Research map / Label-efficient and robust learning / Domain adaptation and generalization
Curriculum Manager for Source Selection in Multi-Source Domain Adaptation
Luyu Yang, Yogesh Balaji, Ser-Nam Lim, Abhinav Shrivastava
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 the adversarial curriculum manager for source sample weighting | DANN (combined sources) · DomainNet average | accuracy (%): 43.0 -> 46.5 | Improved |
| add the adversarial curriculum manager for source sample weighting | DANN (combined sources) · DomainNet quickdraw target | accuracy (%): 7.7 -> 16.0 | Improved |
| use CMSS weighting instead of IWAN discriminator-based sample weights | IWAN · DomainNet average | accuracy (%): 43.1 -> 46.5 | Improved |
| use CMSS instead of M3SDA | M3SDA · Digits average | accuracy (%): 87.6 -> 90.8 | Improved |
| use CMSS instead of M3SDA | M3SDA · PACS average | accuracy (%): 88.3 -> 89.5 | Improved |
| use CMSS instead of M3SDA | M3SDA · PACS sketch target | accuracy (%): 76.7 -> 82.0 | Improved |
| use CMSS instead of M3SDA | M3SDA · Office-Caltech10 average | accuracy (%): 96.4 -> 97.2 | Improved |
| use CMSS instead of MDAN | MDAN · Digits to MNIST-M target | accuracy (%): 75.7 -> 75.3 | No clear effect |
| use CMSS instead of WBN | WBN · PACS photo/art targets | accuracy (%): 89.9 -> 88.6 | Mixed |
| train DANN on combined sources versus Source Only | Source Only · DomainNet quickdraw target | accuracy (%): 13.0 -> 7.7 | Hurt |
Closest papers by meaning
- Universal Source-Free Domain Adaptation (CVPR 2020 · similarity 0.89)
- From Big to Small: Adaptive Learning to Partial-Set Domains (TPAMI 2022 · similarity 0.88)
- Transferable Curriculum for Weakly-Supervised Domain Adaptation (AAAI 2019 · similarity 0.88)
- Bridging Theory and Practice in Source-Free Domain Adaptation via Adversarial Proxy Perturbation (ECCV 2026 · similarity 0.88)
- Towards Accurate and Robust Domain Adaptation Under Multiple Noisy Environments (TPAMI 2022 · similarity 0.88)
- Active Universal Domain Adaptation (ICCV 2021 · 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.
