Research map / Label-efficient and robust learning / Domain adaptation and generalization
Domain Conditioned Adaptation Network
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 first task-specific feature correction loss and regularizer (ablation) | DCAN · Office-31 | average accuracy (%): 84.4 -> 89.5 | Helped |
| Add second task-specific feature correction loss and regularizer (ablation) | DCAN · Office-31 | average accuracy (%): 87.8 -> 89.5 | Helped |
| Add first correction regularizer (ablation) | DCAN · Office-31 | average accuracy (%): 87.7 -> 89.5 | Helped |
| Add second correction regularizer (ablation) | DCAN · Office-31 | average accuracy (%): 88.6 -> 89.5 | Helped |
| Add target entropy minimization loss (ablation) | DCAN · Office-31 | average accuracy (%): 88.4 -> 89.5 | Helped |
| Add domain-conditioned channel attention instead of shared convolutional networks (ablation) | DCAN · Office-31 | average accuracy (%): 87.5 -> 89.5 | Helped |
Closest papers by meaning
- Boosting Domain Adaptation by Discovering Latent Domains (CVPR 2018 · similarity 0.90)
- Conditional Adversarial Domain Adaptation (NeurIPS 2018 · similarity 0.90)
- Unsupervised Domain Adaptation with Residual Transfer Networks (NeurIPS 2016 · similarity 0.90)
- Residual Parameter Transfer for Deep Domain Adaptation (CVPR 2018 · similarity 0.89)
- Adversarial Discriminative Domain Adaptation (CVPR 2017 · similarity 0.89)
- Enhancing Domain Adaptation through Prompt Gradient Alignment (NeurIPS 2024 · similarity 0.88)
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.