Learning Class-level Prototypes for Few-shot Learning
This work addresses the challenge of outlier sensitivity in few-shot learning for computer vision applications, representing an incremental improvement over existing methods.
The paper tackles the problem of few-shot learning by proposing a framework that learns to generate class-level prototypes less influenced by outlier samples, achieving competitive results on datasets like miniImageNet and cross-domain tasks.
Few-shot learning aims to recognize new categories using very few labeled samples. Although few-shot learning has witnessed promising development in recent years, most existing methods adopt an average operation to calculate prototypes, thus limited by the outlier samples. In this work, we propose a simple yet effective framework for few-shot classification, which can learn to generate preferable prototypes from few support data, with the help of an episodic prototype generator module. The generated prototype is meant to be close to a certain \textit{\targetproto{}} and is less influenced by outlier samples. Extensive experiments demonstrate the effectiveness of this module, and our approach gets a significant raise over baseline models, and get a competitive result compared to previous methods on \textit{mini}ImageNet, \textit{tiered}ImageNet, and cross-domain (\textit{mini}ImageNet $\rightarrow$ CUB-200-2011) datasets.