# FineGAN: Unsupervised Hierarchical Disentanglement for Fine-Grained Object Generation and Discovery

arXiv: https://arxiv.org/abs/1811.11155 · HTML: https://mlsanity.com/paper/1811.11155/

## Key facts

- Cited by 58 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 27 Nov 2018.

## Built on by (most cited first, 30 of 58)

- [Projected GANs Converge Faster](https://mlsanity.com/paper/2111.01007/) (2021)
- [Disentangled Representation Learning](https://mlsanity.com/paper/2211.11695/) (2022)
- [GIRAFFE HD: A High-Resolution 3D-aware Generative Model](https://mlsanity.com/paper/2203.14954/) (2022)
- [Defect-GAN: High-Fidelity Defect Synthesis for Automated Defect Inspection](https://mlsanity.com/paper/2103.15158/) (2021)
- [Unsupervised Layered Image Decomposition into Object Prototypes](https://mlsanity.com/paper/2104.14575/) (2021)
- [Learning Generative Models of Textured 3D Meshes from Real-World Images](https://mlsanity.com/paper/2103.15627/) (2021)
- [Diagonal Attention and Style-based GAN for Content-Style Disentanglement in Image Generation and Translation](https://mlsanity.com/paper/2103.16146/) (2021)
- [Picture that Sketch: Photorealistic Image Generation from Abstract Sketches](https://mlsanity.com/paper/2303.11162/) (2023)
- [The Hidden Language of Diffusion Models](https://mlsanity.com/paper/2306.00966/) (2023)
- [CoMoGAN: continuous model-guided image-to-image translation](https://mlsanity.com/paper/2103.06879/) (2021)
- [Where and What? Examining Interpretable Disentangled Representations](https://mlsanity.com/paper/2104.05622/) (2021)
- [Unsupervised Foreground Extraction via Deep Region Competition](https://mlsanity.com/paper/2110.15497/) (2021)
- [Collaging Class-specific GANs for Semantic Image Synthesis](https://mlsanity.com/paper/2110.04281/) (2021)
- [Is an Object-Centric Video Representation Beneficial for Transfer?](https://mlsanity.com/paper/2207.10075/) (2022)
- [GANSeg: Learning to Segment by Unsupervised Hierarchical Image Generation](https://mlsanity.com/paper/2112.01036/) (2021)
- [CoordGAN: Self-Supervised Dense Correspondences Emerge from GANs](https://mlsanity.com/paper/2203.16521/) (2022)
- [MOST: Multiple Object localization with Self-supervised Transformers for object discovery](https://mlsanity.com/paper/2304.05387/) (2023)
- [The Pursuit of Knowledge: Discovering and Localizing Novel Categories using Dual Memory](https://mlsanity.com/paper/2105.01652/) (2021)
- [Benchmarks, Algorithms, and Metrics for Hierarchical Disentanglement](https://mlsanity.com/paper/2102.05185/) (2021)
- [Compositional Image Decomposition with Diffusion Models](https://mlsanity.com/paper/2406.19298/) (2024)
- [Style Equalization: Unsupervised Learning of Controllable Generative Sequence Models](https://mlsanity.com/paper/2110.02891/) (2021)
- [SIEDOB: Semantic Image Editing by Disentangling Object and Background](https://mlsanity.com/paper/2303.13062/) (2023)
- [Graph-based Unsupervised Disentangled Representation Learning via Multimodal Large Language Models](https://mlsanity.com/paper/2407.18999/) (2024)
- [MOGAN: Morphologic-structure-aware Generative Learning from a Single Image](https://mlsanity.com/paper/2103.02997/) (2021)
- [Physics-informed Guided Disentanglement in Generative Networks](https://mlsanity.com/paper/2107.14229/) (2021)
- [Contrastive Fine-grained Class Clustering via Generative Adversarial Networks](https://mlsanity.com/paper/2112.14971/) (2021)
- [TUVF: Learning Generalizable Texture UV Radiance Fields](https://mlsanity.com/paper/2305.03040/) (2023)
- [Hadamard product in deep learning: Introduction, Advances and Challenges](https://mlsanity.com/paper/2504.13112/) (2025)
- [Learning Foreground-Background Segmentation from Improved Layered GANs](https://mlsanity.com/paper/2104.00483/) (2021)
- [Knowledge-Guided Object Discovery with Acquired Deep Impressions](https://mlsanity.com/paper/2103.10611/) (2021)

## Abstract (arXiv)

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