A novel forget-update module for few-shot domain generalization

作者：

Highlights：

• First effort to perform domain generalization on few-shot learning scenarios.

• A new method to construct the relationship information for FSL scenarios.

• It extracts a domain-adaptive relationship embedding using forgetting and updating mechanism.

摘要

•First effort to perform domain generalization on few-shot learning scenarios.•A new method to construct the relationship information for FSL scenarios.•It extracts a domain-adaptive relationship embedding using forgetting and updating mechanism.

论文关键词：Few-shot classification,Domain adaptation,Few-shot domain generalization

论文评审过程：Received 13 October 2020, Revised 31 March 2022, Accepted 7 April 2022, Available online 12 April 2022, Version of Record 27 April 2022.

论文官网地址：https://doi.org/10.1016/j.patcog.2022.108704