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 language | English |
|---|---|
| Title of host publication | 2018 IEEE International Conference on Image Processing, ICIP 2018 - Proceedings |
| Publisher | IEEE Computer Society |
| Pages | 1068-1072 |
| Number of pages | 5 |
| ISBN (Electronic) | 9781479970612 |
| DOIs | |
| Publication status | Published - 2018 Aug 29 |
| Event | 25th IEEE International Conference on Image Processing, ICIP 2018 - Athens, Greece Duration: 2018 Oct 7 → 2018 Oct 10 |
Publication series
| Name | Proceedings - International Conference on Image Processing, ICIP |
|---|---|
| ISSN (Print) | 1522-4880 |
Conference
| Conference | 25th IEEE International Conference on Image Processing, ICIP 2018 |
|---|---|
| Country | Greece |
| City | Athens |
| Period | 18/10/7 → 18/10/10 |
Fingerprint
All Science Journal Classification (ASJC) codes
- Software
- Computer Vision and Pattern Recognition
- Signal Processing
Cite this
}
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 proceeding › Conference 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 -