Research map / Label-efficient and robust learning / Domain adaptation and generalization
Domain-Symmetric Networks for Adversarial Domain Adaptation
Check 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 Domain-Symmetric Networks with two-level domain confusion | ResNet-50 · Office-31 | accuracy: 87.7 -> 88.4 | Helped |
| Use Domain-Symmetric Networks with two-level domain confusion | ResNet-50 · ImageCLEF-DA | accuracy: 87.7 -> 89.9 | Helped |
| Use Domain-Symmetric Networks with two-level domain confusion | ResNet-50 · Office-Home | accuracy: 65.8 -> 67.6 | Helped |
| Add cross-domain category supervision for the target classifier (ablation) | SymNets · Office-31 | accuracy: 78.1 -> 88.4 | Helped |
| Add entropy minimization (ablation) | SymNets · Office-31 | accuracy: 85.7 -> 88.4 | Helped |
| Add domain-level confusion and category-level confusion (ablation) | SymNets · Office-31 | accuracy: 86.9 -> 88.4 | Helped |
| Use category-level confusion instead of domain-level confusion for source samples (ablation) | SymNets · Office-31 | accuracy: 87.8 -> 88.4 | Helped |
Closest papers by meaning
- Adversarial Discriminative Domain Adaptation (CVPR 2017 · similarity 0.91)
- A DIRT-T Approach to Unsupervised Domain Adaptation (ICLR 2018 · similarity 0.90)
- Reusing the Task-Specific Classifier as a Discriminator: Discriminator-Free Adversarial Domain Adaptation (CVPR 2022 · similarity 0.90)
- Maximum Classifier Discrepancy for Unsupervised Domain Adaptation (CVPR 2018 · similarity 0.90)
- Discriminative Adversarial Domain Adaptation (AAAI 2020 · similarity 0.90)
- Unsupervised Domain Adaptation with Residual Transfer Networks (NeurIPS 2016 · similarity 0.90)
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.