FineGAN: Unsupervised Hierarchical Disentanglement for Fine-Grained Object Generation and Discovery
Abstract
We propose FineGAN, a novel unsupervised GAN framework, which disentangles the background, object shape, and object appearance to hierarchically generate images of fine-grained object categories. To disentangle the factors without supervision, our key idea is to use information theory to associate each factor to a latent code, and to condition the relationships between the codes in a specific way to induce the desired hierarchy. Through extensive experiments, we show that FineGAN achieves the desired disentanglement to generate realistic and diverse images belonging to fine-grained classes of birds, dogs, and cars. Using FineGAN's automatically learned features, we also cluster real images as a first attempt at solving the novel problem of unsupervised fine-grained object category discovery. Our code/models/demo can be found at https://github.com/kkanshul/finegan
Cite
Text
Singh et al. "FineGAN: Unsupervised Hierarchical Disentanglement for Fine-Grained Object Generation and Discovery." Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, 2019. doi:10.1109/CVPR.2019.00665Markdown
[Singh et al. "FineGAN: Unsupervised Hierarchical Disentanglement for Fine-Grained Object Generation and Discovery." Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, 2019.](https://mlanthology.org/cvpr/2019/singh2019cvpr-finegan/) doi:10.1109/CVPR.2019.00665BibTeX
@inproceedings{singh2019cvpr-finegan,
title = {{FineGAN: Unsupervised Hierarchical Disentanglement for Fine-Grained Object Generation and Discovery}},
author = {Singh, Krishna Kumar and Ojha, Utkarsh and Lee, Yong Jae},
booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition},
year = {2019},
doi = {10.1109/CVPR.2019.00665},
url = {https://mlanthology.org/cvpr/2019/singh2019cvpr-finegan/}
}