Edge-Labeling based Directed Gated Graph Network for Few-shot Learning

1 code implementation • 27 Jan 2021 • Peixiao Zheng, Xin Guo, Lin Qi

In this paper, we proposed an edge-labeling-based directed gated graph network (DGGN) for few-shot learning, which utilizes gated recurrent units to implicitly update the similarity between nodes.

Few-Shot Learning