Research map / Label-efficient and robust learning / Domain adaptation and generalization
Distant Domain Transfer Learning
Ben Tan, Yu Zhang, Sinno Pan, Qiang Yang
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 |
|---|---|---|---|
| SLA with selected intermediate data instead of supervised CNN | distant domain transfer · Caltech-256 images | average accuracy: 0.78 -> 0.86 | Improved |
| direct deep transfer (DTL) instead of no transfer | CNN · Caltech-256 images | average accuracy: 0.78 -> 0.74 | Hurt |
| self-taught features from all intermediate data (STL) | CNN · Caltech-256 images | average accuracy: 0.78 -> 0.79 | Improved |
| learned SLA ordering instead of random order of intermediate data (ablation) | SLA · Caltech-256 images | average accuracy: 0.62 -> 0.86 | Improved |
| learned SLA ordering instead of category-wise order (ablation) | SLA · Caltech-256 images | average accuracy: 0.81 -> 0.86 | Improved |
| learned SLA ordering instead of random order (ablation) | SLA · AwA SIFT | average accuracy: 0.65 -> 0.81 | Improved |
Closest papers by meaning
- Learning Across Tasks and Domains (ICCV 2019 · similarity 0.85)
- Maximum Structural Generation Discrepancy for Unsupervised Domain Adaptation (TPAMI 2022 · similarity 0.85)
- Factors of Influence for Transfer Learning Across Diverse Appearance Domains and Task Types (TPAMI 2021 · similarity 0.85)
- Domain Invariant Masked Autoencoders for Self-Supervised Learning from Multi-Domains (ECCV 2022 · similarity 0.85)
- Domain Transfer Becomes Identifiable via a Single Alignment (ICML 2026 · similarity 0.85)
- Link-based Contrastive Learning for One-Shot Unsupervised Domain Adaptation (CVPR 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.
