Prototype Relationship Optimization Network for Few‐Shot Learning

Abstract Few‐shot learning (FSL) aims to infer labels for new samples based on a few labeled samples. FSL based on prototype metrics emphasizes the distance between unlabeled sample features and prototypes generated from a few labeled samples. However, due to the limited number of samples and the uncertainty of samples, the discrepancy between prototypes and the center of the real features may lead to metric error. This paper proposes the Prototype Relationship Optimization Network (PRON) to alleviate the prototype bias issue by utilizing prototype relationship optimization. The PRON involves three fundamental processes: (i) Constructing a multi‐layer prototype through multi‐layer feature embedding to enhance prototype representation capabilities; (ii) Utilizing prototype relationship interaction network of multi‐layer prototype forms multi‐layer prototype relationships to weaken the influence of uncertainty and strengthen the discrimination; (iii) Introduces a prototype refinement mechanism in the cascade structure to optimize prototype relationship representation. The inductive standard experimental results on three popular benchmark datasets show that the performance of the proposed method is very competitive and comparable to the state‐of‐the‐art FSL methods. © 2024 Institute of Electrical Engineers of Japan and Wiley Periodicals LLC.