no code implementations • 21 Jun 2021 • Jianyi Li, Guizhong Liu
Metric learning is a widely used method for few shot learning in which the quality of prototypes plays a key role in the algorithm.
no code implementations • 23 Aug 2020 • Jianyi Li, Guizhong Liu
Most previous few-shot learning algorithms are based on meta-training with fake few-shot tasks as training samples, where large labeled base classes are required.
Ranked #10 on Unsupervised Few-Shot Image Classification on Mini-Imagenet 5-way (1-shot) (using extra training data)