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 any 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 video demo can be found at https://www.youtube.com/watch?v=tkk0SeWGu-8.

本论文提出了一种名为FineGAN的新型无监督生成对抗网络框架，旨在实现对细粒度物体类别进行分层次生成。FineGAN采用信息理论将三种因素（背景、目标形状、目标外貌）与潜在代码相关联，并以特定方式进行编码，从而实现所需层次关系，并通过大量实验验证了FineGAN的有效性。FineGAN的代码/模型/演示可在URL中找到。

FineGAN：细粒度对象生成和发现的无监督分层解缠模型