Research map / Label-efficient and robust learning / Domain adaptation and generalization
Learning Unbiased Transferability for Domain Adaptation by Uncertainty Modeling
Jian Hu, Haowen Zhong, Fei Yang, Shaogang Gong, Guile Wu, Junchi Yan
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 UTEP | DANN · Office-31 (UDA) | avg accuracy: 86.1 -> 88.0 | Improved |
| add UTEP | MDD · Office-31 (UDA) | avg accuracy: 88.9 -> 89.9 | Improved |
| add UTEP | CADA · Office-31 (UDA) | avg accuracy: 89.5 -> 90.0 | Improved |
| add UTEP | TransPar · Office-31 (UDA) | avg accuracy: 89.9 -> 90.8 | Improved |
| add UTEP | DANN · Office-Home (UDA) | avg accuracy: 65.2 -> 67.3 | Improved |
| add UTEP | CADA · Office-Home (UDA) | avg accuracy: 70.2 -> 70.6 | Improved |
| add UTEP | DANN · VisDA-2017 | mean accuracy: 72.3 -> 79.2 | Improved |
| add UTEP | MDD · VisDA-2017 | mean accuracy: 81.4 -> 82.3 | Improved |
| add UTEP rather than UPS pseudo labeling | DANN · Office-Home (3-shot SSL) | avg accuracy: 63.3 -> 65.1 | Improved |
| add bias loss to the full UTEP (ablation) | DANN+UTEP · Office-31 (UDA) | avg accuracy: 87.2 -> 88.0 | Improved |
| add negative cross-entropy to the full UTEP (ablation) | DANN+UTEP · Office-31 (UDA) | avg accuracy: 87.3 -> 88.0 | Improved |
| add target bias loss (TBL) to the full UTEP (ablation) | DANN+UTEP · Office-31 (UDA) | avg accuracy: 87.3 -> 88.0 | Improved |
Closest papers by meaning
- A Balanced and Uncertainty-aware Approach for Partial Domain Adaptation (ECCV 2020 · similarity 0.90)
- Transferable Adversarial Training: A General Approach to Adapting Deep Classifiers (ICML 2019 · similarity 0.90)
- Transferable Calibration with Lower Bias and Variance in Domain Adaptation (NeurIPS 2020 · similarity 0.89)
- On the Transferability and Discriminability of Representation Learning in Unsupervised Domain Adaptation (TPAMI 2025 · similarity 0.89)
- Revisiting the Domain Shift and Sample Uncertainty in Multi-source Active Domain Transfer (CVPR 2024 · similarity 0.88)
- Can We Evaluate Domain Adaptation Models Without Target-Domain Labels? (ICLR 2024 · 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.
