Research map / Label-efficient and robust learning / Domain adaptation and generalization
Weakly Supervised Open-Set Domain Adaptation by Dual-Domain Collaboration
Shuhan Tan, Jiening Jiao, Wei-Shi Zheng
Check 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 intraclass aggregation G (ablation) | CDA · DukeMTMC-reID 5↔6 | CMC rank-1: 49.8 -> 61.5 | Improved |
| add known-unknown separation U (ablation) | CDA · DukeMTMC-reID 5↔6 | CMC rank-1: 57.3 -> 61.5 | Improved |
| add conditional distribution alignment Dist_C (ablation) | CDA · DukeMTMC-reID 5↔6 | CMC rank-1: 23.1 -> 61.5 | Improved |
| add marginal distribution alignment Dist_M (ablation) | CDA · DukeMTMC-reID 5↔6 | CMC rank-1: 60.3 -> 61.5 | Improved |
| add entropy-based outlier detection for uncertain pseudo-labels (ablation) | CDA · DukeMTMC-reID 7↔8 | CMC rank-1: 38.0 -> 67.2 | Improved |
| use domain-specific dual mappings rather than one shared mapping (ablation) | CDA · DukeMTMC-reID 7↔8 | CMC rank-1: 33.9 -> 67.2 | Improved |
Closest papers by meaning
- Distinguish Then Exploit: Source-free Open Set Domain Adaptation via Weight Barcode Estimation and Sparse Label Assignment (CVPR 2025 · similarity 0.90)
- Open Set Domain Adaptation by Backpropagation (ECCV 2018 · similarity 0.90)
- Open-Set Graph Domain Adaptation via Separate Domain Alignment (AAAI 2024 · similarity 0.88)
- COSDA: Counterfactual-based Susceptibility Risk Framework for Open-Set Domain Adaptation (ICML 2025 · similarity 0.88)
- A Theory of Learning Unified Model via Knowledge Integration from Label Space Varying Domains (CVPR 2025 · 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.
