Research map / Label-efficient and robust learning / Domain adaptation and generalization
Taxonomy-Structured 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 a domain taxonomist alongside adversarial domain discrimination | TSDA · DT-14 | accuracy: 68.8 -> 100.0 | Helped |
| use a domain taxonomist alongside adversarial domain discrimination | TSDA · DT-40 | accuracy: 55.4 -> 82.6 | Helped |
| use a domain taxonomist alongside adversarial domain discrimination | TSDA · ImageNet-Attribute-DT | accuracy: 78.7 -> 80.7 | Helped |
| use a domain taxonomist alongside adversarial domain discrimination | TSDA · CUB-DT | accuracy: 75.9 -> 82.4 | Helped |
| add the discriminator (ablation) | TSDA · DT-14 | accuracy: 34.5 -> 100.0 | Helped |
| add the taxonomist (ablation) | TSDA · DT-14 | accuracy: 68.8 -> 100.0 | Helped |
| add the discriminator (ablation) | TSDA · DT-40 | accuracy: 42.7 -> 82.6 | Helped |
| add the taxonomist (ablation) | TSDA · DT-40 | accuracy: 55.4 -> 82.6 | Helped |
| add the discriminator (ablation) | TSDA · ImageNet-Attribute-DT | accuracy: 62.0 -> 80.7 | Helped |
| add the taxonomist (ablation) | TSDA · ImageNet-Attribute-DT | accuracy: 75.3 -> 80.7 | Helped |
| add the discriminator (ablation) | TSDA · CUB-DT | accuracy: 80.6 -> 82.4 | Helped |
| add the taxonomist (ablation) | TSDA · CUB-DT | accuracy: 66.9 -> 82.4 | Helped |
Closest papers by meaning
- Domain Adaptation with Asymmetrically-Relaxed Distribution Alignment (ICML 2019 · similarity 0.87)
- GANTEE: Generative Adversarial Network for Taxonomy Enterance Evaluation (AAAI 2023 · similarity 0.86)
- Bridging Theory and Algorithm for Domain Adaptation (ICML 2019 · similarity 0.86)
- Graph-Relational Domain Adaptation (ICLR 2022 · similarity 0.86)
- Category-Aware Active Domain Adaptation (ICML 2024 · similarity 0.85)
- Gradient-Based Sample Selection for Black-Box Universal Domain Adaptation (AAAI 2025 · similarity 0.85)
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.