Research map / Label-efficient and robust learning / Domain adaptation and generalization
STEM: An Approach to Multi-Source Domain Adaptation With Guarantees
Van-Anh Nguyen, Tuan Nguyen, Trung Le, Quan Hung Tran, Dinh Phung
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 |
|---|---|---|---|
| use simplified domain discriminator instead of theoretical oriented one (ablation) | STEM · Digits-five ->mm | accuracy (%): 86.8 -> 89.7 | Improved |
| use simplified domain discriminator instead of theoretical oriented one (ablation) | STEM · Digits-five ->mt | accuracy (%): 99.1 -> 99.4 | Improved |
| add VAT and entropy clustering losses (ablation) | STEM · Digits-five ->mm | accuracy (%): 83.04 -> 89.71 | Improved |
| add VAT and entropy clustering losses (ablation) | STEM · Digits-five ->up | accuracy (%): 96.86 -> 98.42 | Improved |
| add student trained to mimic teacher (ablation) | STEM · Digits-five average | accuracy (%): 92.7 -> 95.0 | Improved |
| add student trained to mimic teacher (ablation) | STEM · DomainNet average | accuracy (%): 51.6 -> 53.4 | Improved |
| add student trained to mimic teacher (ablation) | STEM · Office-Caltech10 average | accuracy (%): 97.9 -> 97.9 | No clear effect |
Later papers that compared with this method
1 later accepted paper reports STEM as a baseline in their results tables; 0 of them report a better number on most of the results they share with it.
- Efficient Memory Crystallization for Graph Learning under Non-Stationary Distribution Shifts (NeurIPS 2026 · better on 1 of 2 shared results)
Matched by method name in results tables read by AI. Authors' own tables tend to favour the newer method, and a comparison can be missed when a method is renamed.
Closest papers by meaning
- On Balancing Bias and Variance in Unsupervised Multi-Source-Free Domain Adaptation (ICML 2023 · similarity 0.91)
- Partial Feature Selection and Alignment for Multi-Source Domain Adaptation (CVPR 2021 · similarity 0.91)
- Graphical Modeling for Multi-Source Domain Adaptation (TPAMI 2022 · similarity 0.90)
- Understanding and Improving Source-free Domain Adaptation from a Theoretical Perspective (CVPR 2024 · similarity 0.89)
- Revisiting Source-Free Domain Adaptation: Insights into Representativeness, Generalization, and Variety (CVPR 2025 · similarity 0.89)
- Invertible Projection and Conditional Alignment for Multi-Source Blended-Target Domain Adaptation (AAAI 2025 · similarity 0.89)
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.
