期刊
2021 IEEE/CVF INTERNATIONAL CONFERENCE ON COMPUTER VISION (ICCV 2021)
卷 -, 期 -, 页码 8968-8979出版社
IEEE
DOI: 10.1109/ICCV48922.2021.00886
关键词
-
资金
- RIE2020 Industry Alignment Fund - Industry Collaboration Projects (IAF-ICP) Funding Initiative
- Singapore Telecommunications Limited (Singtel), through Singtel Cognitive and Artificial Intelligence Lab for Enterprises (SCALE@NTU)
This paper introduces a robust domain adaptation technique RDA, which mitigates overfitting in unsupervised domain adaptation through adversarial attacking. By using Fourier adversarial attacking method to generate adversarial samples, training can become more robust and achieve superior performance across multiple computer vision tasks.
Unsupervised domain adaptation (UDA) involves a supervised loss in a labeled source domain and an unsupervised loss in an unlabeled target domain, which often faces more severe overfitting (than classical supervised learning) as the supervised source loss has clear domain gap and the unsupervised target loss is often noisy due to the lack of annotations. This paper presents RDA, a robust domain adaptation technique that introduces adversarial attacking to mitigate overfitting in UDA. We achieve robust domain adaptation by a novel Fourier adversarial attacking (FAA) method that allows large magnitude of perturbation noises but has minimal modification of image semantics, the former is critical to the effectiveness of its generated adversarial samples due to the existence of 'domain gaps'. Specifically, FAA decomposes images into multiple frequency components (FCs) and generates adversarial samples by just perturbating certain FCs that capture little semantic information. With FAA-generated samples, the training can continue the 'random walk' and drift into an area with a flat loss landscape, leading to more robust domain adaptation. Extensive experiments over multiple domain adaptation tasks show that RDA can work with different computer vision tasks with superior performance.
作者
我是这篇论文的作者
点击您的名字以认领此论文并将其添加到您的个人资料中。
推荐
暂无数据