Research map / Label-efficient and robust learning / Domain adaptation and generalization
Domain-Constraint Transfer Coding for Imbalanced Unsupervised Domain Adaptation
Read the paperCheck your idea against 108,967 papers
AI-extracted summary. Written by AI from the paper's title only (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 locality adaptor to the coding objective (ablation) | DcTC · Office+Caltech balanced UDA | accuracy PC (%): 83.98 -> 88.8 | Helped |
| use SRC instead of nearest neighbor classifier (ablation) | DcTC · Office+Caltech balanced UDA | accuracy PC (%): 87.39 -> 88.8 | No clear effect |
| DcTC versus best baseline JDA on balanced UDA | DcTC · Office+Caltech balanced UDA | accuracy PC (%): 87.55 -> 88.8 | Helped |
| DcTC versus feature-learning baselines when target has 1 class | DcTC · Office+Caltech label-imbalanced UDA, C_T=1 | accuracy (%): 81.16 -> 87.11 | Helped |
| DcTC versus GFK on multi-sub-domain imbalanced UDA | DcTC · Office+Caltech multi-sub-domain | average accuracy (%): 80.93 -> 90.94 | Helped |
| vary feature dimension, alpha, lambda (ablation) | DcTC · Office+Caltech balanced UDA | accuracy | No clear effect |
Closest papers by meaning
- CDTrans: Cross-domain Transformer for Unsupervised Domain Adaptation (ICLR 2022 · similarity 0.89)
- Dynamic Weighted Learning for Unsupervised Domain Adaptation (CVPR 2021 · similarity 0.89)
- Aligning Domain-Specific Distribution and Classifier for Cross-Domain Classification from Multiple Sources (AAAI 2019 · similarity 0.89)
- FixBi: Bridging Domain Spaces for Unsupervised Domain Adaptation (CVPR 2021 · similarity 0.89)
- Can We Evaluate Domain Adaptation Models Without Target-Domain Labels? (ICLR 2024 · similarity 0.88)
- Balanced Learning for Domain Adaptive Semantic Segmentation (ICML 2025 · similarity 0.87)
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.