Research map / Label-efficient and robust learning / Domain adaptation and generalization
Online Meta-Learning for Multi-Source and Semi-Supervised Domain Adaptation
Da Li, Timothy Hospedales
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 online meta-learning of initial conditions | DANN · PACS (multi-source DA, ResNet-18) | avg accuracy: 83.62 -> 85.58 | Improved |
| add online meta-learning of initial conditions | MCD (n=4) · PACS (multi-source DA, ResNet-18) | avg accuracy: 84.79 -> 87.24 | Improved |
| add online meta-learning of initial conditions | MCD (os) · PACS (multi-source DA, ResNet-18) | avg accuracy: 85.15 -> 86.39 | Improved |
| add online meta-learning of initial conditions | MCD · Office-Home (multi-source DA, ResNet-50) | avg accuracy: 73.32 -> 73.83 | Improved |
| add online meta-learning of initial conditions | MCD · DomainNet MSDA (ResNet-18) | avg accuracy: 40.69 -> 41.00 | Improved |
| add online meta-learning of initial conditions | MCD · DomainNet MSDA (ResNet-34) | avg accuracy: 43.85 -> 44.19 | Improved |
| add online meta-learning of initial conditions | DANN · DomainNet MSDA (ResNet-18) | avg accuracy: 40.16 -> 40.65 | Improved |
| add online meta-learning of initial conditions | MME · Office-Home 3-shot SSDA (AlexNet) | avg accuracy: 45.5 -> 45.6 | No clear effect |
| add online meta-learning of initial conditions | MME · Office-Home 3-shot SSDA (ResNet-34) | avg accuracy: 64.7 -> 65.4 | Improved |
| add online meta-learning of initial conditions | MME · DomainNet SSDA (ResNet-34) | avg accuracy: 68.9 -> 70.1 | Improved |
| add online meta-learning of initial conditions | MME · DomainNet SSDA (AlexNet) | avg accuracy: 48.2 -> 48.8 | Improved |
| vary meta-update ratio S from 3 to 5 to 10 (ablation) | Meta-MCD · DomainNet MSDA (ResNet-18) | avg accuracy: 41.02 / 40.98 / 40.93 | No clear effect |
Closest papers by meaning
- On Balancing Bias and Variance in Unsupervised Multi-Source-Free Domain Adaptation (ICML 2023 · similarity 0.89)
- Minimum Class Confusion for Versatile Domain Adaptation (ECCV 2020 · similarity 0.89)
- Learning to Adapt to Evolving Domains (NeurIPS 2020 · similarity 0.89)
- Revisiting Source-Free Domain Adaptation: Insights into Representativeness, Generalization, and Variety (CVPR 2025 · similarity 0.88)
- Universal Semi-Supervised Domain Adaptation by Mitigating Common-Class Bias (CVPR 2024 · similarity 0.87)
- Understanding and Improving Source-free Domain Adaptation from a Theoretical Perspective (CVPR 2024 · 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.
