Research map / Label-efficient and robust learning / Domain adaptation and generalization
Partial Transfer Learning With Selective Adversarial 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 |
|---|---|---|---|
| Use selective adversarial adaptation and entropy minimization rather than RTN | AlexNet transfer model · Office-31 partial transfer tasks (average) | accuracy (%): 78.82 -> 87.27 | Helped |
| Use selective adversarial adaptation and entropy minimization rather than RTN | AlexNet transfer model · Caltech-Office partial transfer tasks (average) | accuracy (%): 71.56 -> 85.83 | Helped |
| Use selective adversarial adaptation and entropy minimization rather than RTN | AlexNet transfer model · ImageNet-Caltech partial transfer tasks (average) | accuracy (%): 57.07 -> 62.03 | Helped |
| Add selective adversarial mechanism (ablation) | SAN without selective mechanism (SAN-entropy) · Office-31 partial transfer tasks (average) | accuracy (%): 85.64 -> 87.27 | Helped |
| Add selective adversarial mechanism (ablation) | SAN without selective mechanism (SAN-entropy) · Caltech-Office partial transfer tasks (average) | accuracy (%): 75.97 -> 85.83 | Helped |
| Add selective adversarial mechanism (ablation) | SAN without selective mechanism (SAN-entropy) · ImageNet-Caltech partial transfer tasks (average) | accuracy (%): 53.79 -> 62.03 | Helped |
| Add entropy minimization (ablation) | SAN without entropy minimization (SAN-selective) · Office-31 partial transfer tasks (average) | accuracy (%): 83.73 -> 87.27 | Helped |
| Add entropy minimization (ablation) | SAN without entropy minimization (SAN-selective) · Caltech-Office partial transfer tasks (average) | accuracy (%): 79.44 -> 85.83 | Helped |
| Add entropy minimization (ablation) | SAN without entropy minimization (SAN-selective) · ImageNet-Caltech partial transfer tasks (average) | accuracy (%): 59.02 -> 62.03 | Helped |
Closest papers by meaning
- Learning to Transfer Examples for Partial Domain Adaptation (CVPR 2019 · similarity 0.90)
- Adversarially-Trained Deep Nets Transfer Better: Illustration on Image Classification (ICLR 2021 · similarity 0.89)
- Adversarial Training Helps Transfer Learning via Better Representations (NeurIPS 2021 · similarity 0.88)
- Importance Weighted Adversarial Nets for Partial Domain Adaptation (CVPR 2018 · similarity 0.87)
- Adversarially robust transfer learning (ICLR 2020 · similarity 0.87)
- Adversarial-Learned Loss for Domain Adaptation (AAAI 2020 · 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.