arXivDaily arXiv每日学术速递 周一至周五更新
arXiv周末暂无论文更新,休息一下吧,周末愉快~~
arXiv 2103.15939cs.CVcs.LG
收藏

一种基于三重分布嵌入的零样本学习方法

A Simple Approach for Zero-Shot Learning based on Triplet Distribution Embeddings

KTH Royal Institute of Technology(瑞典皇家理工学院);Sony Europe B.V.(索尼欧洲公司)

Vivek Chalumuri, Bac Nguyen

摘要:

零样本学习(Zero-Shot Learning,简称ZRL)的目标是在没有标记训练数据的情况下,利用包含可见类和不可见类之间的知识的语义信息来识别不可见类。现有的语义空间嵌入方法主要使用向量来表示语义空间的嵌入。尽管流行,这样的向量表示限制了表现力方面的建模类内的变化,为每个类。我们通过利用分布嵌入来解决这个问题。更具体地说,图像嵌入和类嵌入都被建模为高斯分布,其中它们的相似性关系通过使用三元组约束来保持。指导我们方法的关键直觉是,对于每个图像,正确的类标签的嵌入应该比任何其他类标签的嵌入更接近。在多个基准数据集上进行的大量实验表明,该方法在传统的GML和更具挑战性的广义零样本学习(GML)设置下都取得了非常有竞争力的结果。

英文摘要:

Given the semantic descriptions of classes, Zero-Shot Learning (ZSL) aims to recognize unseen classes without labeled training data by exploiting semantic information, which contains knowledge between seen and unseen classes. Existing ZSL methods mainly use vectors to represent the embeddings to the semantic space. Despite the popularity, such vector representation limits the expressivity in terms of modeling the intra-class variability for each class. We address this issue by leveraging the use of distribution embeddings. More specifically, both image embeddings and class embeddings are modeled as Gaussian distributions, where their similarity relationships are preserved through the use of triplet constraints. The key intuition which guides our approach is that for each image, the embedding of the correct class label should be closer than that of any other class label. Extensive experiments on multiple benchmark data sets show that the proposed method achieves highly competitive results for both traditional ZSL and more challenging Generalized Zero-Shot Learning (GZSL) settings.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑