A3: Active Adversarial Alignment for Source-Free Domain Adaptation
Fuente:
arXiv
Saved in:
| Main Authors: | , |
|---|---|
| Format: | Preprint |
| Published: |
2024
|
| Subjects: | |
| Online Access: | |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866917796459315200 |
|---|---|
| author | Eze, Chrisantus Crick, Christopher |
| author_facet | Eze, Chrisantus Crick, Christopher |
| contents | Unsupervised domain adaptation (UDA) aims to transfer knowledge from a labeled source domain to an unlabeled target domain. Recent works have focused on source-free UDA, where only target data is available. This is challenging as models rely on noisy pseudo-labels and struggle with distribution shifts. We propose Active Adversarial Alignment (A3), a novel framework combining self-supervised learning, adversarial training, and active learning for robust source-free UDA. A3 actively samples informative and diverse data using an acquisition function for training. It adapts models via adversarial losses and consistency regularization, aligning distributions without source data access. A3 advances source-free UDA through its synergistic integration of active and adversarial learning for effective domain alignment and noise reduction. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2409_18418 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | A3: Active Adversarial Alignment for Source-Free Domain Adaptation Eze, Chrisantus Crick, Christopher Machine Learning Artificial Intelligence Computer Vision and Pattern Recognition Unsupervised domain adaptation (UDA) aims to transfer knowledge from a labeled source domain to an unlabeled target domain. Recent works have focused on source-free UDA, where only target data is available. This is challenging as models rely on noisy pseudo-labels and struggle with distribution shifts. We propose Active Adversarial Alignment (A3), a novel framework combining self-supervised learning, adversarial training, and active learning for robust source-free UDA. A3 actively samples informative and diverse data using an acquisition function for training. It adapts models via adversarial losses and consistency regularization, aligning distributions without source data access. A3 advances source-free UDA through its synergistic integration of active and adversarial learning for effective domain alignment and noise reduction. |
| title | A3: Active Adversarial Alignment for Source-Free Domain Adaptation |
| topic | Machine Learning Artificial Intelligence Computer Vision and Pattern Recognition |
| url | https://arxiv.org/abs/2409.18418 |