Research map / Label-efficient and robust learning / Domain adaptation and generalization
Deep Transfer Learning with Joint Adaptation Networks
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 |
|---|---|---|---|
| align joint distributions across task-specific layers with JMMD instead of using the strongest reported baseline | AlexNet domain adaptation · Office-31 (average) | classification accuracy (%): 74.3 -> 76.0 | Helped |
| adversarially maximize JMMD (ablation) | JAN with AlexNet · Office-31 (average) | classification accuracy (%): 76.0 -> 76.3 | Helped |
| align joint distributions across task-specific layers with JMMD instead of using the strongest reported baseline | ResNet domain adaptation · Office-31 (average) | classification accuracy (%): 82.2 -> 84.3 | Helped |
| adversarially maximize JMMD (ablation) | JAN with ResNet · Office-31 (average) | classification accuracy (%): 84.3 -> 84.6 | Helped |
| align joint distributions across task-specific layers with JMMD instead of using the strongest reported baseline | AlexNet domain adaptation · ImageCLEF-DA (average) | classification accuracy (%): 77.9 -> 79.3 | Helped |
| align joint distributions across task-specific layers with JMMD instead of using the strongest reported baseline | ResNet domain adaptation · ImageCLEF-DA (average) | classification accuracy (%): 83.9 -> 85.8 | Helped |
| vary the JMMD tradeoff parameter λ (ablation) | JAN · Office-31 A → W | classification accuracy | Mixed |
Closest papers by meaning
- Unsupervised Domain Adaptation with Residual Transfer Networks (NeurIPS 2016 · similarity 0.89)
- Residual Parameter Transfer for Deep Domain Adaptation (CVPR 2018 · similarity 0.89)
- Deep Asymmetric Transfer Network for Unbalanced Domain Adaptation (AAAI 2018 · similarity 0.88)
- Interpretations of Domain Adaptations via Layer Variational Analysis (ICLR 2023 · similarity 0.88)
- Transferable Adversarial Training: A General Approach to Adapting Deep Classifiers (ICML 2019 · similarity 0.88)
- Min-Max Statistical Alignment for Transfer Learning (CVPR 2019 · similarity 0.87)
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.