Research map / Label-efficient and robust learning / Domain adaptation and generalization
Fast Generalized Distillation for Semi-Supervised Domain Adaptation
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 |
|---|---|---|---|
| Use closed-form LOOCV-based imitation parameter estimation instead of brute-force search | GDSDA · Office W->A / D->A single source | accuracy and speed: about 6 times faster | Mixed |
| Use two source models instead of a single source | GDSDA-SVM · Office D+W->A | accuracy | Helped |
| Estimate lambda by LOOCV instead of brute-force best search in multi-source | GDSDA-SVM · Office D+W->A | accuracy: around 30 times faster | Mixed |
| Increase hard-label imitation weight lambda1 from 0 (use target labels in addition to soft labels) (ablation) | GDSDA · Office D->A, W->A | accuracy | Helped |
| Distill from source model with lambda1=0 (no target labels) (ablation) | GDSDA · Office D->A, W->A | accuracy | Helped |
Closest papers by meaning
- Universal Semi-Supervised Domain Adaptation by Mitigating Common-Class Bias (CVPR 2024 · similarity 0.86)
- Understanding and Improving Source-free Domain Adaptation from a Theoretical Perspective (CVPR 2024 · similarity 0.86)
- A Theory of Learning Unified Model via Knowledge Integration from Label Space Varying Domains (CVPR 2025 · similarity 0.85)
- Unlocking the Potential of Unlabeled Data in Semi-Supervised Domain Generalization (CVPR 2025 · similarity 0.85)
- Revisiting Source-Free Domain Adaptation: Insights into Representativeness, Generalization, and Variety (CVPR 2025 · similarity 0.84)
- Gradient-Based Sample Selection for Black-Box Universal Domain Adaptation (AAAI 2025 · similarity 0.84)
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.