Research map / Label-efficient and robust learning / Domain adaptation and generalization
Domain Agnostic Learning with Disentangled Representations
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 DADA instead of MCD | Digit-Five DAL · Digit-Five (DAL, average) | accuracy: 56.4 -> 62.3 | Helped |
| use DADA instead of DANN | Office-Caltech10 with AlexNet · Office-Caltech10 (DAL, average) | accuracy: 88.9 -> 89.8 | Helped |
| use DADA instead of DANN | Office-Caltech10 with ResNet · Office-Caltech10 (DAL, average) | accuracy: 90.6 -> 92.9 | Helped |
| use DADA instead of MCD | DomainNet DAL with ResNet · DomainNet (DAL, average) | accuracy: 20.7 -> 21.5 | Helped |
| add domain disentanglement to class disentanglement (ablation) | DADA · Digit-Five (DAL, average) | accuracy: 54.9 -> 57.5 | Helped |
| add ring loss (ablation) | DADA with class and domain disentanglement · Digit-Five (DAL, average) | accuracy: 57.5 -> 60.4 | Helped |
| add reconstruction loss (ablation) | DADA with class and domain disentanglement and ring loss · Digit-Five (DAL, average) | accuracy: 60.4 -> 62.3 | Helped |
Closest papers by meaning
- A Unified Feature Disentangler for Multi-Domain Image Translation and Manipulation (NeurIPS 2018 · similarity 0.89)
- Towards Principled Disentanglement for Domain Generalization (CVPR 2022 · similarity 0.88)
- Detach and Adapt: Learning Cross-Domain Disentangled Deep Representation (CVPR 2018 · similarity 0.88)
- Discriminative Adversarial Domain Adaptation (AAAI 2020 · similarity 0.87)
- Domain Generalization via Model-Agnostic Learning of Semantic Features (NeurIPS 2019 · similarity 0.86)
- Demystifying Inter-Class Disentanglement (ICLR 2020 · similarity 0.86)
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.