###
DOI:
Journal of Software:2018.29(S2):16-29

一种基于视觉特征组合构造的零样本学习方法
杨刚,刘金露,李锡荣,许洁萍
(中国人民大学 信息学院, 北京 100872;中国人民大学 信息学院, 北京 100872;数据工程与知识工程重点实验室(中国人民大学), 北京 100872)
Visual Feature Combination Approach for Zero-Shot Learning
YANG Gang,LIU Jin-Lu,LI Xi-Rong,XU Jie-Ping
(School of Information, Renmin University of China, Beijing 100872, China;School of Information, Renmin University of China, Beijing 100872, China;Key Laboratory of Data Engineering and Knowledge Engineering(Renmin University of China), Beijing 100872, China)
Abstract
Chart / table
Reference
Similar Articles
Article :Browse 542   Download 397
Received:April 14, 2018    Revised:September 30, 2018
> 中文摘要: 零样本学习是机器学习和图像识别领域重要的研究热点.零样本学习方法通常利用未见类与可见类之间的类别语义信息,将从可见类样本学习到的知识转移到未见类,实现对未见类样本的分类识别.提出了一种基于视觉特征组合构造的零样本学习方法,采用特征组合的方式构造产生大量未见类样例特征,将零样本学习问题转化为标准的监督学习分类问题.该方法模拟了人类的联想认知过程,其主要包括4步:特征-属性关系提取、样例构造、样例过滤、特征域适应.在可见类样本上抽取类别属性与特征维度的对应关系;利用特征-属性关系,通过视觉特征的组合构造的方式,产生未见类样例;引入非相似表示,过滤掉不合理的未见类样例;提出半监督特征域适应和无监督特征域适应,实现未见类样例的线性转换,产生更有效的未见类样例.在3个基准数据集(AwA,AwA2和SUN)上的实验结果显示,该方法效能优越,在数据集AwA上获得了当前最优的Top-1分类正确率82.6%.实验结果证明了该方法的有效性和先进性.
Abstract:Zero-Shot learning is an important research in the field of machine learning and image recognition. Zero-Shot learning methods normally use the semantic information among unseen classes and seen classes to transfer the knowledge which is learned from examples of seen classes to unseen classes, so as to recognize and classify the examples of unseen classes. In this study, a zero-shot learning approach based on construction of visual feature combination is proposed. The approach generates many examples of unseen class on visual feature level by the way of feature combination, which is first proposed, and thus transforms zero-shot learning problem to be a traditional classification problem solved by supervised learning. The approach mimics human cognition process of associative memory, and includes four steps:feature-attribute relation extraction, example construction, example screening, and domain adaption. On training examples of seen classes, the relationship between class attributes and dimensions of feature is extracted; on visual feature level, examples of unseen classes are generated by visual feature combination; dissimilarity representation is introduced to filter the generated examples of unseen classes; semi-supervised and unsupervised feature domain adaption are proposed to linearly transform the generated examples of unseen classes to be more effective. The proposed approach shows superior performance on three benchmark datasets (AwA, AwA2, and SUN), especially on dataset AwA, it obtains 82.6% top-1 accuracy which is the best result as far as we know. Experiment results demonstrate the effectiveness and superiority of the proposed approach.
文章编号:     中图分类号:    文献标志码:
基金项目:国家自然科学基金(61773385,61672523) 国家自然科学基金(61773385,61672523)
Foundation items:National Natural Science Foundation of China (61773385, 61672523)
Reference text:

杨刚,刘金露,李锡荣,许洁萍.一种基于视觉特征组合构造的零样本学习方法.软件学报,2018,29(S2):16-29

YANG Gang,LIU Jin-Lu,LI Xi-Rong,XU Jie-Ping.Visual Feature Combination Approach for Zero-Shot Learning.Journal of Software,2018,29(S2):16-29