DPGN论文笔记

Distribution Propagation Graph Network for Few-shot Learning

Abstract：

This paper propose DPGN，which conveys both the distribution-level relations and instance-level relations in each few-shot learning task.

Contributions:

• DPGN is the first to explicitly incorporate distribution propagationin graph network for few-shot learning. The further ablation studies have demonstrated the effectiveness of distribution relations.

• They devise the dual complete graph networkthat combines instance-level and distribution-level relations.

* DPGN achieves a significant improvement of 5% ∼ 12% on average in few-shot classification accuracy. In semi supervised tasks, DPGN outperforms existing graph-based few-shotlearning methods by 7% ∼ 13%.