datasets without labels, improving the performance of generative models.

Original languageEnglish
Title of host publication2018 IEEE International Conference on Image Processing, ICIP 2018 - Proceedings
PublisherIEEE Computer Society
Pages1068-1072
Number of pages5
ISBN (Electronic)9781479970612
DOIs
Publication statusPublished - 2018 Aug 29
Event25th IEEE International Conference on Image Processing, ICIP 2018 - Athens, Greece
Duration: 2018 Oct 72018 Oct 10

Publication series

NameProceedings - International Conference on Image Processing, ICIP
ISSN (Print)1522-4880

Conference

Conference25th IEEE International Conference on Image Processing, ICIP 2018
CountryGreece
CityAthens
Period18/10/718/10/10

Fingerprint

Labels
Learning systems
Experiments

All Science Journal Classification (ASJC) codes

  • Software
  • Computer Vision and Pattern Recognition
  • Signal Processing

Cite this

Lee, H., Kim, T., Song, E., & Lee, S. Y. (2018). Collabonet: Collaboration of generative models by unsupervised classification. In 2018 IEEE International Conference on Image Processing, ICIP 2018 - Proceedings (pp. 1068-1072). [8451825] (Proceedings - International Conference on Image Processing, ICIP). IEEE Computer Society. https://doi.org/10.1109/ICIP.2018.8451825
Lee, Hyeongmin ; Kim, Taeoh ; Song, Eungyeol ; Lee, Sang Youn. / Collabonet : Collaboration of generative models by unsupervised classification. 2018 IEEE International Conference on Image Processing, ICIP 2018 - Proceedings. IEEE Computer Society, 2018. pp. 1068-1072 (Proceedings - International Conference on Image Processing, ICIP).
@inproceedings{21f339f151334da3b2da6eae4a5cddad,
title = "Collabonet: Collaboration of generative models by unsupervised classification",
abstract = "Designing models for learning dataset with complex distributions is one of the main challenges that still remains in machine learning areas. We propose CollaboNet, which can divide a large dataset into sub-datasets, train two generative models separately, and let two models work together to achieve better performance. The proposed algorithm divides a large dataset without label since the capability difference between two generative models in performing tasks on each data is the main criterion for dividing a large dataset. In other words, the classification model can be trained by unsupervised manner. Autoencoder experiments for pure MNIST and the datasets combined artificially from two image sets shows that CollaboNet successfully splits large datasets without labels, improving the performance of generative models.",
author = "Hyeongmin Lee and Taeoh Kim and Eungyeol Song and Lee, {Sang Youn}",
year = "2018",
month = "8",
day = "29",
doi = "10.1109/ICIP.2018.8451825",
language = "English",
series = "Proceedings - International Conference on Image Processing, ICIP",
publisher = "IEEE Computer Society",
pages = "1068--1072",
booktitle = "2018 IEEE International Conference on Image Processing, ICIP 2018 - Proceedings",
address = "United States",

}

Lee, H, Kim, T, Song, E & Lee, SY 2018, Collabonet: Collaboration of generative models by unsupervised classification. in 2018 IEEE International Conference on Image Processing, ICIP 2018 - Proceedings., 8451825, Proceedings - International Conference on Image Processing, ICIP, IEEE Computer Society, pp. 1068-1072, 25th IEEE International Conference on Image Processing, ICIP 2018, Athens, Greece, 18/10/7. https://doi.org/10.1109/ICIP.2018.8451825

Collabonet : Collaboration of generative models by unsupervised classification. / Lee, Hyeongmin; Kim, Taeoh; Song, Eungyeol; Lee, Sang Youn.

2018 IEEE International Conference on Image Processing, ICIP 2018 - Proceedings. IEEE Computer Society, 2018. p. 1068-1072 8451825 (Proceedings - International Conference on Image Processing, ICIP).

Research output: Chapter in Book/Report/Conference proceedingConference contribution

TY - GEN

T1 - Collabonet

T2 - Collaboration of generative models by unsupervised classification

AU - Lee, Hyeongmin

AU - Kim, Taeoh

AU - Song, Eungyeol

AU - Lee, Sang Youn

PY - 2018/8/29

Y1 - 2018/8/29

N2 - Designing models for learning dataset with complex distributions is one of the main challenges that still remains in machine learning areas. We propose CollaboNet, which can divide a large dataset into sub-datasets, train two generative models separately, and let two models work together to achieve better performance. The proposed algorithm divides a large dataset without label since the capability difference between two generative models in performing tasks on each data is the main criterion for dividing a large dataset. In other words, the classification model can be trained by unsupervised manner. Autoencoder experiments for pure MNIST and the datasets combined artificially from two image sets shows that CollaboNet successfully splits large datasets without labels, improving the performance of generative models.

AB - Designing models for learning dataset with complex distributions is one of the main challenges that still remains in machine learning areas. We propose CollaboNet, which can divide a large dataset into sub-datasets, train two generative models separately, and let two models work together to achieve better performance. The proposed algorithm divides a large dataset without label since the capability difference between two generative models in performing tasks on each data is the main criterion for dividing a large dataset. In other words, the classification model can be trained by unsupervised manner. Autoencoder experiments for pure MNIST and the datasets combined artificially from two image sets shows that CollaboNet successfully splits large datasets without labels, improving the performance of generative models.

UR - http://www.scopus.com/inward/record.url?scp=85062908117&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=85062908117&partnerID=8YFLogxK

U2 - 10.1109/ICIP.2018.8451825

DO - 10.1109/ICIP.2018.8451825

M3 - Conference contribution

T3 - Proceedings - International Conference on Image Processing, ICIP

SP - 1068

EP - 1072

BT - 2018 IEEE International Conference on Image Processing, ICIP 2018 - Proceedings

PB - IEEE Computer Society

ER -

Lee H, Kim T, Song E, Lee SY. Collabonet: Collaboration of generative models by unsupervised classification. In 2018 IEEE International Conference on Image Processing, ICIP 2018 - Proceedings. IEEE Computer Society. 2018. p. 1068-1072. 8451825. (Proceedings - International Conference on Image Processing, ICIP). https://doi.org/10.1109/ICIP.2018.8451825