基于跨域对抗学习的零样本分类

刘欢; 郑庆华; 罗敏楠; 赵洪科; 肖阳; 吕彦章

doi:10.7544/issn1000-1239.2019.20190614

基于跨域对抗学习的零样本分类

¹(西安交通大学计算机科学与技术学院西安 710049)
²(天津大学管理与经济学部天津 300072)
³(综合业务网国家重点实验室(西安电子科技大学) 西安 710071) (huanliucs@gmail.com)

基金项目: 国家重点研发计划项目2018YFB1004500)；国家自然科学基金面上项目(61572399)；国家自然科学基金创新群体(61721002)；教育部创新团队(IRT_17R86)

详细信息

中图分类号: TP391
计量
- 文章访问数: 1422
- HTML全文浏览量: 3
- PDF下载量: 670
出版历程
- 发布日期: 2019-11-30

Cross-Domain Adversarial Learning for Zero-Shot Classification

¹(School of Computer Science and Technology, Xi’an Jiaotong University, Xi’an 710049)
²(College of Management and Economics, Tianjin University, Tianjin 300072)
³(State Key Laboratory of Integrated Services Networks (Xidian University), Xi’an 710071)

摘要

摘要: 零样本学习旨在识别具有少量、甚至没有训练样本的未见类，这些类与可见类遵循不同的数据分布.最近，随着深度神经网络在跨模态生成方面的成功，使用合成的样本对未见数据进行分类取得了巨大突破.现有方法通过共享生成器和解码器，联合传统生成对抗网络和变分自编码器来实现样本的合成.然而，由于这2种生成网络产生的数据分布不同，联合模型合成的数据遵循复杂的多域分布.针对这个问题，提出跨域对抗生成网络(CrossD-AGN)，将传统生成对抗网络和变分自编码器有机结合起来，基于类级语义信息为未见类合成样本，从而实现零样本分类.提出跨域对抗学习机制，引入2个对称的跨域判别器，通过判断合成样本属于生成器域分布还是解码器域分布，促使联合模型中的生成器/解码器不断优化，提高样本合成能力.在多个真实数据集上进行了广泛的实验，结果表明了所提出方法在零样本学习上的有效性和优越性.
- 零样本学习 /
- 生成模型 /
- 跨模态生成 /
- 跨域对抗学习 /
- 联合模型
Abstract: Zero-shot learning (ZSL) aims to recognize novel categories, which have few or even no sample for training and follow a different distribution from seen classes. With the recent advances of deep neural networks on cross-modal generation, encouraging breakthroughs have been achieved on classifying unseen categories with their synthetic samples. Extant methods synthesize unseen samples with the combination of generative adversarial nets (GANs) and variational auto-encoder (VAE) by sharing the generator and the decoder. However, due to the different data distributions produced by these two kinds of generative models, fake samples synthesized by the joint model follow the complex multi-domain distribution instead of satisfying a single model distribution. To address this issue, in this paper we propose a cross-domain adversarial generative network (CrossD-AGN) to integrate the traditional GANs and VAE into a unified framework, which is able to generate unseen samples based on the class-level semantics for zero-shot classification. We propose two symmetric cross-domain discriminators along with the cross-domain adversarial learning mechanism to learn to determine whether a synthetic sample is from the generator-domain or the decoder-domain distribution, so as to drive the generator/decoder of the joint model to improve its capacity of synthesizing fake samples. Extensive experimental results over several real-world datasets demonstrate the effectiveness and superiority of the proposed model on zero-shot visual classification.
- zero-shot learning /
- generative model /
- cross-modal generation /
- cross-domain adversarial learning /
- joint model

HTML全文

参考文献(0)

施引文献(18)

期刊类型引用(7)

1.	杨秀璋，武帅，宋籍文，廖文婧，任天舒，刘建义. 基于LDA和关系图谱的数据治理文献主题演化研究. 信息技术与信息化. 2022(08): 6-12 . 百度学术
2.	黄飞杰，张卫东，侯石鹏，宋红文. 基于GSP算法的卷烟消费者研究. 信息与电脑(理论版). 2022(16): 58-60 . 百度学术
3.	张瑾，朱桂祥，王宇琛，郑烁佳，陈镜潞. 基于异质图表达学习的跨境电商推荐模型. 电子与信息学报. 2022(11): 4008-4017 . 百度学术
4.	冯晨娇，宋鹏，王智强，梁吉业. 一种基于3因素概率图模型的长尾推荐方法. 计算机研究与发展. 2021(09): 1975-1986 . 本站查看
5.	牛俊洁，崔忠伟，赵晨洁，王永金，吴恋. 个性化旅游推荐技术研究及发展综述. 物联网技术. 2020(03): 86-88+91 . 百度学术
6.	史亚奇. 基于人性化特征的旅游地智能推荐系统. 现代电子技术. 2020(11): 183-186 . 百度学术
7.	张如花，屈正庚. 基于AHP的旅游网站评价体系研究. 甘肃科学学报. 2019(05): 32-36 . 百度学术