Research map / Label-efficient and robust learning / Domain adaptation and generalization
Structure Preserving Generative Cross-Domain Learning
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 GSP with cross-domain graph alignment and a source-supervised target classifier instead of SymNets | UDA with ResNet-50 · Office-31 | Top-1 Accuracy (%): 88.4 -> 89.5 | Helped |
| Use GSP with cross-domain graph alignment and a source-supervised target classifier instead of SymNets | UDA with ResNet-50 · Office-Home | Top-1 Accuracy (%): 67.6 -> 68.4 | Helped |
| Use GSP with cross-domain graph alignment and a source-supervised target classifier instead of the strongest listed baseline | UDA with ResNet-50 · ImageCLEF-DA | Top-1 Accuracy (%): 80.2 -> 79.4; 96.4 -> 97.2 | Mixed |
Closest papers by meaning
- Bi-Directional Generation for Unsupervised Domain Adaptation (AAAI 2020 · similarity 0.89)
- CDTrans: Cross-domain Transformer for Unsupervised Domain Adaptation (ICLR 2022 · similarity 0.89)
- Aligning Domain-Specific Distribution and Classifier for Cross-Domain Classification from Multiple Sources (AAAI 2019 · similarity 0.88)
- Cross-Domain Gradient Discrepancy Minimization for Unsupervised Domain Adaptation (CVPR 2021 · similarity 0.88)
- Can We Evaluate Domain Adaptation Models Without Target-Domain Labels? (ICLR 2024 · similarity 0.88)
- SimProF: A Simple Probabilistic Framework for Unsupervised Domain Adaptation (AAAI 2025 · similarity 0.87)
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.