Scheduled sampling for one-shot learning via matching network

Highlights：

• A scheduled sampling strategy is introduced to adjust the training procedure of matching network, which accomplishes to learn the ability for one-shot prediction from easy to difficult.

• We propose a novel metric to measure the difficulty of training samples, which jointly considers the diversity and similarity among the labels’ semantic. Samples with high-difficulty values are more difficult to learn for the matching network.

• We conduct extensive experiments on datasets mini-Imagenet, Birds, and Flowers to illustrate the effectiveness and superiority of the proposed method. The experimental results demonstrate that our method consistently outperforms other competitors.