AI Paper Atlas

Research map / Image generation / Editing and style transfer

Particularity beyond Commonality: Unpaired Identity Transfer with Multiple References

Ruizheng Wu, Xin Tao, Yingcong Chen, Xiaoyong Shen, Jiaya Jia

ECCV 2020 · Image generation › Editing and style transfer · approach: Image-to-image translation · 2 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 category classification discriminator Dcl (ablation)multi-reference framework · RaFDAcc (%): 16.77 -> 73.03Improved
add category classification discriminator Dcl (ablation)multi-reference framework · RaFDIS: 5.80 -> 2.49Hurt
add category classification discriminator Dcl (ablation)multi-reference framework · RaFDmFID (1e3): 12.13 -> 6.08Improved
add category comparison discriminator Dco (ablation)multi-reference framework · RaFDAcc (%): 68.84 -> 73.03Improved
add category comparison discriminator Dco (ablation)multi-reference framework · RaFDmFID (1e3): 7.70 -> 6.08Improved
add category comparison discriminator Dco (ablation)multi-reference framework · RaFDIS: 2.41 -> 2.49Improved
increase reference images from 1 to 3 (ablation)multi-reference framework · RaFDAcc (%): 53.12 -> 73.03Improved
increase reference images from 3 to 5 (ablation)multi-reference framework · RaFDAcc (%): 73.03 -> 90.01Improved
increase reference images from 5 to 10 (ablation)multi-reference framework · RaFDAcc (%): 90.01 -> 90.21No clear effect
increase reference images from 1 to 10 (ablation)multi-reference framework · RaFDRuntime (ms): 51.1 -> 71.5Hurt
increase reference images from 1 to 5 (ablation)multi-reference framework · RaFDIS: 3.31 -> 1.46Hurt
use semantic pyramid alignment instead of only highest-level features (ablation)multi-reference framework · RaFD (qualitative)visual qualityImproved

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