Journal of Computer Applications ›› 2021, Vol. 41 ›› Issue (11): 3127-3131.DOI: 10.11772/j.issn.1001-9081.2021010061

• Artificial intelligence • Previous Articles     Next Articles

Open set fuzzy domain adaptation algorithm via progressive separation

Xiaolong LIU1(), Shitong WANG2   

  1. 1.School of Artificial Intelligence and Computer Science,Jiangnan University,Wuxi Jiangsu 214122,China
    2.Jiangsu Key Laboratory of Media Design and Software Technology (Jiangnan University),Wuxi Jiangsu 214122,China
  • Received:2021-01-13 Revised:2021-03-25 Accepted:2021-03-30 Online:2021-04-15 Published:2021-11-10
  • Contact: Xiaolong LIU
  • About author:LIU Xiaolong, born in 1995, M. S. candidate. His research interests include artificial intelligence, pattern recognition, machine learning.
    WANG Shitong,born in 1964,Ph. D.,professor. His research interests include artificial intelligence,pattern recognition,fuzzy system.
  • Supported by:
    the National Natural Science Foundation of China(61572236)

渐进式分离的开放集模糊域自适应算法

刘晓龙1(), 王士同2   

  1. 1.江南大学 人工智能与计算机学院,江苏 无锡 214122
    2.江苏省媒体设计与软件技术重点实验室(江南大学),江苏 无锡 214122
  • 通讯作者: 刘晓龙
  • 作者简介:刘晓龙(1995—),男,山东潍坊人,硕士研究生,主要研究方向:人工智能、模式识别、机器学习
    王士同(1964—),男,江苏扬州人,教授,博士生导师,博士,CCF会员,主要研究方向:人工智能、模式识别、模糊系统。
  • 基金资助:
    国家自然科学基金资助项目(61572236)

Abstract:

The aim of domain adaptation is to use the knowledge in a labeled (source) domain to improve the model classification performance of an unlabeled (target) domain, and this method has achieved good results. However, in the open realistic scenes, the target domain usually contains unknown classes that are not observed in the source domain, which is called open set domain adaptation problem. For such challenging scene setting, the traditional domain adaptation algorithm is powerless. Therefore, an open set fuzzy domain adaptation algorithm via progressive separation was proposed. Firstly, based on the open set fuzzy domain adaptation algorithm with membership degree introduced, the method of separating the known and unknown class samples in the target domain step by step was explored. Then, only known classes separated from the target domain were aligned with the source domain, so as to reduce the distribution difference between the two domains and perform the fuzzy adaptation. The negative transfer effect caused by the mismatch between unknown and known classes was reduced well by the proposed algorithm. Six domain transformation experimental results on Office dataset show that, the accuracy of the proposed algorithm has the significant improvement in image classification compared with the traditional domain adaptation algorithm, and verify that the proposed algorithm can gradually enhance the accuracy and robustness of the domain adaptation classification model.

Key words: machine learning, open set, fuzzy domain adaptation, progressive separation, transfer learning

摘要:

域自适应的目的是利用有标记(源)域中的信息来提高未标记(目标)域模型的分类性能,且这种方法已经取得了不错的成果。然而在具有开放性的现实场景下,目标域通常包含源域中未观察到的未知类样本,这被称为开放集域自适应问题。传统的域自适应算法对这样具有挑战性的场景设定无能为力,因此提出了渐进式分离的开放集模糊域自适应算法。首先,基于引进隶属度的开放集模糊域自适应算法,探索了逐步分离目标域中已知类和未知类样本的方法;然后,仅将从目标域中分离出的已知类与源域对齐,从而减小两个域之间的分布差异,进行模糊域自适应。所提算法很好地解决了由于未知类和已知类之间的不匹配而导致的负迁移所带来的影响。在Office数据集上的6组域自适应转化实验结果表明,与传统的域自适应算法比较,所提算法在图像分类中的精度有显著的提升,验证了该算法可以逐步增强域自适应分类模型的准确性和鲁棒性。

关键词: 机器学习, 开放集, 模糊域自适应, 渐进式分离, 迁移学习

CLC Number: