Deep knowledge integration of heterogeneous features for domain adaptive SAR target recognition
作者：
Highlights：
• Deep knowledge integration at the feature and the decision levels based on heterogeneous features.
• Design the feature weights to weigh the importance of different types of features.
• Update feature weights online without re-visiting the previous information by using few labeled target domain samples to achieve domain adaptation.
摘要
•Deep knowledge integration at the feature and the decision levels based on heterogeneous features.•Design the feature weights to weigh the importance of different types of features.•Update feature weights online without re-visiting the previous information by using few labeled target domain samples to achieve domain adaptation.
论文关键词：Heterogeneous features,Knowledge integration,Domain adaptation,Online learning,Synthetic aperture radar
论文评审过程：Received 5 November 2021, Revised 18 January 2022, Accepted 12 February 2022, Available online 14 February 2022, Version of Record 3 March 2022.
论文官网地址：https://doi.org/10.1016/j.patcog.2022.108590
