Research map / Label-efficient and robust learning / Domain adaptation and generalization
Cross-Domain Kernel Induction for Transfer Learning
Wei-Cheng Chang, Yuexin Wu, Hanxiao Liu, Yiming Yang
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 |
|---|---|---|---|
| use parallel-data kernel completion (KerTL) instead of CorrNet | KerTL · MNIST (m=2, l=1024) | AUC: 0.934 -> 0.962 | Improved |
| use KerTL instead of strongest baseline HHTL | KerTL · APR average (m=2, l=1024) | AUC: 0.704 -> 0.745 | Improved |
| use parallel data (HHTL/CorrNet/KerTL) vs methods without parallel data | TL methods · APR and MNIST | AUC: 0.532 -> 0.745 | Improved |
| use KerTL instead of SVM with more target labels (above ~200) on APR | KerTL · APR varying m | AUC | Hurt |
Closest papers by meaning
- Universal Semi-Supervised Domain Adaptation by Mitigating Common-Class Bias (CVPR 2024 · similarity 0.86)
- Enhancing Semi-supervised Domain Adaptation via Effective Target Labeling (AAAI 2024 · similarity 0.85)
- A Unified Framework for Heterogeneous Semi-supervised Learning (CVPR 2025 · similarity 0.85)
- Theoretical Performance Guarantees for Partial Domain Adaptation via Partial Optimal Transport (ICML 2025 · similarity 0.85)
- Unlocking the Potential of Unlabeled Data in Semi-Supervised Domain Generalization (CVPR 2025 · similarity 0.85)
- Pseudo-Labeling for Unsupervised Domain Adaptation with Kernel GLMs (NeurIPS 2026 · similarity 0.85)
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.
