AI Paper Atlas

Research map / Image generation / GANs

FakeCLR: Exploring Contrastive Learning for Solving Latent Discontinuity in Data-Efficient GANs

Ziqiang Li, Chaoyue Wang, Heliang Zheng, Jing Zhang, Bin Li

ECCV 2022 · Image generation › GANs · approach: Large-scale GAN latent analysis · 28 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 real-image instance discrimination (ablation)StyleGAN2-ADA-Linear · FFHQ-100FID: 82 -> 107Hurt
add real-image instance discrimination (ablation)StyleGAN2-ADA-Linear · FFHQ-5KFID: 9.39 -> 8.50Improved
add fake-image instance discrimination (ablation)StyleGAN2-ADA-Linear · FFHQ-100FID: 82 -> 76.6Improved
add fake-image instance discrimination (ablation)StyleGAN2-ADA-Linear · FFHQ-2KFID: 13.01 -> 12.69Improved
add instance-perturbation contrastive loss (ablation)StyleGAN2-ADA-Linear · FFHQ-100FID: 82 -> 43.35Improved
add instance-perturbation contrastive loss (ablation)StyleGAN2-ADA-Linear · FFHQ-2KFID: 13.01 -> 11.29Improved
add noise-related latent augmentation (ablation)FakeCLR (instance-perturbation) · FFHQ-100FID: 43.35 -> 44.10Hurt
add noise-related latent augmentation (ablation)FakeCLR (instance-perturbation) · FFHQ-2KFID: 11.29 -> 10.65Improved
add forgetting factor of queue (ablation)FakeCLR with latent augmentation · FFHQ-100FID: 44.10 -> 41.62Improved
add forgetting factor of queue (ablation)FakeCLR with latent augmentation · FFHQ-2KFID: 10.65 -> 10.40Improved
add diversity-aware queue (ablation)FakeCLR without it · FFHQ-100FID: 41.62 -> 42.56Hurt
add diversity-aware queue (ablation)FakeCLR without it · FFHQ-2KFID: 10.40 -> 9.90Improved

Later papers that compared with this method

3 later accepted papers report FakeCLR as a baseline in their results tables; 2 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