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
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 changed | Where | Measured | Effect |
|---|---|---|---|
| add multi-task attribute-group classifiers (ablation) | Source Only · WebCariA (photo to caricature) | average F1: 0.6770 -> 0.6922 | Improved |
| add multi-task attribute-group classifiers (ablation) | Target Only · WebCariA (photo to caricature) | average F1: 0.7358 -> 0.7601 | Improved |
| add multi-task attribute-group classifiers (ablation) | DTA · WebCariA (photo to caricature) | average F1: 0.6941 -> 0.7000 | Improved |
| add multi-task attribute-group classifiers (ablation) | Source Only · WebCariA (photo to caricature) | average accuracy: 0.8054 -> 0.8050 | No clear effect |
| add multi-task attribute-group classifiers (ablation) | DTA · WebCariA (photo to caricature) | average accuracy: 0.8100 -> 0.8076 | Hurt |
| add multi-task attribute-group classifiers (ablation) | Target Only · WebCariA (photo to caricature) | average accuracy: 0.8474 -> 0.8526 | Improved |
| add feature consistency to label consistency (ablation) | DAAN-L · WebCariA (photo to caricature) | average F1: 0.7038 -> 0.7181 | Improved |
| add attention consistency to label consistency (ablation) | DAAN-L · WebCariA (photo to caricature) | average F1: 0.7038 -> 0.7192 | Improved |
| add attention consistency to label plus feature consistency (ablation) | DAAN-LF · WebCariA (photo to caricature) | average F1: 0.7181 -> 0.7215 | Improved |
| add attention consistency to label plus feature consistency (ablation) | DAAN-LF · WebCariA (photo to caricature) | average accuracy: 0.8219 -> 0.8239 | Improved |
| use attention consistency instead of feature consistency as single constraint (ablation) | DAAN · WebCariA (photo to caricature) | average F1: 0.7094 -> 0.7107 | Improved |
| replace DTA with DAAN-LFA | DAAN · WebCariA (photo to caricature) | average F1: 0.6941 -> 0.7215 | Improved |
Closest papers by meaning
- Attributes-Guided and Pure-Visual Attention Alignment for Few-Shot Recognition (AAAI 2021 · similarity 0.83)
- Effectively Leveraging Attributes for Visual Similarity (ICCV 2021 · similarity 0.83)
- PriSM: Parsing and Style-Mixed Consistency for Unsupervised Domain Adaptation in Facial Landmark Detection (ECCV 2026 · similarity 0.83)
- CDAC: Cross-domain Attention Consistency in Transformer for Domain Adaptive Semantic Segmentation (ICCV 2023 · similarity 0.82)
- WarpGAN: Automatic Caricature Generation (CVPR 2019 · similarity 0.82)
- Learning to Caricature via Semantic Shape Transform (IJCV 2021 · similarity 0.82)
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.
