AI Paper Atlas

Research map / Image generation / Text-to-image diffusion

LoFGAN: Fusing Local Representations for Few-Shot Image Generation

Zheng Gu, Wenbin Li, Jing Huo, Lei Wang, Yang Gao

ICCV 2021 · Image generation › Text-to-image diffusion · approach: Personalized and region-controlled generation · 78 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
replace global fusion with the local fusion module (LFM) (ablation)MatchingGAN† · Flowers FIDFID: 139.90 -> 86.59Improved
replace global fusion with the local fusion module (LFM) (ablation)MatchingGAN† · Animal Faces FIDFID: 147.95 -> 112.99Improved
replace global fusion with the local fusion module (LFM) (ablation)MatchingGAN† · VGGFace FIDFID: 27.93 -> 22.99Improved
replace global fusion with the local fusion module (LFM) (ablation)MatchingGAN† · Flowers LPIPSLPIPS: 0.3410 -> 0.3704Improved
add local reconstruction loss to LFM (ablation)MatchingGAN†+LFM · Flowers FIDFID: 86.59 -> 79.33Improved
add local reconstruction loss to LFM (ablation)MatchingGAN†+LFM · VGGFace FIDFID: 22.99 -> 20.31Improved
add local reconstruction loss to LFM (ablation)MatchingGAN†+LFM · Animal Faces FIDFID: 112.99 -> 112.81No clear effect
add local reconstruction loss to LFM (ablation)MatchingGAN†+LFM · Animal Faces LPIPSLPIPS: 0.5024 -> 0.4964Hurt
augment classifier training data with LoFGAN imagesResNet18 classifier · Flowers low-data classificationtop-1 accuracy: 60.00 -> 65.10Improved
augment classifier training data with MatchingGAN†ResNet18 classifier · VGGFace low-data classificationtop-1 accuracy: 67.38 -> 65.17Hurt
add LFM to MatchingGAN† augmentation (ablation)ResNet18 classifier · Flowers low-data classificationtop-1 accuracy: 60.39 -> 62.75Improved
increase training shots k_train from 3 to 9LoFGAN · Flowersaverage FID: 78.30 -> 77.18Improved

Later papers that compared with this method

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

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