BriefGPT.xyz
May, 2016
零样本学习中预测未见类别的视觉典型
Predicting Visual Exemplars of Unseen Classes for Zero-Shot Learning
HTML
PDF
Soravit Changpinyo, Wei-Lun Chao, Fei Sha
TL;DR
本文提出了一种新的零样本学习模型，利用语义嵌入空间中的聚类结构来对已知对象的类别语义描述和示例进行建模，并通过训练多个基于核的回归器来实现语义表示-范例对的结构约束，从而在包括ImageNet数据集在内的标准基准数据集上显着优于现有的零样本学习方法。
Abstract
Leveraging class semantic descriptions and examples of known objects,
zero-shot learning
makes it possible to train a recognition model for an object class whose examples are not available. In this paper, we propose a novel
→