Multi-attention mutual information distributed framework for few-shot learning

作者：

Highlights：

• Mutual learning module based on the multi-attention mechanism.

• Combine few-shot learning and distributed learning.

• Propose the concept of distributed few-shot learning for the first time.

• The method achieves the expected performance on two datasets.

摘要

•Mutual learning module based on the multi-attention mechanism.•Combine few-shot learning and distributed learning.•Propose the concept of distributed few-shot learning for the first time.•The method achieves the expected performance on two datasets.

论文关键词：Few-shot learning,Attention mechanism,Mutual learning,Distributed learning

论文评审过程：Received 3 November 2021, Revised 24 February 2022, Accepted 28 March 2022, Available online 14 April 2022, Version of Record 27 April 2022.

论文官网地址：https://doi.org/10.1016/j.eswa.2022.117062