AI Paper Atlas

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

Unsupervised Domain Attention Adaptation Network for Caricature Attribute Recognition

Wen Ji, Kelei He, Jing Huo, Zheng Gu, Yang Gao

ECCV 2020 · Label-efficient and robust learning › Domain adaptation and generalization · approach: Geometric alignment and synthetic-to-real adaptation · 8 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 multi-task attribute-group classifiers (ablation)Source Only · WebCariA (photo to caricature)average F1: 0.6770 -> 0.6922Improved
add multi-task attribute-group classifiers (ablation)Target Only · WebCariA (photo to caricature)average F1: 0.7358 -> 0.7601Improved
add multi-task attribute-group classifiers (ablation)DTA · WebCariA (photo to caricature)average F1: 0.6941 -> 0.7000Improved
add multi-task attribute-group classifiers (ablation)Source Only · WebCariA (photo to caricature)average accuracy: 0.8054 -> 0.8050No clear effect
add multi-task attribute-group classifiers (ablation)DTA · WebCariA (photo to caricature)average accuracy: 0.8100 -> 0.8076Hurt
add multi-task attribute-group classifiers (ablation)Target Only · WebCariA (photo to caricature)average accuracy: 0.8474 -> 0.8526Improved
add feature consistency to label consistency (ablation)DAAN-L · WebCariA (photo to caricature)average F1: 0.7038 -> 0.7181Improved
add attention consistency to label consistency (ablation)DAAN-L · WebCariA (photo to caricature)average F1: 0.7038 -> 0.7192Improved
add attention consistency to label plus feature consistency (ablation)DAAN-LF · WebCariA (photo to caricature)average F1: 0.7181 -> 0.7215Improved
add attention consistency to label plus feature consistency (ablation)DAAN-LF · WebCariA (photo to caricature)average accuracy: 0.8219 -> 0.8239Improved
use attention consistency instead of feature consistency as single constraint (ablation)DAAN · WebCariA (photo to caricature)average F1: 0.7094 -> 0.7107Improved
replace DTA with DAAN-LFADAAN · WebCariA (photo to caricature)average F1: 0.6941 -> 0.7215Improved

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