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 >
Disentangled Representation Learning in Real-World Image Datasets via Image Segmentation Prior
Title: | Disentangled Representation Learning in Real-World Image Datasets via Image Segmentation Prior |
Authors: | Nakagawa, Nao Browse this author | Togo, Ren Browse this author | Ogawa, Takahiro Browse this author →KAKEN DB | Haseyama, Miki Browse this author →KAKEN DB |
Keywords: | Image segmentation | Standards | Task analysis | Decoding | Data models | Solid modeling | Semantics | Alpha blend | disentanglement | image segmentation | real-world image | representation learning |
Issue Date: | 30-Jul-2021 |
Publisher: | IEEE (Institute of Electrical and Electronics Engineers) |
Journal Title: | IEEE Access |
Volume: | 9 |
Start Page: | 110880 |
End Page: | 110888 |
Publisher DOI: | 10.1109/ACCESS.2021.3101229 |
Abstract: | We propose a novel method that can learn easy-to-interpret latent representations in real-world image datasets using a VAE-based model by splitting an image into several disjoint regions. Our method performs object-wise disentanglement by exploiting image segmentation and alpha compositing. With remarkable results obtained by unsupervised disentanglement methods for toy datasets, recent studies have tackled challenging disentanglement for real-world image datasets. However, these methods involve deviations from the standard VAE architecture, which has favorable disentanglement properties. Thus, for disentanglement in images of real-world image datasets with preservation of the VAE backbone, we designed an encoder and a decoder that embed an image into disjoint sets of latent variables corresponding to objects. The encoder includes a pre-trained image segmentation network, which allows our model to focus only on representation learning while adopting image segmentation as an inductive bias. Evaluations using real-world image datasets, CelebA and Stanford Cars, showed that our method achieves improved disentanglement and transferability. |
Rights: | © 2021 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: | article |
URI: | http://hdl.handle.net/2115/82697 |
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)
|
|