BriefGPT.xyz
Jun, 2024
预定义原型的类内分离与解缠
Predefined Prototypes for Intra-Class Separation and Disentanglement
HTML
PDF
Antonio Almudévar, Théo Mariotte, Alfonso Ortega, Marie Tahon, Luis Vicente...
TL;DR
该研究论文提出了一种基于人工指定标准预定义原型的原型学习方法，其可以增加类别之间的嵌入可分性并解耦嵌入的不同方差因素，从而实现可解释的预测。通过提供实验证明了该方法的优势。
Abstract
prototypical learning
is based on the idea that there is a point (which we call prototype) around which the embeddings of a class are clustered. It has shown promising results in scenarios with little
labeled data
→