Few-shot learning with unsupervised part discovery and part-aligned similarity

Highlights：

• We propose a novel unsupervised Part Discovery Network, which can learn discriminative and transferable part representations from unlabeled images for few-shot learning.

• We propose Part-Aligned Similarity, which measures image similarities based on discriminative and aligned parts via partweighting and part-alignment mechanisms.

• We conduct extensive experiments on five few-shot learning benchmarks. The experimental results demonstrate that the proposed approach outperforms previous unsupervised methods by a large margin and achieves comparable performance with supervised methods.