Research map / Label-efficient and robust learning / Domain adaptation and generalization
Mapping conditional distributions for domain adaptation under generalized target shift
Read the paperCheck 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 |
|---|---|---|---|
| Add Information Maximization (IM) to OSTAR | OSTAR · Digits subsampled | balanced accuracy: 88.39 \pm 1.5 -> 96.69 \pm 0.7 | Helped |
| Add Information Maximization (IM) to OSTAR | OSTAR · VisDA12 subsampled | balanced accuracy: 49.05 \pm 0.9 -> 58.84 \pm 1.0 | Helped |
| Add Information Maximization (IM) to OSTAR | OSTAR · Office31 subsampled | balanced accuracy: 76.19 \pm 0.8 -> 82.61 \pm 0.4 | Helped |
| Add Information Maximization (IM) to OSTAR | OSTAR · OfficeHome subsampled | balanced accuracy: 54.64 \pm 0.7 -> 59.51 \pm 0.4 | Helped |
| Add IM to OSTAR (ablation) | OSTAR · MNIST→USPS balanced | balanced accuracy: 95.12 \pm 0.6 -> 96.91 \pm 0.3 | Helped |
| Add IM classifier refinement and representation updates (ablation) | OSTAR+IM classifier-only · MNIST→USPS balanced | balanced accuracy: 96.68 \pm 0.1 -> 96.91 \pm 0.3 | Helped |
| Add OT transport-cost regularization (λOT=10⁻²) (ablation) | OSTAR · MNIST→USPS high shift | balanced accuracy: 85.24 \pm 1.6 -> 88.55 \pm 1.1 | Helped |
| Add OT transport-cost regularization (λOT=10⁻²) (ablation) | OSTAR · MNIST→USPS mild shift | balanced accuracy: 88.28 \pm 1.5 -> 91.77 \pm 1.2 | Helped |
| Add OT transport-cost regularization (λOT=10⁻²) (ablation) | OSTAR · MNIST→USPS balanced shift | balanced accuracy: 94.92 \pm 0.6 -> 95.12 \pm 0.6 | No clear effect |
| Apply IM across the baseline and OSTAR models (ablation) | MARSc, IW-WD, and OSTAR · Digits | balanced accuracy | Mixed |
Closest papers by meaning
- Theoretical Performance Guarantees for Partial Domain Adaptation via Partial Optimal Transport (ICML 2025 · similarity 0.91)
- A General Representation-Based Approach to Multi-Source Domain Adaptation (ICML 2025 · similarity 0.90)
- Revisiting Source-Free Domain Adaptation: Insights into Representativeness, Generalization, and Variety (CVPR 2025 · similarity 0.89)
- Pseudo-Labeling for Unsupervised Domain Adaptation with Kernel GLMs (NeurIPS 2026 · similarity 0.89)
- Diffusion-Driven Progressive Target Manipulation for Source-Free Domain Adaptation (NeurIPS 2025 · similarity 0.89)
- Robust Domain Generalization under Divergent Marginal and Conditional Distributions (NeurIPS 2026 · similarity 0.89)
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.