Research map / Label-efficient and robust learning / Domain adaptation and generalization
Multi-Source Distilling 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 Wasserstein-based source weights rather than uniform prediction weights (ablation) | MDDA · Digits-five | accuracy (%): 81.5 -> 88.1 | Helped |
| Use Wasserstein-based source weights rather than uniform prediction weights (ablation) | MDDA · Office-31 | accuracy (%): 83.1 -> 84.2 | Helped |
| Add source-sample distilling and classifier fine-tuning (ablation) | MDDA · Digits-five | accuracy (%): 87.8 -> 88.1 | Helped |
| Add source-sample distilling and classifier fine-tuning (ablation) | MDDA · Office-31 | accuracy (%): 83.7 -> 84.2 | Helped |
| Add source-sample distilling before classifier fine-tuning (ablation) | Wasserstein-distance-based ADDA, target sy · Digits-five source-to-target tasks | accuracy (%): 52.0 -> 54.5; 70.8 -> 71.0; 89.4 -> 89.5; 38.6 -> 40.8 | Mixed |
| Use MDDA rather than DCTN | Multi-source domain adaptation · Digits-five | accuracy (%): 84.8 -> 88.1 | Helped |
| Use MDDA rather than DCTN | Multi-source domain adaptation · Office-31 | accuracy (%): 83.8 -> 84.2 | Helped |
Closest papers by meaning
- Deep Cocktail Network: Multi-Source Unsupervised Domain Adaptation With Category Shift (CVPR 2018 · similarity 0.92)
- Adversarial Multiple Source Domain Adaptation (NeurIPS 2018 · similarity 0.90)
- Unsupervised Domain Adaptation with Residual Transfer Networks (NeurIPS 2016 · similarity 0.89)
- Invertible Projection and Conditional Alignment for Multi-Source Blended-Target Domain Adaptation (AAAI 2025 · similarity 0.87)
- A General Representation-Based Approach to Multi-Source Domain Adaptation (ICML 2025 · similarity 0.87)
- Revisiting the Domain Shift and Sample Uncertainty in Multi-source Active Domain Transfer (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.