arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 1803.08035cs.CVcs.CL
收藏

基于语义嵌入和知识图谱的Zero-shot识别

Zero-shot Recognition via Semantic Embeddings and Knowledge Graphs

The Robotics Institute, Carnegie Mellon University(卡内基梅隆大学机器人研究所)

Xiaolong Wang, Yufei Ye, Abhinav Gupta

摘要:

我们考虑的问题zero-shot识别:学习一个视觉分类器的类别与零训练样本,只是使用词嵌入的类别和它的关系,视觉数据提供。处理不熟悉或新类别的关键是将从熟悉类中获得的知识转移到描述不熟悉类中。在本文中,我们建立在最近推出的图卷积网络(GCN),并提出了一种方法,使用语义嵌入和分类关系来预测分类器。给定一个学习过的知识图谱(KG),我们的方法将每个节点(表示视觉类别)的语义嵌入作为输入。经过一系列的图卷积,我们预测每个类别的视觉分类器。在训练过程中,给出了几个类别的视觉分类器来学习GCN参数。在测试时,这些过滤器被用来预测看不见的类别的视觉分类器。我们证明了我们的方法对KG中的噪声具有鲁棒性。更重要的是,与当前最先进的结果相比,我们的方法在性能上有了显着的改进(从某些指标的2 ~ 3%到一些指标的20%)。

英文摘要:

We consider the problem of zero-shot recognition: learning a visual classifier for a category with zero training examples, just using the word embedding of the category and its relationship to other categories, which visual data are provided. The key to dealing with the unfamiliar or novel category is to transfer knowledge obtained from familiar classes to describe the unfamiliar class. In this paper, we build upon the recently introduced Graph Convolutional Network (GCN) and propose an approach that uses both semantic embeddings and the categorical relationships to predict the classifiers. Given a learned knowledge graph (KG), our approach takes as input semantic embeddings for each node (representing visual category). After a series of graph convolutions, we predict the visual classifier for each category. During training, the visual classifiers for a few categories are given to learn the GCN parameters. At test time, these filters are used to predict the visual classifiers of unseen categories. We show that our approach is robust to noise in the KG. More importantly, our approach provides significant improvement in performance compared to the current state-of-the-art results (from 2 ~ 3% on some metrics to whopping 20% on a few).

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。

↑