|
Hokkaido University Collection of Scholarly and Academic Papers >
Graduate School of Information Science and Technology / Faculty of Information Science and Technology >
Peer-reviewed Journal Articles, etc >
Unsupervised Feature Learning for Output Control of Generative Models
| Title: | Unsupervised Feature Learning for Output Control of Generative Models |
| Authors: | Toda, Kazuki Browse this author | | Atarashi, Kyohei Browse this author | | Oyama, Satoshi Browse this author →KAKEN DB | | Kurihara, Masahito Browse this author →KAKEN DB |
| Keywords: | unsupervised learning | | deep learning | | generative model | | output control |
| Issue Date: | Dec-2020 |
| Publisher: | IEEE |
| Journal Title: | 2020 Joint 11th International Conference on Soft Computing and Intelligent Systems and 21st International Symposium on Advanced Intelligent Systems (SCIS-ISIS) |
| Start Page: | 1 |
| End Page: | 6 |
| Publisher DOI: | 10.1109/SCISISIS50064.2020.9322714 |
| Abstract: | Deep generative models are being actively studied, particularly variational autoencoders (VAEs) because they can generate high-quality images. The M2 model supports semi-supervised learning from both labeled and unlabeled data, which enables the generated images to be easily controlled by changing the class label values. However, generative models must be learned from only unlabeled data when class labels are not available. A model is presented that incorporates a deep clustering method into the M2 model, which enables clusters to be identified among unlabeled data so that each data point can be assigned to one of the clusters. The generated images in unlabeled datasets can easily be controlled by changing the cluster assignment of each data point. |
| Conference Name: | Joint 11th International Conference on Soft Computing and Intelligent Systems and 21st International Symposium on Advanced Intelligent Systems |
| Conference Sequence: | 2020 |
| Conference Place: | Japan |
| Rights: | © 2020 IEEE. Personal use of this material is permitted. Permission from IEEE must be obtained for all other uses, in any current or future media, including reprinting/republishing this material for advertising or promotional purposes, creating new collective works, for resale or redistribution to servers or lists, or reuse of any copyrighted component of this work in other works. |
| Type: | proceedings |
| URI: | http://hdl.handle.net/2115/80338 |
| Appears in Collections: | 情報科学院・情報科学研究院 (Graduate School of Information Science and Technology / Faculty of Information Science and Technology) > 雑誌発表論文等 (Peer-reviewed Journal Articles, etc)
|
Submitter: 小山 聡
|
