FineGAN: Unsupervised Hierarchical Disentanglement for Fine-Grained Object Generation and Discovery
arXiv:1811.11155
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
References in corpus (9)
- Batch Normalization: Accelerating Deep Network Training by Reducing Internal Covariate Shift
- GANs Trained by a Two Time-Scale Update Rule Converge to a Local Nash Equilibrium
- Generative Adversarial Text to Image Synthesis
- Energy-based Generative Adversarial Network
- Bird Species Categorization Using Pose Normalized Deep Convolutional Nets
- A Note on the Inception Score
- LR-GAN: Layered Recursive Generative Adversarial Networks for Image Generation
- Generating Images Part by Part with Composite Generative Adversarial Networks
- Disentangling Factors of Variation by Mixing Them