Research map / Label-efficient and robust learning / Domain adaptation and generalization
Learning to Transfer Examples for Partial Domain Adaptation
Check 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 ETN's transferability weighting and discriminative weight quantification instead of SAN | ResNet-50 partial domain adaptation · Office-Home (12-task Avg.) | accuracy: 65.30 -> 70.45 | Helped |
| use ETN's transferability weighting and discriminative weight quantification instead of SAN | ResNet-50 partial domain adaptation · Office-31 (6-task Avg.) | accuracy: 94.96±0.36 -> 96.73±0.16 | Helped |
| use ETN's transferability weighting and discriminative weight quantification instead of SAN | ResNet-50 partial domain adaptation · ImageNet-Caltech (2-task Avg.) | accuracy: 76.51±0.39 -> 79.08±0.26 | Helped |
| use ETN instead of PADA | VGG partial domain adaptation · Office-31 (6-task Avg.) | accuracy: 92.54±0.24 -> 96.74±0.13 | Helped |
| add transferability weights to the source classifier (ablation) | ETN · Office-Home (12-task Avg.) | accuracy: 68.93 -> 70.45 | Helped |
| add the auxiliary label predictor to the auxiliary domain discriminator (ablation) | ETN · Office-Home (12-task Avg.) | accuracy: 61.79 -> 70.45 | Helped |
Closest papers by meaning
- Unsupervised Domain Adaptation with Residual Transfer Networks (NeurIPS 2016 · similarity 0.90)
- Blending-Target Domain Adaptation by Adversarial Meta-Adaptation Networks (CVPR 2019 · similarity 0.90)
- Partial Transfer Learning With Selective Adversarial Networks (CVPR 2018 · similarity 0.90)
- Transferable Adversarial Training: A General Approach to Adapting Deep Classifiers (ICML 2019 · similarity 0.90)
- Learning Transferrable Representations for Unsupervised Domain Adaptation (NeurIPS 2016 · similarity 0.89)
- A General Representation-Based Approach to Multi-Source Domain Adaptation (ICML 2025 · similarity 0.88)
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.