AI Paper Atlas

Research map / Image generation / Editing and style transfer

Continuous and Diverse Image-to-Image Translation via Signed Attribute Vectors

Qi Mao, Hung-Yu Tseng, Hsin-Ying Lee, Jia‐Bin Huang, Siwei Ma, Ming–Hsuan Yang

IJCV 2022 · Image generation › Editing and style transfer · approach: Image-to-image translation · 34 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 the sign operation to attribute vectors (signed attribute vectors) (ablation)Ours · CelebA-HQ male-to-femaletranslation ACCImproved
add reverse sign domain adversarial loss (ablation)Ours · CelebA-HQ male-to-femaleDIPD and LPIPSImproved
add interpolated domain adversarial loss (ablation)Ours · CelebA-HQ male-to-femaleFID and LPIPSImproved
add style reconstruction loss (ablation)Ours · CelebA-HQ male-to-femaleFIDImproved
add fusing network before the generator (ablation)Ours · CelebA-HQ male-to-femaleFIDImproved
add MMD constraint on attribute vectors (ablation)Ours · CelebA-HQ male-to-female / AFHQ wildlifeACC, FID, DIPD, LPIPS smoothnessMixed
replace StarGAN-v2 separate per-domain attribute spaces with signed attribute vectorsOurs vs StarGAN-v2 · CelebA-HQ and AFHQsmoothness of LPIPS curveImproved
use larger batch size for FUNITFUNIT · CelebA-HQrealism preference: 82.50 -> 83.75Improved

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