AI Paper Atlas

Research map / Label-efficient and robust learning / Zero-/few-shot and meta-learning

Improving Diversity in Zero-Shot GAN Adaptation with Semantic Variations

Seogkyu Jeon, Bei Liu, Pilhyeon Lee, Kibeom Hong, Jianlong Fu, Hyeran Byun

ICCV 2023 · Label-efficient and robust learning › Zero-/few-shot and meta-learning · approach: Transductive and semantic-dictionary zero-shot · 1 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 directional loss with directional moment loss over learned semantic variations (ablation)zero-shot GAN adaptation baseline · AFHQ Dog-to-Catintra-cluster LPIPS (Avg.): 0.402 -> 0.464Improved
add elastic weight consolidation loss (ablation)Baseline + L_dm · AFHQ Dog-to-Catintra-cluster LPIPS (Avg.): 0.464 -> 0.493Improved
add relation consistency loss (ablation)Baseline + L_dm + L_EWC · AFHQ Dog-to-Catintra-cluster LPIPS (Avg.): 0.493 -> 0.507Improved
use L_EWC instead of layer selection in StyleGAN-NADA (ablation)StyleGAN-NADA · AFHQ Dog-to-Catintra-cluster LPIPS (Avg.): 0.460 -> 0.480Improved
full method vs StyleGAN-NADA + L_EWC (ablation)StyleGAN-NADA + L_EWC · AFHQ Dog-to-Catintra-cluster LPIPS (Avg.): 0.480 -> 0.507Improved
proposed zero-shot method vs 10-shot Ojha et al. on diversityOurs · AFHQ Dog-to-Catintra-cluster LPIPS (Avg.): 0.575 -> 0.507Hurt
proposed method vs StyleGAN-NADA on FID in zero-shotOurs · AFHQ Dog-to-CatFID: 70.225 -> 61.347Improved
extend method to 10-shot settingOurs · AFHQ Dog-to-Cat 10-shotFID: 57.196 -> 45.084 (vs Ojha et al.)Improved
increase lambda_EWC beyond or below 10^7 (ablation)Ours · AFHQ Dog-to-CatFID: 61.347 -> 94.317 (1e5), 81.758 (1e8)Hurt
increase number of semantic variations K from 6 to 8 (ablation)Ours · AFHQ Dog-to-CatFID: 61.347 -> 66.698Hurt

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