Research map / Label-efficient and robust learning / Domain adaptation and generalization
Implicit Class-Conditioned Domain Alignment for Unsupervised 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 implicit class-conditioned alignment with MDD | MDD · Office-Home RS-UT | per-class average accuracy: 58.50 -> 61.67 | Helped |
| use implicit class-conditioned alignment with MDD | MDD · Office-Home standard | accuracy: 68.1 -> 69.5 | Helped |
| use implicit class-conditioned alignment with MDD | MDD · VisDA2017 synthetic→real | target accuracy: 74.6 -> 75.8 | Helped |
| use source-balanced sampling | MDD · Office-Home RS-UT | per-class average accuracy: 55.44 -> 58.50 | Helped |
| add implicit alignment | DANN · SVHN→MNIST, source balanced/target imbalanced (mild) | per-class average accuracy: 78.2±2.8 -> 88.6±0.7 | Helped |
| add implicit alignment | MDD · Office-Home Ar→Cl | accuracy: 55.3 -> 56.2 | Helped |
| add class-conditioned sampling while keeping masking (ablation) | MDD · Office-Home Ar→Cl | accuracy: 55.5 -> 56.2 | Helped |
| add masking while keeping class-conditioned sampling (ablation) | MDD · Office-Home Ar→Cl | accuracy: 54.6 -> 56.2 | Helped |
| add class-conditioned sampling while keeping masking (ablation) | MDD · Office-Home Cl→Pr | accuracy: 70.1 -> 73.1 | Helped |
| add masking while keeping class-conditioned sampling (ablation) | MDD · Office-Home Cl→Pr | accuracy: 70.5 -> 73.1 | Helped |
| increase class diversity in each minibatch (ablation) | implicit alignment domain adaptation · Office-Home RS-UT | target accuracy | Helped |
| sample target examples using ground-truth labels rather than pseudo-labels (ablation) | implicit alignment domain adaptation · Office-Home RS-UT | target accuracy | Helped |
Closest papers by meaning
- Co-regularized Alignment for Unsupervised Domain Adaptation (NeurIPS 2018 · similarity 0.91)
- A Prototype-Oriented Framework for Unsupervised Domain Adaptation (NeurIPS 2021 · similarity 0.90)
- Domain Adaptation with Asymmetrically-Relaxed Distribution Alignment (ICML 2019 · similarity 0.90)
- MetaAlign: Coordinating Domain Alignment and Classification for Unsupervised Domain Adaptation (CVPR 2021 · similarity 0.89)
- CASUAL: Conditional Support Alignment for Domain Adaptation with Label Shift (AAAI 2025 · similarity 0.89)
- On Unsupervised Domain Adaptation: Pseudo Label Guided Mixup for Adversarial Prompt Tuning (AAAI 2024 · 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.