Class-based Core Feature Extraction Network for Few-shot Classification

Xianchao Zhang, Yifei Shuang, Xiaotong Zhang, Han Liu

Abstract: Few-shot classification classifies unlabeled samples into correct classes when only few training samples are available for each class. Current researches focus on extracting better features and learning similarities between support data and query data based on the extracted features. However, the location of the main objects and the background in an image are interfering factors for few-shot classification, as they contain little useful information. In this paper, we propose a class-based core feature extraction network (CCFEN) which highlights common object of images in the same class and reduces the interference of background by using local feature descriptors and core feature extraction network to learn the common object. Experiments on two classical few-shot learning datasets show that our method achieves better results than state-of-the-art few-shot learning methods.