.png){kind=icon}
返回
Cross Knowledge-based Generative Zero-Shot Learning approach with Taxonomy Regularization
.png){kind=icon}
OA
AI
DOI：10.1016/j.neunet.2021.02.009.png)
.png){kind=icon}
.png){kind=icon}
分享.png){kind=icon}
收藏
摘要
En 中文
Although zero-shot learning (ZSL) has an inferential capability of recognizing new classes that have never been seen before, it always faces two fundamental challenges of the cross modality and cross domain challenges. In order to alleviate these problems, we develop a generative network-based ZSL approach equipped with the proposed Cross Knowledge Learning (CKL) scheme and Taxonomy Regularization (TR). In our approach, the semantic features are taken as inputs, and the output is the synthesized visual features generated from the corresponding semantic features. CKL enables more relevant semantic features to be trained for semantic-to-visual feature embedding in ZSL, while Taxonomy Regularization (TR) significantly improves the intersections with unseen images with more generalized visual features generated from generative network. Extensive experiments on several benchmark datasets (i.e., AwA1, AwA2, CUB, NAB and aPY) show that our approach is superior to these state-of-the-art methods in terms of ZSL image classification and retrieval. (C) 2021 Elsevier Ltd. All rights reserved.
Keyword:
Zero-Shot Learning
Image recognition
Generative Adversarial Network
Knowledge engineering
AI总结
对已上传原文的论文进行重点信息的提取，主要内容包括：简要概述、研究摘要、背景介绍、关键亮点、图文解析、展望与总结。
期刊
IF:
6.3
论文数:
8.2K
被引数:
3.0W
机构
引用论文
.png){kind=icon}
分享收藏
查看更多内容