Few-shot类增量学习的基本和新颖表现揭秘

Jun, 2022

Few-shot类增量学习的基本和新颖表现揭秘

Demystifying the Base and Novel Performances for Few-shot Class-incremental Learning

Jaehoon Oh, Se-Young Yun

TL;DR本文研究了 few-shot class-incremental learning (FSCIL) 问题，提出了一种基于规范化原型分类器的简单方法，名为 NoNPC，该方法适用于增量式新类别的识别，具有与先进算法相当的性能表现。

Abstract

Few-shot class-incremental learning (FSCIL) has addressed challenging real-world scenarios where unseen novel classes continually arrive with few samples. In these scenarios, it is required to develop a model tha