AI Paper Atlas

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

Smoothness Similarity Regularization for Few-Shot GAN Adaptation

Vadim Sushko, Ruyu Wang, Juergen Gall

ICCV 2023 · Label-efficient and robust learning › Domain adaptation and generalization · approach: Cross-domain few-shot with transformers · 7 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 smoothness similarity regularization L_SS to the generator (without L_all) (ablation)StyleGANv2 few-shot adaptation · Face->Anime, Church->Shellsdiversity (LPIPS) and qualityMixed
add multi-layer discriminator loss L_all (without L_SS) (ablation)StyleGANv2 few-shot adaptation · Face->Anime, Church->Shellsimage quality and diversityMixed
combine L_SS and L_all (ablation)StyleGANv2 few-shot adaptation · Face->Anime, Church->ShellsFID and LPIPSImproved
replace PPL and MixDL regularizers with L_SS (ablation)StyleGANv2 with L_all · Face->Anime, Church->ShellsFID and LPIPSImproved
use L_all instead of PatchGAN discriminator loss (ablation)StyleGANv2 discriminator · Church->Shells and Face->AnimeFIDImproved
increase lambda_SS to large values (25.0, 125.0) (ablation)L_SS · Face->Anime, Church->ShellsFID vs LPIPSMixed
apply L_SS on very high-resolution generator features (e.g. 128x128) instead of 32x32 (ablation)L_SS · Face->Anime, Church->Shellsimage qualityHurt
weight earlier D layers higher in L_all instead of uniform (ablation)L_all · Face->Anime vs Church->ShellsFIDMixed
weight later D layers higher in L_all instead of uniform (ablation)L_all · Face->Anime, Church->ShellsFID vs LPIPSMixed
regularize smoothness w.r.t. class embeddings as well as noise in BigGAN (ablation)BigGAN few-shot adaptation · ImageNet->Flowers, ImageNet->Pokemonsdiversity (LPIPS)Improved
apply method to structurally close source-target pairs (Face->Sketch, Face->Sunglasses)Ours vs prior methods · Face->Sketch, Face->SunglassesFID and LPIPSNo 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