Research map / Label-efficient and robust learning / Domain adaptation and generalization
Separate to Adapt: Open Set Domain Adaptation via Progressive Separation
Check 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 progressive known/unknown separation and weighted adversarial adaptation | open set domain adaptation · Digits (average) | OS accuracy: 82.4 -> 87.3 | Helped |
| use progressive known/unknown separation and weighted adversarial adaptation | open set domain adaptation · VisDA-2017 Synthetic → Real | OS accuracy: 62.9 -> 66.8 | Helped |
| use progressive known/unknown separation and weighted adversarial adaptation | open set domain adaptation · Office-31 (average) | OS accuracy: 90.8 -> 92.9 | Helped |
| use progressive known/unknown separation and weighted adversarial adaptation | open set domain adaptation · Office-Home (average) | OS accuracy: 66.7 -> 69.5 | Helped |
| add instance-level weighting of target samples during domain adversarial learning (ablation) | STA · Office-31 (average) | OS accuracy: 86.1 -> 92.9 | Helped |
| use a multi-binary classifier instead of a softmax classifier (ablation) | STA · Office-31 (average) | OS accuracy: 91.5 -> 92.9 | Helped |
| add the fine-grained binary classifier (ablation) | STA · Office-31 (average) | OS accuracy: 87.2 -> 92.9 | Helped |
| alternate between separation and adaptation (ablation) | STA · Office-31 (average) | OS accuracy: 92.5 -> 92.9 | Helped |
Closest papers by meaning
- Open-Set Heterogeneous Domain Adaptation: Theoretical Analysis and Algorithm (AAAI 2025 · similarity 0.90)
- COSDA: Counterfactual-based Susceptibility Risk Framework for Open-Set Domain Adaptation (ICML 2025 · similarity 0.90)
- Dynamic Target Distribution Estimation for Source-Free Open-Set Domain Adaptation (AAAI 2025 · similarity 0.89)
- Distinguish Then Exploit: Source-free Open Set Domain Adaptation via Weight Barcode Estimation and Sparse Label Assignment (CVPR 2025 · similarity 0.89)
- Revisiting Source-Free Domain Adaptation: Insights into Representativeness, Generalization, and Variety (CVPR 2025 · similarity 0.89)
- Understanding and Improving Source-free Domain Adaptation from a Theoretical Perspective (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.