AI Paper Atlas

Research map / Image generation / GANs

OneGAN: Simultaneous Unsupervised Learning of Conditional Image Generation, Foreground Segmentation, and Fine-Grained Clustering

Yaniv Benny, Lior Wolf

ECCV 2020 · Image generation › GANs · approach: Conditional GANs · 35 citations (OpenAlex)

Read the paperCheck your idea against 137,217 papers

AI-extracted. The measured effects below were read by AI from the paper's full text (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.

Measured effects reported in the paper

What was changedWhereMeasuredEffect
add multi-phase training schedule (ablation)OneGAN · Birds segmentationIOU: 28.2 -> 55.5Improved
add multi-phase training schedule (ablation)OneGAN · Birds generationFID: 196.5 -> 20.5Improved
add reconstruction path (Phase II) to generation-only training (ablation)OneGAN · Birds segmentationIOU: 45.7 -> 55.5Improved
add reconstruction of real images (ablation)OneGAN · Birds segmentationIOU: 53.5 -> 55.5Improved
add reconstruction of real images (ablation)OneGAN · Birds generationCIS: 25.6 -> 30.7Improved
add reconstruction of real images (ablation)OneGAN · Cars clusteringACC: .057 -> .060Mixed
use GLU layer normalization instead of layer normalization (ablation)OneGAN generators · CUBFID: 87.5 -> 20.5Improved
use GLU layer normalization instead of instance normalization (ablation)OneGAN generators · CUBIOU: 30.1 -> 55.5Improved
add mixup at embedding level (mixup 1,2) (ablation)OneGAN · CUBC-IS: 17.5 -> 30.7Improved
add mixup at skip connections (mixup 3,4) (ablation)OneGAN · CUBC-IS: 22.2 -> 30.7Improved
add bypass skip connection (ablation)OneGAN · CUBFID: 21.2 -> 20.5No clear effect
add mask regularization loss L_RM (ablation)OneGAN · CUBFID: 97.2 -> 20.5Improved

Later papers that compared with this method

1 later accepted paper reports OneGAN as a baseline in their results tables; 1 of them report a better number on most of the results they share with it.

Earlier methods this paper compares with

Named baselines from earlier accepted papers in this paper's results tables: better than 1 of 1 on most shared results.

Matched by method name in results tables read by AI. Authors' own tables tend to favour the newer method, and a comparison can be missed when a method is renamed.

Closest papers by meaning

Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.

Open scime draft

Get the next scime Dispatch and a monthly field update

Free. We send a confirmation link first; every email has a one-click unsubscribe. Privacy