☆ 4.7 Article

A multi-grained unsupervised domain adaptation approach for semantic segmentation

PATTERN RECOGNITION (2023)

Domain Stylization: A Fast Covariance Matching Framework Towards Domain Adaptation

Aysegul Dundar et al.

Summary: The paper presents a simple yet effective domain adaptation framework that aims to reduce the domain gap between synthetic and real data by matching the covariance of universal feature embeddings. By proposing a conditional covariance matching framework, domains can be aligned more precisely, leading to mutual refinement and achieving state-of-the-art domain adaptation results.

IEEE TRANSACTIONS ON PATTERN ANALYSIS AND MACHINE INTELLIGENCE (2021)

添加到收藏夹

Article Computer Science, Artificial Intelligence

Vicinal and categorical domain adaptation

Hui Tang et al.

Summary: To promote categorical domain adaptation (CatDA), new losses of adversarial training at both domain and category levels are proposed based on a joint category-domain classifier. We introduce the concept of vicinal domains, whose instances are produced by a convex combination of pairs of instances respectively from the two domains. Novel adversarial losses for vicinal domain adaptation (VicDA) based on CatDA are proposed, leading to Vicinal and Categorical Domain Adaptation (ViCatDA).

PATTERN RECOGNITION (2021)

添加到收藏夹

Article Computer Science, Artificial Intelligence