Temperature network for few-shot learning with distribution-aware large-margin metric

作者：

Highlights：

• A simple and general approach is proposed to enhance the prototype-based few-shot learning methods, which can theoretically lead to compact intra-class distributions.

• We propose the Temperature Network which can implicitly generate query-specific prototypes. Moreover, in order to best utilize limited training samples, we further propose to train in a hard mode to exhaustively mine the large-margin metric.

• We conduct comprehensive experiments on several publicly available datasets as well as the proposed Dermnet skin disease dataset to validate the proposed method.

摘要

•A simple and general approach is proposed to enhance the prototype-based few-shot learning methods, which can theoretically lead to compact intra-class distributions.•We propose the Temperature Network which can implicitly generate query-specific prototypes. Moreover, in order to best utilize limited training samples, we further propose to train in a hard mode to exhaustively mine the large-margin metric.•We conduct comprehensive experiments on several publicly available datasets as well as the proposed Dermnet skin disease dataset to validate the proposed method.

论文关键词：Few-shot learning,Metric learning,Skin lesion classification,Temperature function

论文评审过程：Received 6 October 2019, Revised 2 November 2020, Accepted 13 December 2020, Available online 6 January 2021, Version of Record 6 January 2021.

论文官网地址：https://doi.org/10.1016/j.patcog.2020.107797