Research map / Label-efficient and robust learning / Domain adaptation and generalization
Re-Weighted Adversarial Adaptation Network for Unsupervised 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 RAAN with OT-based EM-distance adversarial adaptation instead of ADDA | UDA model · SVHN to MNIST | recognition rate: 0.760 -> 0.807 | Helped |
| add label-distribution reweighting (ablation) | RAAN · SVHN to MNIST | recognition rate: 0.807 -> 0.892 | Helped |
| add label-distribution reweighting (ablation) | RAAN · MNIST to USPS | recognition rate: 0.883 -> 0.89 | Helped |
| add label-distribution reweighting (ablation) | RAAN · USPS to MNIST | recognition rate: 0.915 -> 0.921 | Helped |
| add label-distribution reweighting (ablation) | RAAN · MNIST to MNIST-M | recognition rate | No clear effect |
| use RAAN with OT-based EM-distance adversarial adaptation instead of ADDA | UDA model · NYU-D RGB to HHA | overall recognition rate: 0.276 -> 0.308 | Helped |
| add label-distribution reweighting (ablation) | RAAN · NYU-D RGB to HHA | overall recognition rate: 0.308 -> 0.343 | Helped |
| use RAAN instead of ADDA | UDA model · SVHN to MNIST | A-Distance: 1.548 -> 1.526 | Helped |
| add label-distribution reweighting (ablation) | RAAN · SVHN to MNIST | A-Distance: 1.526 -> 1.506 | Helped |
Closest papers by meaning
- Can We Evaluate Domain Adaptation Models Without Target-Domain Labels? (ICLR 2024 · similarity 0.91)
- Reusing the Task-Specific Classifier as a Discriminator: Discriminator-Free Adversarial Domain Adaptation (CVPR 2022 · similarity 0.91)
- Adversarial Reweighting for Partial Domain Adaptation (NeurIPS 2021 · similarity 0.91)
- Cross-Domain Gradient Discrepancy Minimization for Unsupervised Domain Adaptation (CVPR 2021 · similarity 0.90)
- Importance Weighted Adversarial Nets for Partial Domain Adaptation (CVPR 2018 · similarity 0.90)
- Adversarial Discriminative Domain Adaptation (CVPR 2017 · 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.