Research map / Label-efficient and robust learning / Domain adaptation and generalization
Multi-Adversarial 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 class-wise domain discriminators weighted by classifier probabilities instead of a single domain discriminator | domain-adversarial adaptation · Office-31 | accuracy: 74.1 -> 77.1 | Helped |
| use class-wise domain discriminators weighted by classifier probabilities instead of a single domain discriminator | domain-adversarial adaptation · ImageCLEF-DA | accuracy: 85.0 -> 85.8 | Helped |
| use class-wise domain discriminators weighted by classifier probabilities instead of a single domain discriminator | domain-adversarial adaptation · Office-31 with 31 source classes and 25 target classes | accuracy: 66.6 -> 73.7 | Helped |
| share all parameters across domain discriminators (ablation) | MADA · Office-31 A→W and A→D | accuracy | Hurt |
| share only the lowest layers across domain discriminators (ablation) | MADA · Office-31 A→W and A→D | accuracy | Hurt |
Closest papers by meaning
- Adversarial Multiple Source Domain Adaptation (NeurIPS 2018 · similarity 0.92)
- Adversarial Discriminative Domain Adaptation (CVPR 2017 · similarity 0.91)
- f-Domain Adversarial Learning: Theory and Algorithms (ICML 2021 · similarity 0.90)
- Conditional Adversarial Domain Adaptation (NeurIPS 2018 · similarity 0.90)
- Transferable Adversarial Training: A General Approach to Adapting Deep Classifiers (ICML 2019 · similarity 0.90)
- Discriminative Adversarial Domain Adaptation (AAAI 2020 · 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.