-
Memory-Augmented Relation Network for Few-Shot Learning
The proposed method Memory-Augmented Relation Network (MRN) for few-shot learning. -
MiniImagenet
The MiniImagenet dataset is a benchmark for few-shot learning, consisting of 60,000 images from 21 classes, each with 300 images. -
ScanObjectNN
Zero-shot learning (ZSL) aims to classify objects that are not observed or seen during training. It relies on class semantic description to transfer knowledge from the seen...