Research map / Label-efficient and robust learning / Domain adaptation and generalization
Domain Aggregation Networks for Multi-Source 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 |
|---|---|---|---|
| Use DARN instead of MDMN | Multi-source domain adaptation · Amazon sentiment—Electronics | accuracy (%): 85.61 -> 85.75 | Helped |
| Use DARN instead of MDMN | Multi-source domain adaptation · Amazon sentiment—Books | accuracy (%): 80.13 -> 79.93 | Hurt |
| Use DARN instead of MDAN | Multi-source domain adaptation · Amazon sentiment—DVD | accuracy (%): 81.66 -> 81.57 | Hurt |
| Use DARN instead of MDMN | Multi-source domain adaptation · Amazon sentiment—average | accuracy (%): 83.61 -> 83.60 | No clear effect |
| Use DARN instead of MDAN | Multi-source domain adaptation · Digit recognition—MNIST | accuracy (%): 97.10 -> 98.09 | Helped |
| Use DARN instead of MDMN | Multi-source domain adaptation · Digit recognition—MNIST-M | accuracy (%): 64.34 -> 67.06 | Helped |
| Use DARN instead of MDAN | Multi-source domain adaptation · Digit recognition—SVHN | accuracy (%): 77.72 -> 81.58 | Helped |
| Use DARN instead of MDMN | Multi-source domain adaptation · Digit recognition—Synth | accuracy (%): 85.80 -> 86.79 | Helped |
| Use DARN instead of MDAN | Multi-source domain adaptation · Digit recognition—average | accuracy (%): 81.11 -> 83.38 | Helped |
| Use DANN with pooled sources instead of SRC without adaptation | Multi-source domain adaptation · Amazon sentiment—average | accuracy (%): 82.62 -> 82.64 | No clear effect |
| Use DANN with pooled sources instead of SRC without adaptation | Multi-source domain adaptation · Digit recognition—average | accuracy (%): 77.66 -> 77.63 | Hurt |
Closest papers by meaning
- Adversarial Multiple Source Domain Adaptation (NeurIPS 2018 · similarity 0.89)
- On Balancing Bias and Variance in Unsupervised Multi-Source-Free Domain Adaptation (ICML 2023 · similarity 0.89)
- Dynamic Transfer for Multi-Source Domain Adaptation (CVPR 2021 · similarity 0.88)
- Revisiting the Domain Shift and Sample Uncertainty in Multi-source Active Domain Transfer (CVPR 2024 · similarity 0.86)
- Theoretical Performance Guarantees for Partial Domain Adaptation via Partial Optimal Transport (ICML 2025 · similarity 0.86)
- Understanding and Improving Source-free Domain Adaptation from a Theoretical Perspective (CVPR 2024 · similarity 0.86)
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.