Research map / Label-efficient and robust learning / Domain adaptation and generalization
Heuristic 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 HDAN instead of CADA | ResNet50-based Office-Home UDA · Office-Home UDA (Avg) | accuracy (%): 70.2 -> 70.9; 0.9% | Helped |
| Use HDAN instead of GVBG | ResNet101-based DomainNet MSDA · DomainNet MSDA (Avg) | accuracy (%): 46.0 -> 47.6 | Helped |
| Use HDAN instead of CANN | ResNet34-based DomainNet SSDA · DomainNet SSDA (Avg, 1-shot) | accuracy (%): {68.5} -> 69.5 | Helped |
| Use HDAN instead of CANN | ResNet34-based DomainNet SSDA · DomainNet SSDA (Avg, 3-shot) | accuracy (%): {{71.2}} -> 71.3 | Helped |
| Increase heuristic subnetworks from one to three (ablation) | HDAN · Office-Home UDA | accuracy (%): 70.5 -> 70.9 | Helped |
| Increase heuristic subnetworks from three to five (ablation) | HDAN · Office-Home UDA | accuracy (%): 70.9 -> 70.6 | Hurt |
| Add the heuristic range constraint (ablation) | HDAN · Office-Home UDA | accuracy (%): 67.4 -> 70.9 | Helped |
| Add heuristic similarity initialization (ablation) | HDAN · Office-Home UDA | accuracy (%): 70.3 -> 70.9 | Helped |
| Replace L2-norm with L1-norm (ablation) | HDAN · Office-Home UDA | accuracy (%): 70.5 -> 70.9 | Helped |
Closest papers by meaning
- Domain Adaptation with Invariant Representation Learning: What Transformations to Learn? (NeurIPS 2021 · similarity 0.91)
- Learning an Invariant Hilbert Space for Domain Adaptation (CVPR 2017 · similarity 0.90)
- A General Representation-Based Approach to Multi-Source Domain Adaptation (ICML 2025 · similarity 0.90)
- Adapting to Distribution Shift by Visual Domain Prompt Generation (ICLR 2024 · similarity 0.88)
- Enhancing Domain Adaptation through Prompt Gradient Alignment (NeurIPS 2024 · similarity 0.87)
- Open-Set Heterogeneous Domain Adaptation: Theoretical Analysis and Algorithm (AAAI 2025 · similarity 0.87)
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.