基于生成对抗网络的零样本图像分类

doi:10.13700/j.bh.1001-5965.2019.0363

北京航空航天大学学报 ›› 2019, Vol. 45 ›› Issue (12): 2345-2350.doi: 10.13700/j.bh.1001-5965.2019.0363

基于生成对抗网络的零样本图像分类

魏宏喜, 张越

内蒙古大学计算机学院, 呼和浩特 010021

收稿日期:2019-07-08 出版日期:2019-12-20 发布日期:2019-12-31
通讯作者: 魏宏喜 E-mail:cswhx@imu.edu.cn
作者简介:魏宏喜男,博士,教授,博士生导师。主要研究方向:机器学习与数据挖掘;张越男,硕士研究生。主要研究方向:图像分类。
基金资助:
国家自然科学基金（61463038）；内蒙古自治区自然科学基金重大项目（2019ZD14）

Zero-shot image classification based on generative adversarial network

WEI Hongxi, ZHANG Yue

College of Computer Science, Inner Mongolia University, Hohhot 010021, China

Received:2019-07-08 Online:2019-12-20 Published:2019-12-31
Supported by:
National Natural Science Foundation of China (61463038); Natural Science Foundation of Inner Mongolia Autonomous Region (2019ZD14)

摘要/Abstract

摘要： 在图像分类任务中，零样本图像分类问题已成为一个研究热点。为了解决零样本图像分类问题，采用一种基于生成对抗网络（GAN）的方法，通过生成未知类的图像特征使得零样本分类任务转换为传统的图像分类任务。同时对生成对抗网络中的判别网络做出改进，使其判别过程更加准确，从而进一步提高生成图像特征的质量。实验结果表明：所提方法在AWA、CUB和SUN数据集上的分类准确率分别提高了0.4%、0.4%和0.5%。因此，所提方法通过改进生成对抗网络，能够生成质量更好的图像特征，从而有效解决零样本图像分类问题。

关键词: 深度学习, 图像分类, 零样本学习, 生成对抗网络(GAN), 图像特征生成

Abstract: The problem of zero-shot image classification has become a research focus in the field of image classification. In this paper, a method based on generative adversarial network (GAN) is used to solve the problem of zero-shot image classification. By generating image features of unseen classes, the zero-shot classification task is transformed into a conventional image classification task. At the same time, this paper makes modifications to the discriminant network in the generative adversarial network to make the discriminating process more accurate. The experimental results show that the performance of the proposed method has been increased by 0.4%, 0.4% and 0.5% on the datasets of AWA, CUB and SUN, respectively. Therefore, the proposed method can generate the better features by improving the generative adversarial networks, which results in solving the problem of zero-shot image calssification effectively.

Key words: deep learning, image classification, zero-shot learning, generative adversarial network (GAN), image feature generation

中图分类号:

TP391

魏宏喜, 张越. 基于生成对抗网络的零样本图像分类[J]. 北京航空航天大学学报, 2019, 45(12): 2345-2350.

WEI Hongxi, ZHANG Yue. Zero-shot image classification based on generative adversarial network[J]. JOURNAL OF BEIJING UNIVERSITY OF AERONAUTICS AND A, 2019, 45(12): 2345-2350.

参考文献

[1] LAROCHELLE H,ERHAN D,BENGIO Y.Zero-data learning of new tasks[C]//Proceedings of the Association for the Advancement of Artificial Intelligence. Palo Alto:AAAI Press,2008:646-651.
[2] CHANGPINYO S,CHAO W,GONG B,et al.Synthesized classifiers for zero-shot learning[C]//Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition.Piscataway,NJ:IEEE Press,2016:5327-5336.
[3] KODIROV E,XIANG T,GONG S.Semantic auto-encoder for zero-shot learning[C]//Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition.Piscataway,NJ:IEEE Press,2017:4447-4456.
[4] XIAN Y,SCHIELE B,AKATA Z.Zero-shot learning-the good,the bad and the ugly[C]//Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition.Piscataway,NJ:IEEE Press,2017:3077-3086.
[5] DING Z,SHAO M,FU Y.Low-rank embedded ensemble semantic dictionary for zero-shot learning[C]//Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition.Piscataway,NJ:IEEE Press,2017:6005-6013.
[6] LAMPERT C H,NICKISCH H,HARMELING S.Attribute-based classification for zero-shot visual object categorization[J].IEEE Transactions on Pattern Analysis and Machine Intelligence,2014,36(3):453-465.
[7] ROMERA-PAREDES B,TORR P.An embarrassingly simple approach to zero-shot learning[C]//Proceedings of the International Conference on Machine Learning.Madison:Omnipress,2015:2152-2161.
[8] GOODFELLOW I,POUGET-ABADIE J,MIRZA M,et al.Generative adversarial nets[C]//Proceedings of the Neural Information Processing Systems.Cambridge:MIT Press,2014:2672-2680.
[9] XIAN Y,LORENZ T,SCHIELE B,et al.Feature generating networks for zero-shot learning[C]//Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition.Piscataway,NJ:IEEE Press,2018:5542-5551.
[10] ZHU Y,ELHOSEINY M,LIU B,et al.A generative adversarial approach for zero-shot learning from noisy texts[C]//Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition.Piscataway,NJ:IEEE Press,2018:1004-1013.
[11] ARJOVSKY M,CHINTALA S,BOTTOU L.Wasserstein generative adversarial networks[C]//Proceedings of the International Conference on Machine Learning.Madison:Omnipress,2017:214-223.
[12] MIRZA M,OSINDERO S.Conditional generative adversarial nets[EB/OL].(2014-11-06)[2019-07-01].https://arxiv.org/abs/1411.1784.
[13] LAMPERT C H,NICKISCH H,HARMELING S.Learning to detect unseen object classes by between-class attribute transfer[C]//Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition.Piscataway,NJ:IEEE Press,2009:951-958.
[14] WAH C,BRANSON S,WELINDER P,et al.The Caltech-UCSD Birds-200-2011 dataset:CNS-TR-2011-001[R].Pasadena:California Institute of Technology,2011.
[15] PATTERSON G,HAYS J.SUN attribute database:Discovering,annotating,and recognizing scene attributes[C]//Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition.Piscataway,NJ:IEEE Press,2012:2751-2758.
[16] NOROUZI M,MIKOLOV T,BENGIO S.Zero-shot learning by convex combination of semantic embeddings[C]//Proceedings of the International Conference on Learning Representations.Brookline:Microtome Publishing,2014:10-19.
[17] ZHANG Z,SALIGRAMA V.Zero-shot learning via semantic similarity embedding[C]//Proceedings of the IEEE International Conference on Computer Vision and Pattern Recognition.Piscataway,NJ:IEEE Press,2015:4166-4174.
[18] FROME A,CORRADO G S,SHLENS J,et al.DeViSE:A deep visual semantic embedding model[C]//Proceedings of the Neural Information Processing Systems.Cambridge:MIT Press,2013:2121-2129.
[19] AKATA Z,REED S,WALTER D,et al.Evaluation of output embeddings for fine-grained image classification[C]//Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition.Piscataway,NJ:IEEE Press,2015:2927-2936.
[20] AKATA Z,PERRONNIN F,HARCHAOUI Z,et al.Label-embedding for image classification[J].IEEE Transactions on Pattern Analysis and Machine Intelligence,2016,38(7):1425-1438.

基于生成对抗网络的零样本图像分类

Zero-shot image classification based on generative adversarial network

PDF (PC)

可视化

摘要/Abstract

引用本文

使用本文

参考文献

相关文章 14

编辑推荐

Metrics

本文评价

[1]	张克明, 蔡远文, 任元. 基于生成对抗网络的航天异常事件检测方法[J]. 北京航空航天大学学报, 2019, 45(7): 1329-1336.
[2]	张新峰, 郭宇桐, 蔡轶珩, 孙萌. 基于DCNN和全连接CRF的舌图像分割算法[J]. 北京航空航天大学学报, 2019, 45(12): 2364-2374.
[3]	湛颖, 高妍, 谢凌云. 中国国画艺术美感特征分析与分类[J]. 北京航空航天大学学报, 2019, 45(12): 2514-2522.
[4]	赵国, 秦世引. PMMWI与VI优势互补的人体隐蔽违禁物检测与定位[J]. 北京航空航天大学学报, 2019, 45(10): 2011-2025.
[5]	郭琳, 秦世引. 遥感图像飞机目标高效搜检深度学习优化算法[J]. 北京航空航天大学学报, 2019, 45(1): 159-173.
[6]	韩京冶, 许福, 陈志泊, 刘辉. 一种基于深度学习的交互式电话号码识别方法[J]. 北京航空航天大学学报, 2018, 44(5): 1074-1080.
[7]	王鑫, 吴际, 刘超, 杨海燕, 杜艳丽, 牛文生. 基于LSTM循环神经网络的故障时间序列预测[J]. 北京航空航天大学学报, 2018, 44(4): 772-784.
[8]	车畅畅, 王华伟, 倪晓梅, 洪骥宇. 基于深度学习的航空发动机故障融合诊断[J]. 北京航空航天大学学报, 2018, 44(3): 621-628.
[9]	许轲, 吴凤鸽, 赵军锁. 基于深度强化学习的软件定义卫星姿态控制算法[J]. 北京航空航天大学学报, 2018, 44(12): 2651-2659.
[10]	王鑫, 侯志强, 余旺盛, 戴铂, 金泽芬芬. 基于深度稀疏学习的鲁棒视觉跟踪[J]. 北京航空航天大学学报, 2017, 43(12): 2554-2563.
[11]	张旭, 蒋建国, 洪日昌, 杜跃. 基于朴素贝叶斯K近邻的快速图像分类算法[J]. 北京航空航天大学学报, 2015, 41(2): 302-310.
[12]	丁锴, 陈伟海, 吴星明, 刘中. 基于规范割的空间金字塔图像分类算法[J]. 北京航空航天大学学报, 2013, 39(10): 1342-1347.
[13]	郑红, 吴兴华, 曹琼, 李文庆. 基于云特征的遥感图像可用度影响因素分析[J]. 北京航空航天大学学报, 2010, 36(12): 1396-1399.
[14]	刘娜娜, 李景文, 李宁. 基于图论分割的多光谱图像非监督分类方法[J]. 北京航空航天大学学报, 2009, 35(5): 544-546.