Recent advances of few-shot learning methods and applications

The rapid development of deep learning provides great convenience for production and life. However, the massive labels required for training models limits further development. Few-shot learning which can obtain a high-performance model by learning few samples in new tasks, providing a solution for many scenarios that lack samples. This paper summarizes few-shot learning algorithms in recent years and proposes a taxonomy. Firstly, we introduce the few-shot learning task and its significance. Secondly, according to different implementation strategies, few-shot learning methods in recent years are divided into five categories, including data augmentation-based methods, metric learning-based methods, parameter optimization-based methods, external memory-based methods, and other approaches. Next, We investigate the application of few-shot learning methods and summarize them from three directions, including computer vision, human-machine language interaction, and robot actions. Finally, we analyze the existing few-shot learning methods by comparing evaluation results on miniImageNet, and summarize the whole paper.

Automated summary

The rapid development of deep learning has greatly facilitated production and life, but the reliance on massive labels for training models hinders further progress. Few-shot learning, which can achieve high-performance models with limited samples, offers a solution for scenarios lacking data. This paper provides an overview of recent few-shot learning algorithms and proposes a taxonomy. The paper discusses the significance of few-shot learning, categorizes methods based on different implementation strategies, explores their applications in computer vision, human-machine language interaction, and robot actions, and analyzes existing approaches based on evaluation results on miniImageNet.