点击次数：
影响因子：11.041
DOI码：10.1109/TIP.2022.3162471
发表刊物：IEEE Transactions on Image Processing (TIP)
关键字：Unsupervised domain adaptationsemantic segmentationcategory divergenceinter-class separationintra-class aggregation
摘要：Unsupervised domain adaptation (UDA) aims to enhance the generalization capability of a certain model from a source domain to a target domain. Present UDA models focus on alleviating the domain shift by minimizing the feature discrepancy between the source domain and the target domain but usually ignore the class confusion problem. In this work, we propose an Inter-class Separation and Intra-class Aggregation (ISIA) mechanism. It encourages the cross-domain representative consistency between the same categories and differentiation among diverse categories. In this way, the features belonging to the same categories are aligned together and the confusable categories are separated. By measuring the align complexity of each category, we design an Adaptive-weighted Instance Matching (AIM) strategy to further optimize the instance-level adaptation. Based on our proposed methods, we also raise a hierarchical unsupervised domain adaptation framework for cross-domain semantic segmentation task. Through performing the image-level, feature-level, category-level and instance-level alignment, our method achieves a stronger generalization performance of the model from the source domain to the target domain. In two typical cross-domain semantic segmentation tasks, i.e., GTA5 -> Cityscapes and SYNTHIA -> Cityscapes, our method achieves the state-of-the-art segmentation accuracy. We also build two crass-domain semantic segmentation datasets based on the publicly available data, i.e., remote sensing building segmentation and road segmentation, for domain adaptive segmentation. Our code, models and datasets are available at https://github.com/HibiscusYB/BAFFT.
论文类型：期刊论文
文献类型：期刊
卷号：2022(31):
页面范围：2878-2892
是否译文：否
发表时间：2022-03-01
收录刊物：SCI
发布期刊链接：https://ieeexplore.ieee.org/document/9745831