Certainty and Uncertainty Guided Active Domain Adaptation
Fuente:
arXiv
Saved in:
| Main Authors: | , , |
|---|---|
| Format: | Preprint |
| Published: |
2025
|
| Subjects: | |
| Online Access: | |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866918034666422272 |
|---|---|
| author | Safaei, Bardia VS, Vibashan Patel, Vishal M. |
| author_facet | Safaei, Bardia VS, Vibashan Patel, Vishal M. |
| contents | Active Domain Adaptation (ADA) adapts models to target domains by selectively labeling a few target samples. Existing ADA methods prioritize uncertain samples but overlook confident ones, which often match ground-truth. We find that incorporating confident predictions into the labeled set before active sampling reduces the search space and improves adaptation. To address this, we propose a collaborative framework that labels uncertain samples while treating highly confident predictions as ground truth. Our method combines Gaussian Process-based Active Sampling (GPAS) for identifying uncertain samples and Pseudo-Label-based Certain Sampling (PLCS) for confident ones, progressively enhancing adaptation. PLCS refines the search space, and GPAS reduces the domain gap, boosting the proportion of confident samples. Extensive experiments on Office-Home and DomainNet show that our approach outperforms state-of-the-art ADA methods. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2505_19421 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | Certainty and Uncertainty Guided Active Domain Adaptation Safaei, Bardia VS, Vibashan Patel, Vishal M. Computer Vision and Pattern Recognition Active Domain Adaptation (ADA) adapts models to target domains by selectively labeling a few target samples. Existing ADA methods prioritize uncertain samples but overlook confident ones, which often match ground-truth. We find that incorporating confident predictions into the labeled set before active sampling reduces the search space and improves adaptation. To address this, we propose a collaborative framework that labels uncertain samples while treating highly confident predictions as ground truth. Our method combines Gaussian Process-based Active Sampling (GPAS) for identifying uncertain samples and Pseudo-Label-based Certain Sampling (PLCS) for confident ones, progressively enhancing adaptation. PLCS refines the search space, and GPAS reduces the domain gap, boosting the proportion of confident samples. Extensive experiments on Office-Home and DomainNet show that our approach outperforms state-of-the-art ADA methods. |
| title | Certainty and Uncertainty Guided Active Domain Adaptation |
| topic | Computer Vision and Pattern Recognition |
| url | https://arxiv.org/abs/2505.19421 |