| Paper Abstract and Keywords |
| Presentation |
2022-02-21 16:45
A Note on Disentanglement Using Deep Generative Model Based on Variational Autoencoder
-- Introduction of Regularization Losses Based on Metrics of Disentangled Representation --
Nao Nakagawa, Ren Togo, Takahiro Ogawa, Miki Haseyama (Hokkaido Univ.) |
| Abstract |
(in Japanese) |
(See Japanese page) |
| (in English) |
In this paper, we study disentangled representation learning using a deep generative model based on Variational Autoencoder (VAE). The goal of disentanglement is to obtain a latent representation in which single latent variables correspond to single factors of variation. Although several unsupervised methods have been proposed for disentanglement by imposing the element-wise independence of latent variables, it has been shown that independence does not guarantee disentanglement. Hence, we propose a novel disentanglement method using a VAE-based model whose loss function includes a regularization loss based on a differentiable disentanglement metric. Our method disentangles the representation by applying gradient descent directly to a disentanglement metric function. We first validate the behavior of the various disentanglement metrics and then show the effectiveness of our method. |
| Keyword |
(in Japanese) |
(See Japanese page) |
| (in English) |
deep learning / representation learning / deep generative model / disentanglement / variational autoencoder / / / |
| Reference Info. |
ITE Tech. Rep., vol. 46, no. 6, ME2022-44, pp. 97-102, Feb. 2022. |
| Paper # |
ME2022-44 |
| Date of Issue |
2022-02-14 (MMS, ME, AIT) |
| ISSN |
Print edition: ISSN 1342-6893 Online edition: ISSN 2424-1970 |
| Download PDF |
|
| Conference Information |
| Committee |
AIT ME MMS IEICE-IE IEICE-ITS |
| Conference Date |
2022-02-21 - 2022-02-22 |
| Place (in Japanese) |
(See Japanese page) |
| Place (in English) |
online |
| Topics (in Japanese) |
(See Japanese page) |
| Topics (in English) |
|
| Paper Information |
| Registration To |
ME |
| Conference Code |
2022-02-AIT-ME-MMS-IE-ITS |
| Language |
Japanese |
| Title (in Japanese) |
(See Japanese page) |
| Sub Title (in Japanese) |
(See Japanese page) |
| Title (in English) |
A Note on Disentanglement Using Deep Generative Model Based on Variational Autoencoder |
| Sub Title (in English) |
Introduction of Regularization Losses Based on Metrics of Disentangled Representation |
| Keyword(1) |
deep learning |
| Keyword(2) |
representation learning |
| Keyword(3) |
deep generative model |
| Keyword(4) |
disentanglement |
| Keyword(5) |
variational autoencoder |
| Keyword(6) |
|
| Keyword(7) |
|
| Keyword(8) |
|
| 1st Author's Name |
Nao Nakagawa |
| 1st Author's Affiliation |
Hokkaido University (Hokkaido Univ.) |
| 2nd Author's Name |
Ren Togo |
| 2nd Author's Affiliation |
Hokkaido University (Hokkaido Univ.) |
| 3rd Author's Name |
Takahiro Ogawa |
| 3rd Author's Affiliation |
Hokkaido University (Hokkaido Univ.) |
| 4th Author's Name |
Miki Haseyama |
| 4th Author's Affiliation |
Hokkaido University (Hokkaido Univ.) |
| 5th Author's Name |
|
| 5th Author's Affiliation |
() |
| 6th Author's Name |
|
| 6th Author's Affiliation |
() |
| 7th Author's Name |
|
| 7th Author's Affiliation |
() |
| 8th Author's Name |
|
| 8th Author's Affiliation |
() |
| 9th Author's Name |
|
| 9th Author's Affiliation |
() |
| 10th Author's Name |
|
| 10th Author's Affiliation |
() |
| 11th Author's Name |
|
| 11th Author's Affiliation |
() |
| 12th Author's Name |
|
| 12th Author's Affiliation |
() |
| 13th Author's Name |
|
| 13th Author's Affiliation |
() |
| 14th Author's Name |
|
| 14th Author's Affiliation |
() |
| 15th Author's Name |
|
| 15th Author's Affiliation |
() |
| 16th Author's Name |
|
| 16th Author's Affiliation |
() |
| 17th Author's Name |
|
| 17th Author's Affiliation |
() |
| 18th Author's Name |
|
| 18th Author's Affiliation |
() |
| 19th Author's Name |
|
| 19th Author's Affiliation |
() |
| 20th Author's Name |
|
| 20th Author's Affiliation |
() |
| Speaker |
Author-1 |
| Date Time |
2022-02-21 16:45:00 |
| Presentation Time |
15 minutes |
| Registration for |
ME |
| Paper # |
MMS2022-19, ME2022-44, AIT2022-19 |
| Volume (vol) |
vol.46 |
| Number (no) |
no.6 |
| Page |
pp.97-102 |
| #Pages |
6 |
| Date of Issue |
2022-02-14 (MMS, ME, AIT) |