AI Paper Atlas

Research map / Image generation / Editing and style transfer

Bridging the Gap Between Label- and Reference-Based Synthesis in Multi-Attribute Image-to-Image Translation

Qiusheng Huang, Zhilin Zheng, Xueqi Hu, Li Sun, Qingli Li

ICCV 2021 · Image generation › Editing and style transfer · approach: Image-to-image translation · 6 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 reference encoding module and latent cycle loss to the label-only model (ablation)Model A · CelebA label-basedFID: 25.10 -> 17.07Improved
add the reference encoding module and latent cycle loss to the label-only model (ablation)Model A · CelebA label-basedAccuracy: 84.3 -> 83.5No clear effect
add source encoding S_s to LEM and REM (ablation)Model B · CelebA label-basedFID: 17.07 -> 12.14Improved
add source encoding S_s to LEM and REM (ablation)Model B · CelebA reference-basedFID: 13.91 -> 9.52Improved
add interpolated image to adversarial loss (ablation)Model C · CelebA label-basedAccuracy: 82.8 -> 86.2Improved
add interpolated image to adversarial loss (ablation)Model C · CelebA label-basedFID: 12.14 -> 17.32Hurt
add mode seeking loss (ablation)Model D · CelebA label-basedLPIPS: 0.012 -> 0.030Improved
add mode seeking loss (ablation)Model D · CelebA label-basedFID: 17.32 -> 14.03Improved
add style closeness loss L_sty (ablation)Model E · CelebA label-basedAccuracy: 82.9 -> 85.1Improved
add style closeness loss L_sty (ablation)Model E · CelebA label-basedLPIPS: 0.030 -> 0.034Improved
add attribute keeping constraint L_ak (ablation)Model F · CelebA label-basedAccuracy: 85.1 -> 87.0Improved
add attribute keeping constraint L_ak (ablation)Model F · CelebA reference-basedAccuracy: 39.5 -> 54.0Improved

Earlier methods this paper compares with

Named baselines from earlier accepted papers in this paper's results tables: better than 3 of 3 on most shared results.

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