AI Paper Atlas

Research map / Label-efficient and robust learning / Domain adaptation and generalization

MineGAN++: Mining Generative Models for Efficient Knowledge Transfer to Limited Data Domains

Yaxing Wang, Abel González-García, Chenshen Wu, Luis Herranz, Fahad Shahbaz Khan, Shangling Jui, Jian Yang, Joost van de Weijer

IJCV 2023 · Label-efficient and robust learning › Domain adaptation and generalization · approach: Mixture and distillation for domain shift · 11 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 Sparse Subnetwork Selection (S3) to MineGAN (ablation)MineGAN · FFHQ Women (100 images)FID: 93.1 -> 82.1Improved
add Sparse Subnetwork Selection (S3) to MineGAN (ablation)MineGAN · FFHQ Children (100 images)FID: 93.4 -> 84.9Improved
add finetuning stage after mining (ablation)MineGAN (w/o FT) · FFHQ Women (100 images)FID: 102.3 -> 93.1Improved
add Sparse Subnetwork Selection (S3) (ablation)MineGAN · FFHQ (25 images, SNGAN)KMMD: 0.337 -> 0.329Improved
add Sparse Subnetwork Selection to TransferGAN (ablation)TransferGAN · Animal face (Bear)FID: 82.82 -> 77.84Improved
select whole filters instead of individual weights (ablation)Sparse Subnetwork Selection · StyleGAN transferFIDImproved
use 6 miner layers instead of 2 (ablation)MineGAN miner · AFHQ cat (100 training images)FID: 51.6 -> 58.3Hurt
use permutation-based improved multi-GAN optimization (ablation)MineGAN(multi) · Red vehicle (0.5:0.5)FID: 59.4 -> 53.2Improved
fuse pretrained GANs into one conditional GAN before mining (ablation)MineGAN(multi) · Winter churchFID: 75.4 -> 69.3Improved
fuse pretrained GANs into one conditional GAN before mining (ablation)MineGAN(multi) · Red vehicle (0.5:0.5)FID: 53.2 -> 55.8Hurt
add Sparse Subnetwork Selection to fused mining (ablation)MineGAN(fusion) · Red vehicle (0.5:0.5)FID: 55.8 -> 48.5Improved
initialize critic from a different pretrained GAN (Kitchen vs Church) (ablation)MineGAN(multi) · LSUN TowerFID: 62.4 -> 61.7No clear effect

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