mlsanityData to 13 Oct 2026

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

arXiv 1811.11155 ↗First posted 27 Nov 2018cs.CV cs.AI cs.GRcited by 58

Not on the map. Why?

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

Key facts. Cited by 58 papers in the map (data through 13 Oct 2026). First posted on arXiv 27 Nov 2018.

Builds on

No reference list yet.

Built on by

Cited by year (2026 to 13 Oct)

Citing papers per year: 2021: 24; 2022: 11; 2023: 11; 2024: 5; 2025: 5; 2026: 2.

58 papers.

Sort:

By area:

  1. 2021Projected GANs Converge Fastercited by 207
  2. 2022Disentangled Representation Learningcited by 112
  3. 2022GIRAFFE HD: A High-Resolution 3D-aware Generative Modelcited by 86
  4. 2021Defect-GAN: High-Fidelity Defect Synthesis for Automated Defect Inspectioncited by 77
  5. 2021Unsupervised Layered Image Decomposition into Object Prototypescited by 50
  6. 2021Learning Generative Models of Textured 3D Meshes from Real-World Imagescited by 44
  7. 2021Diagonal Attention and Style-based GAN for Content-Style Disentanglement in Image Generation and Translationcited by 35
  8. 2023Picture that Sketch: Photorealistic Image Generation from Abstract Sketchescited by 34
  9. 2023The Hidden Language of Diffusion Modelscited by 34
  10. 2021CoMoGAN: continuous model-guided image-to-image translationcited by 27
  11. 2021Where and What? Examining Interpretable Disentangled Representationscited by 27
  12. 2021Unsupervised Foreground Extraction via Deep Region Competitioncited by 26
38 more
  1. 2021Collaging Class-specific GANs for Semantic Image Synthesiscited by 25
  2. 2022Is an Object-Centric Video Representation Beneficial for Transfer?cited by 24
  3. 2021GANSeg: Learning to Segment by Unsupervised Hierarchical Image Generationcited by 19
  4. 2022CoordGAN: Self-Supervised Dense Correspondences Emerge from GANscited by 17
  5. 2023MOST: Multiple Object localization with Self-supervised Transformers for object discoverycited by 17
  6. 2021The Pursuit of Knowledge: Discovering and Localizing Novel Categories using Dual Memorycited by 13
  7. 2021Benchmarks, Algorithms, and Metrics for Hierarchical Disentanglementcited by 12
  8. 2024Compositional Image Decomposition with Diffusion Modelscited by 12
  9. 2021Style Equalization: Unsupervised Learning of Controllable Generative Sequence Modelscited by 11
  10. 2023SIEDOB: Semantic Image Editing by Disentangling Object and Backgroundcited by 11
  11. 2021MOGAN: Morphologic-structure-aware Generative Learning from a Single Imagecited by 9
  12. 2021Physics-informed Guided Disentanglement in Generative Networkscited by 9
  13. 2021Contrastive Fine-grained Class Clustering via Generative Adversarial Networkscited by 9
  14. 2023TUVF: Learning Generalizable Texture UV Radiance Fieldscited by 9
  15. 2024Graph-based Unsupervised Disentangled Representation Learning via Multimodal Large Language Modelscited by 9
  16. 2025Hadamard product in deep learning: Introduction, Advances and Challengescited by 9
  17. 2021Learning Foreground-Background Segmentation from Improved Layered GANscited by 7
  18. 2021Knowledge-Guided Object Discovery with Acquired Deep Impressionscited by 6
  19. 2021DisUnknown: Distilling Unknown Factors for Disentanglement Learningcited by 6
  20. 2022FurryGAN: High Quality Foreground-aware Image Synthesiscited by 6
  21. 2022Extracting Semantic Knowledge from GANs with Unsupervised Learningcited by 5
  22. 2022NeRFEditor: Differentiable Style Decomposition for Full 3D Scene Editingcited by 5
  23. 2022Foreground-Background Separation through Concept Distillation from Generative Image Foundation Modelscited by 5
  24. 2023Controllable Image Generation via Collage Representationscited by 5
  25. 2021Generative Adversarial Networks and Adversarial Autoencoders: Tutorial and Surveycited by 4
  26. 2022Contrastive Learning for Diverse Disentangled Foreground Generationcited by 4
  27. 2024Disentangling Disentangled Representations: Towards Improved Latent Units via Diffusion Modelscited by 4
  28. 2024Unsupervised Object Discovery: A Comprehensive Survey and Unified Taxonomycited by 4
  29. 2021Generating Furry Cars: Disentangling Object Shape & Appearance across Multiple Domainscited by 3
  30. 2021Cluster-guided Image Synthesis with Unconditional Modelscited by 3
  31. 2023ToddlerDiffusion: Interactive Structured Image Generation with Cascaded Schr"odinger Bridgecited by 3
  32. 2021Equine Pain Behavior Classification via Self-Supervised Disentangled Pose Representationcited by 2
  33. 2022ILSGAN: Independent Layer Synthesis for Unsupervised Foreground-Background Segmentationcited by 2
  34. 2023Multi-object Video Generation from Single Frame Layoutscited by 2
  35. 2022Unsupervised Structure-Consistent Image-to-Image Translationcited by 1
  36. 2023SS-CPGAN: Self-Supervised Cut-and-Pasting Generative Adversarial Network for Object Segmentationcited by 1
  37. 2025Chirpy3D: Part-Aware Multi-View Diffusion for Creative Fine-Grained Object Generationcited by 1
  38. 2025Post-Hoc Concept Disentanglement: From Correlated to Isolated Concept Representationscited by 1

50 most cited of 58 All 58 (JSON)