Global and local attentional feature alignment for domain adaptive nuclei detection in histopathology images

作者：

Highlights：

• An adversarial alignment method is proposed for domain adaptive nuclei detection.

• Global and local features are both aligned to alleviate domain shift problem.

• The LocSA module is introduced to refine local features for successful alignment.

摘要

•An adversarial alignment method is proposed for domain adaptive nuclei detection.•Global and local features are both aligned to alleviate domain shift problem.•The LocSA module is introduced to refine local features for successful alignment.

论文关键词：Nuclei detection,Domain adaptation,Histopathology image analysis

论文评审过程：Received 16 September 2021, Revised 8 June 2022, Accepted 27 June 2022, Available online 2 July 2022, Version of Record 3 August 2022.

论文官网地址：https://doi.org/10.1016/j.artmed.2022.102341