SWAT: Sliding Window Adversarial Training for Gradual Domain Adaptation
Fuente:
arXiv
Salvato in:
| Autori principali: | , , , , |
|---|---|
| Natura: | Preprint |
| Pubblicazione: |
2025
|
| Soggetti: | |
| Accesso online: | |
| Tags: |
Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
|
| _version_ | 1866912592075685888 |
|---|---|
| author | Wang, Zixi Zhao, Xiangxu Xie, Tonglan Jing, Mengmeng Zuo, Lin |
| author_facet | Wang, Zixi Zhao, Xiangxu Xie, Tonglan Jing, Mengmeng Zuo, Lin |
| contents | Domain shifts are critical issues that harm the performance of machine learning. Unsupervised Domain Adaptation (UDA) mitigates this issue but suffers when the domain shifts are steep and drastic. Gradual Domain Adaptation (GDA) alleviates this problem in a mild way by gradually adapting from the source to the target domain using multiple intermediate domains. In this paper, we propose Sliding Window Adversarial Training (SWAT) for GDA. SWAT first formulates adversarial streams to connect the feature spaces of the source and target domains. Then, a sliding window paradigm is designed that moves along the adversarial stream to gradually narrow the small gap between adjacent intermediate domains. When the window moves to the end of the stream, i.e., the target domain, the domain shift is explicitly reduced. Extensive experiments on six GDA benchmarks demonstrate the significant effectiveness of SWAT, especially 6.1% improvement on Rotated MNIST and 4.1% advantage on CIFAR-100C over the previous methods. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2501_19155 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | SWAT: Sliding Window Adversarial Training for Gradual Domain Adaptation Wang, Zixi Zhao, Xiangxu Xie, Tonglan Jing, Mengmeng Zuo, Lin Computer Vision and Pattern Recognition Artificial Intelligence Domain shifts are critical issues that harm the performance of machine learning. Unsupervised Domain Adaptation (UDA) mitigates this issue but suffers when the domain shifts are steep and drastic. Gradual Domain Adaptation (GDA) alleviates this problem in a mild way by gradually adapting from the source to the target domain using multiple intermediate domains. In this paper, we propose Sliding Window Adversarial Training (SWAT) for GDA. SWAT first formulates adversarial streams to connect the feature spaces of the source and target domains. Then, a sliding window paradigm is designed that moves along the adversarial stream to gradually narrow the small gap between adjacent intermediate domains. When the window moves to the end of the stream, i.e., the target domain, the domain shift is explicitly reduced. Extensive experiments on six GDA benchmarks demonstrate the significant effectiveness of SWAT, especially 6.1% improvement on Rotated MNIST and 4.1% advantage on CIFAR-100C over the previous methods. |
| title | SWAT: Sliding Window Adversarial Training for Gradual Domain Adaptation |
| topic | Computer Vision and Pattern Recognition Artificial Intelligence |
| url | https://arxiv.org/abs/2501.19155 |