# Learning Class-level Prototypes for Few-shot Learning

Source: [Learning Class-level Prototypes for Few-shot Learning](<https://www.sota2.com/research/paper/68fa6a951e209131cea29127>)

Collection index: [llms.txt](<https://www.sota2.com/research/llms.txt>)

Data updated: 2025-10-25T23:28:26.804Z

Authors: Minglei Yuan, Wenhai Wang, Tao Wang, Chunhao Cai, Qian Xu, Tong Lu

Published: 2021-08-25T06:33:52.000Z

## Abstract

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.

## Recorded benchmark results

A research result applies to its stated dataset, split, metric and evaluation configuration. Compare like-for-like settings, preserve the metric's unit and direction, and distinguish paper-reported results from independent reproduction. The best result recorded here is not a claim of exhaustive, current global coverage.

## Original sources and implementation

[Original paper](<https://arxiv.org/abs/2108.11072>)

[PDF](<https://arxiv.org/pdf/2108.11072.pdf>)