arXivDaily arXiv每日学术速递 周一至周五更新
arXiv周末暂无论文更新,休息一下吧,周末愉快~~
arXiv 2005.07858cs.CV
收藏

基于图卷积网络的部分领域自适应

Partial Domain Adaptation Using Graph Convolutional Networks

Korea Advanced Institute of Science and Technology (KAIST)(韩国科学技术院)

Seunghan Yang, Youngeun Kim, Dongki Jung, Changick Kim

摘要:

部分领域自适应(PDA)是标准领域自适应的一种通用形式,它假设目标标签空间包含在源标签空间中。由于目标标签空间是未知的,PDA的主要挑战是减少不属于目标标签空间的不相关源样本(称为离群值)的学习影响。现有的部分领域自适应方法虽然有效地降低了离群点的重要性,但它们没有考虑每个领域的数据结构,也没有直接对齐源域和目标域中同一类的特征分布,这可能导致类别级分布的不对齐。为了克服这些问题,我们提出了一个图部分领域自适应(GPDA)网络,它利用图卷积网络共同考虑数据结构和每个类的特征分布。具体来说,我们提出了一个标签关系图对齐的分布相同的类别在两个领域,并引入移动平均质心分离的学习网络从标签关系图。我们证明,考虑数据结构和每个类别的分布是有效的PDA和我们的GPDA网络上的Digit和Office-31数据集达到最先进的性能。

英文摘要:

Partial domain adaptation (PDA), in which we assume the target label space is included in the source label space, is a general version of standard domain adaptation. Since the target label space is unknown, the main challenge of PDA is to reduce the learning impact of irrelevant source samples, named outliers, which do not belong to the target label space. Although existing partial domain adaptation methods effectively down-weigh outliers' importance, they do not consider data structure of each domain and do not directly align the feature distributions of the same class in the source and target domains, which may lead to misalignment of category-level distributions. To overcome these problems, we propose a graph partial domain adaptation (GPDA) network, which exploits Graph Convolutional Networks for jointly considering data structure and the feature distribution of each class. Specifically, we propose a label relational graph to align the distributions of the same category in two domains and introduce moving average centroid separation for learning networks from the label relational graph. We demonstrate that considering data structure and the distribution of each category is effective for PDA and our GPDA network achieves state-of-the-art performance on the Digit and Office-31 datasets.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑