Papers › FineGAN: Unsupervised Hierarchical Disentanglement for Fine-Grained Object Generation...

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

27 Nov 2018CVPR 2019 6arXiv:1811.11155archive 2025-07-28

Krishna Kumar Singh, Utkarsh Ojha, Yong Jae Lee

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

PaperPDFConference PDFCode

In Syntology Open this paper in Syntology's Atlas, the map of the papers in Syntology's graph and their citations.

Code

kkanshul/finegan officialmentioned in papermentioned on GitHubpytorchBSD-2-Clause report

Repository list and official/mentioned flags are the archive's, frozen 2025-07-28. Reachability, where shown, is from one Syntology probe window (2026-09-16 to 2026-09-18); repositories not probed show nothing. GitHub stars are not tracked.

Code Syntology ran Syntology

Not run by Syntology. Nothing on this page verifies that the listed code works.

Tasks

Conditional Image GenerationDisentanglementFine-Grained Visual CategorizationImage ClusteringObject

Results from the paper archive 2025-07-28

TaskDatasetModelMetricValueRank at snapshotLeaderboardReport
Image Clustering CUB Birds FineGAN Accuracy 0.126 #1 of 4 Archive leaderboard report
Image Clustering CUB Birds FineGAN NMI 0.403 #1 of 4 Archive leaderboard report
Image Clustering Stanford Cars FineGAN Accuracy 0.078 #2 of 5 Archive leaderboard report
Image Clustering Stanford Cars FineGAN NMI 0.354 #2 of 5 Archive leaderboard report
Image Clustering Stanford Dogs FineGAN Accuracy 0.079 #1 of 4 Archive leaderboard report
Image Clustering Stanford Dogs FineGAN NMI 0.233 #1 of 4 Archive leaderboard report
Image Generation CUB 128 x 128 FineGAN FID 11.25 #2 of 4 Archive leaderboard report
Image Generation CUB 128 x 128 FineGAN Inception score 52.53 #2 of 4 Archive leaderboard report
Image Generation Stanford Cars FineGAN FID 16.03 #2 of 4 Archive leaderboard report
Image Generation Stanford Cars FineGAN Inception score 32.62 #2 of 4 Archive leaderboard report
Image Generation Stanford Dogs FineGAN FID 25.66 #2 of 4 Archive leaderboard report
Image Generation Stanford Dogs FineGAN Inception score 46.92 #2 of 4 Archive leaderboard report

Ranks are positions in the archive's leaderboards as they stood at the 2025-07-28 snapshot. Results published since then are not among these rows, so a rank here is not a current standing.

Methods

Convolution

Report a problem or propose a change · a person checks every report against the paper or source before anything changes; decisions are listed on /corrections