Research map / Label-efficient and robust learning / Domain adaptation and generalization
Unified Deep Supervised Domain Adaptation and Generalization
Saeid Motiian, Marco Piccirilli, Donald A. Adjeroh, Gianfranco Doretto
Read the paperCheck 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 one labeled target sample per class (CCSAA-1) to the base model (ablation) | CCSAA · Office (average) | accuracy (%): 72.4 -> 81.6 | Improved |
| increase labeled target samples per class from 1 to 2 (ablation) | CCSAA · Office (average) | accuracy (%): 81.6 -> 84.4 | Improved |
| increase labeled target samples per class from 2 to 3 (ablation) | CCSAA · Office (average) | accuracy (%): 84.4 -> 86.1 | Improved |
| add 1 labeled target sample per class (ablation) | CCSAA · Office Amazon->DSLR | accuracy (%): 64.3 -> 80.5 | Improved |
| add 1 labeled target sample per class (ablation) | CCSAA · Office Webcam->DSLR | accuracy (%): 94.7 -> 97.6 | Improved |
| increase to 3 labeled target samples per class on Webcam->DSLR (ablation) | CCSAA · Office Webcam->DSLR | accuracy (%): 97.7 -> 98.0 | No clear effect |
Closest papers by meaning
- Unsupervised Domain Adaptation in the Wild via Disentangling Representation Learning (IJCV 2020 · similarity 0.90)
- Cross-Domain Gated Learning for Domain Generalization (IJCV 2022 · similarity 0.89)
- Delving into Pre-training for Domain Transfer: A Broad Study of Pre-training for Domain Generalization and Domain Adaptation (IJCV 2026 · similarity 0.88)
- Generalized Domain Adaptation (CVPR 2021 · similarity 0.87)
- AdaDCP: Learning an Adapter with Discrete Cosine Prior for Clear-to-Adverse Domain Generalization (ICCV 2025 · similarity 0.87)
- A General Representation-Based Approach to Multi-Source Domain Adaptation (ICML 2025 · similarity 0.86)
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.
