Compositional Embeddings for Multi-Label One-Shot Learning
Compositional Embeddings for Multi-Label One-Shot Learning
复制标题
DOI：
10.1109/wacv48630.2021.00034
复制
发表时间：
2020-02
期刊：
影响因子：
--
通讯作者：
Zeqian Li;M. Mozer;J. Whitehill
中科院分区：
文献类型：
--
作者：
Zeqian Li;M. Mozer;J. Whitehill
我们提出了一个组合嵌入框架，在一次性学习的设置中，该框架不仅可以推断每个输入图像的单个类，而且可以推断一组类。具体来说，我们提出并评估了几种新的模型，包括（1）一个嵌入函数f与一个“组合”函数g联合训练，该函数计算两个嵌入向量中编码的类之间的集合并集运算;以及（2）嵌入f与一个“查询”函数h联合训练，该函数计算一个嵌入中编码的类是否继承了另一个嵌入中编码的类。与以前的工作相比，这些模型必须感知与输入示例相关联的类，并对不同类标签集之间的关系进行编码，并且仅使用由训练示例之间的标签集关系组成的弱一次性监督来训练它们。在OmniGlot、Open Images和COCO数据集上的实验表明，本文提出的组合嵌入模型优于现有的嵌入方法。我们的组合嵌入模型可以应用于单次学习和监督学习的多标签对象识别。
We present a compositional embedding framework that infers not just a single class per input image, but a set of classes, in the setting of one-shot learning. Specifically, we propose and evaluate several novel models consisting of (1) an embedding function f trained jointly with a "composition" function g that computes set union operations between the classes encoded in two embedding vectors; and (2) embedding f trained jointly with a "query" function h that computes whether the classes encoded in one embedding subsume the classes encoded in another embedding. In contrast to prior work, these models must both perceive the classes associated with the input examples and encode the relationships between different class label sets, and they are trained using only weak one-shot supervision consisting of the label-set relationships among training examples. Experiments on the OmniGlot, Open Images, and COCO datasets show that the proposed compositional embedding models outperform existing embedding methods. Our compositional embedding models have applications to multi-label object recognition for both one-shot and supervised learning.