Disentangled Representation Learning in Real-World Image Datasets via Image Segmentation Prior
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 rem...
Main Authors: | Nao Nakagawa, Ren Togo, Takahiro Ogawa, Miki Haseyama |
---|---|
Format: | Article |
Language: | English |
Published: |
IEEE
2021-01-01
|
Series: | IEEE Access |
Subjects: | |
Online Access: | https://ieeexplore.ieee.org/document/9502079/ |
Similar Items
-
FaceShapeGene: A disentangled shape representation for flexible face image editing
by: Sen-Zhe Xu, et al.
Published: (2021-06-01) -
Frequency Disentanglement Distillation Image Deblurring Network
by: Yiming Liu, et al.
Published: (2021-07-01) -
Unsupervised MR harmonization by learning disentangled representations using information bottleneck theory
by: Lianrui Zuo, et al.
Published: (2021-11-01) -
Disentangled Autoencoder for Cross-Stain Feature Extraction in Pathology Image Analysis
by: Helge Hecht, et al.
Published: (2020-09-01) -
Stylistic and Spatial Disentanglement in GANs
by: Alharbi, Yazeed
Published: (2021)