Research map / Label-efficient and robust learning / Domain adaptation and generalization
Overcoming Concept Shift in Domain-Aware Settings through Consolidated Internal Distributions
Mohammad Rostami, Aram Galstyan
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 |
|---|---|---|---|
| Adapt the source-trained model using a GMM of its internal source distribution and sliced Wasserstein alignment | SMAUI · MNIST→USPS | classification accuracy: 92.2 $\pm$ 0.5 vs. \textbf{96.4}$\pm$ 0.3 | Hurt |
| Adapt the source-trained model using a GMM of its internal source distribution and sliced Wasserstein alignment | SMAUI · USPS→MNIST | classification accuracy: \textbf{98.2} $\pm$ 0.2 vs. 98.0 | Improved |
| Adapt the source-trained model using a GMM of its internal source distribution and sliced Wasserstein alignment | SMAUI · SVHN→MNIST | classification accuracy: 92.6 $\pm$ 1.0 vs. \textbf{97.9}$\pm$ 0.4 | Hurt |
| Adapt the source-trained model using internal-distribution alignment | SMAUI · Office-31 average | classification accuracy: 88.4 vs. \textbf{90.6} | Hurt |
| Adapt the source-trained model using internal-distribution alignment | SMAUI · ImageCLEF-DA average | classification accuracy: \textbf{95.3} vs. 89.7 | Improved |
| Adapt the source-trained model using internal-distribution alignment | SMAUI · Office-Caltech average | classification accuracy: \textbf{94.0} vs. 94.6 | Hurt |
| Adapt the source-trained model using internal-distribution alignment | SMAUI · VisDA-2017 Syn.→Real. | classification accuracy: \textbf{76.9} $\pm$ 0.7 vs. 71.9 | Improved |
| Use high-confidence pseudo-samples when generating the internal-distribution dataset | SMAUI · Sequential model adaptation | target-domain generalization | Mixed |
Closest papers by meaning
- Concept-Based Unsupervised Domain Adaptation (ICML 2025 · similarity 0.87)
- Adapting to Distribution Shift by Visual Domain Prompt Generation (ICLR 2024 · similarity 0.87)
- A General Representation-Based Approach to Multi-Source Domain Adaptation (ICML 2025 · similarity 0.87)
- Category-Aware Active Domain Adaptation (ICML 2024 · similarity 0.86)
- Revisiting the Domain Shift and Sample Uncertainty in Multi-source Active Domain Transfer (CVPR 2024 · similarity 0.85)
- Memory-Assisted Sub-Prototype Mining for Universal Domain Adaptation (ICLR 2024 · similarity 0.85)
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.
