Research map / Label-efficient and robust learning / Domain adaptation and generalization
Domain Adaptation under Open Set Label Shift
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 |
|---|---|---|---|
| Use PULSE’s label-shift correction followed by a single PU learning stage instead of k-PU | OSLS adaptation · CIFAR-10 | Acc (All): 83.6 -> 86.1 | Helped |
| Use PULSE’s label-shift correction followed by a single PU learning stage instead of domain discrimination | OSLS adaptation · CIFAR-10 | MPE (Novel): 0.331 -> 0.008 | Helped |
| Use PULSE instead of DANCE | OSLS adaptation · CIFAR-100 | Acc (All): 47.3 -> 63.4 | Helped |
| Use PULSE instead of domain discrimination | OSLS adaptation · CIFAR-100 | MPE (Novel): 0.046 -> 0.078 | Hurt |
| Use PULSE instead of k-PU | OSLS adaptation · Entity30 | Acc (All): 50.7 -> 58.0 | Helped |
| Use PULSE instead of domain discrimination | OSLS adaptation · Entity30 | MPE (Novel): 0.135 -> 0.054 | Helped |
| Use PULSE instead of k-PU | OSLS adaptation · Newsgroups20 | Acc (All): 52.1 -> 62.2 | Helped |
| Use PULSE instead of BODA | OSLS adaptation · Newsgroups20 | MPE (Novel): 0.16 -> 0.061 | Helped |
| Use PULSE instead of k-PU | OSLS adaptation · Tabula Muris | Acc (All): 85.9 -> 87.8 | Helped |
| Use PULSE instead of domain discrimination | OSLS adaptation · Tabula Muris | MPE (Novel): 0.071 -> 0.058 | Helped |
| Use PULSE instead of k-PU | OSLS adaptation · BreakHis | Acc (All): 75.6 -> 79.1 | Helped |
| Use PULSE instead of k-PU | OSLS adaptation · BreakHis | MPE (Novel): 0.059 -> 0.054 | Helped |
Closest papers by meaning
- A Theory of Learning Unified Model via Knowledge Integration from Label Space Varying Domains (CVPR 2025 · similarity 0.89)
- Open-Set Heterogeneous Domain Adaptation: Theoretical Analysis and Algorithm (AAAI 2025 · similarity 0.89)
- COSDA: Counterfactual-based Susceptibility Risk Framework for Open-Set Domain Adaptation (ICML 2025 · similarity 0.89)
- Confusing Pair Correction Based on Category Prototype for Domain Adaptation under Noisy Environments (AAAI 2024 · similarity 0.89)
- Pseudo-Labeling for Unsupervised Domain Adaptation with Kernel GLMs (NeurIPS 2026 · similarity 0.89)
- Universal Semi-Supervised Domain Adaptation by Mitigating Common-Class Bias (CVPR 2024 · similarity 0.88)
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.