Research map / Label-efficient and robust learning / Domain adaptation and generalization
Class Overwhelms: Mutual Conditional Blended-Target 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 |
|---|---|---|---|
| align class-conditional feature distributions and correct the classifier without domain labels | MCDA · Office-31 | accuracy: outperforms them by 0.8% | Helped |
| align class-conditional feature distributions and correct the classifier without domain labels | MCDA · Office-Home | accuracy: outperform them by 1.3% | Helped |
| apply MCDA rather than the strongest reported domain-label baseline | MCDA · DomainNet | accuracy: 34.4 -> 34.5 | Helped |
| apply MCDA rather than the strongest listed label-shift baseline | MCDA · Office-Home-LMT | accuracy: 65.0 -> 65.9 | Helped |
| add one RandAug augmented sample per example (ablation) | MCDA · Office-Home-LMT | accuracy: 65.9 -> 68.1 | Helped |
| add mixed target labeling (ablation) | MCDA · Office-Home | accuracy: 70.1 -> 71.1 | Helped |
| add mixed target labeling (ablation) | MCDA · DomainNet selected domains | accuracy: 34.2 -> 36.7 | Helped |
| add balanced sampling (ablation) | MCDA · Office-Home | accuracy: 67.2 -> 70.3 | Helped |
| add balanced sampling (ablation) | MCDA · DomainNet selected domains | accuracy: 32.1 -> 35.8 | Helped |
| add low-level feature manipulation (ablation) | MCDA with mixed target labels and balanced sampling · Office-Home | accuracy: 70.3 -> 71.1 | Helped |
| add low-level feature manipulation (ablation) | MCDA with mixed target labels and balanced sampling · DomainNet selected domains | accuracy: 35.8 -> 36.7 | Helped |
| vary the uncertainty threshold from 0.01 to 0.09 (ablation) | MCDA · Office-Home (Art) | accuracy: 71.9, 71.9, 71.7, 72.3, 71.8 | No clear effect |
Closest papers by meaning
- Invertible Projection and Conditional Alignment for Multi-Source Blended-Target Domain Adaptation (AAAI 2025 · similarity 0.89)
- Style Adaptation and Uncertainty Estimation for Multi-Source Blended-Target Domain Adaptation (NeurIPS 2024 · similarity 0.88)
- Collaborative Semantic Consistency Alignment for Blended-Target Domain Adaptation (AAAI 2025 · similarity 0.88)
- Open-Set Heterogeneous Domain Adaptation: Theoretical Analysis and Algorithm (AAAI 2025 · similarity 0.88)
- A Separation and Alignment Framework for Black-Box Domain Adaptation (AAAI 2024 · similarity 0.88)
- Universal Semi-Supervised Domain Adaptation by Mitigating Common-Class Bias (CVPR 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.