Assessing two novel distance-based loss functions for few-shot image classification

Mauricio Mendez Ruiz, Gilberto Ochoa Ruiz, Andres Mendez Vazquez, Jorge Gonzalez-Zapata

Keywords: Metric learning, few-shot learning, image classification

Abstract: Few-shot learning is a challenging area of research which aims to learn new concepts with only a few labeled samples of data. Recent works based on metric-learning approaches benefit from the meta-learning process in which we have episodic tasks conformed by support set (training) and query set (test), and the objective is to learn a similarity comparison metric between those sets. Due to the lack of data, the learning process of the embedding network becomes an important part of the few-shot task. In this work, we propose two different loss functions which consider the importance of the embedding vectors by looking at the intra-class and inter-class distance between the few data. The first loss function is the Proto-Triplet Loss, which is based on the original triplet loss with the modifications needed to better work on few-shot scenarios. The second loss function is based on an inter and intra class nearest neighbors score, which help us to know the quality of embeddings obtained from the trained network. Extensive experimental results on the miniImagenNet benchmark increase the accuracy performance from other metric-based few-shot learning methods by a margin of $2\%$, demonstrating the capability of these loss functions to allow the network to generalize better to previously unseen classes.