[1]刘 帅,黄 刚,戴晓峰,等.一种融合生成对抗网络的零样本图像分类方法[J].计算机技术与发展,2022,32(07):87-92.[doi:10. 3969 / j. issn. 1673-629X. 2022. 07. 015]
　LIU Shuai,HUANG Gang,DAI Xiao-feng,et al.A Zero-shot Classification Based on Generative Adversarial Network[J].,2022,32(07):87-92.[doi:10. 3969 / j. issn. 1673-629X. 2022. 07. 015]
点击复制

一种融合生成对抗网络的零样本图像分类方法()
分享到：

《计算机技术与发展》[ISSN:1006-6977/CN:61-1281/TN]

卷:
32
期数:
2022年07期
页码:
87-92
栏目:
图形与图像
出版日期:
2022-07-10

文章信息/Info

Title:
A Zero-shot Classification Based on Generative Adversarial Network
文章编号:
1673-629X(2022)07-0086-06
作者:
刘 帅1; 黄 刚1; 戴晓峰1; 颜金花2
1. 南京邮电大学 计算机学院,江苏 南京 210023;
2. 南京工业大学 计算机科学与技术学院,江苏 南京 211816
Author(s):
LIU Shuai1 ; HUANG Gang1 ; DAI Xiao-feng1 ; YAN Jin-hua2
1. School of Computer,Nanjing University of Posts and Telecommunications,Nanjing 210023,China;
2. School of Computer Science and Technology,Nanjing Technology University,Nanjing 211816,China
关键词:
零样本学习; 生成对抗网络; 语义信息; 图像特征生成; 信息重构
Keywords:
zero-shot learning; generative adversarial network; semantic information; image feature generation; information reconstruction
分类号:
TP301
DOI:
10. 3969 / j. issn. 1673-629X. 2022. 07. 015
摘要:
目前, 很多零样本图像分类方法是采用学习语义信息空间和图像特征空间之间的映射关系来实现图像分类, 但是这些方法会产生枢纽化和域漂移问题。 通过利用生成对抗网络实现图像特征生成可以缓解以上两种问题,但该方法容易产生模式崩溃从而导致生成的图像特征不真实。 因此提出一种改进的生成对抗网络方法,通过在生成器网络上增加一个重构网络,将生成器生成的图像特征重构回语义信息,以此实现生成器网络生成的图像特征更加符合语义信息的图像特征。 实验结果表明,该方法相较于原本的生成对抗网络模型而言,在 AWA、CUB、FLO、SUN 四个数据集上的分类准确率分别提升了 1. 0、0. 1、1. 2 和 0. 9 个百分点,证明了通过融合改进的生成对抗网络实现零样本图像分类方法的有效性和可行性。
Abstract:
Since most zero - shot image classification adopts the mapping relationship between the semantic information space? ? and the image feature space to achieve the image classification, which will cause hubness and domain drift. The above two problems can be alleviated by using the generated adversarial network to generate the image feature,but this method is prone to mode collapse,which will result in unrealistic image features. Therefore, an improved generative adversarial network method is proposed. By adding are construction network to the generator network, the image features generated by the generator are reconstructed back to semantic information,so that it is more in line with the semantic information. The experiment shows that compared with the original generative adversarial network model,the proposed method has increased by 1. 0,0. 1,1. 2, and 0. 9 percent in classification accuracy on the four datasets of AWA,CUB,FLO,and SUN, respectively. It proves the effectiveness and feasibility of the zero - shot image classification method by fusing the improved generative adversarial network.

相似文献/References:

[1]秦牧轩,荆晓远,吴 飞.基于公共空间嵌入的端到端深度零样本学习[J].计算机技术与发展,2018,28(11):44.[doi:10.3969/ j. issn.1673-629X.2018.11.010]
　QIN Mu-xuan,JING Xiao-yuan,WU Fei.End-to-end Deep Zero-shot Learning Based on Co-space Embedding[J].,2018,28(07):44.[doi:10.3969/ j. issn.1673-629X.2018.11.010]
[2]康嘉钰,苏凡军.基于生成对抗网络的长短兴趣推荐模型[J].计算机技术与发展,2020,30(06):35.[doi:10. 3969 / j. issn. 1673-629X. 2020. 06. 007]
　KANG Jia-yu,SU Fan-jun.A Long-short-term Interests Recommendation Model Based on Generative Adversarial Networks[J].,2020,30(07):35.[doi:10. 3969 / j. issn. 1673-629X. 2020. 06. 007]
[3]蒋文杰,罗晓曙*,戴沁璇.一种改进的生成对抗网络的图像上色方法研究[J].计算机技术与发展,2020,30(07):56.[doi:10. 3969 / j. issn. 1673-629X. 2020. 07. 013]
　JIANG Wen-jie,LUO Xiao-shu*,DAI Qin-xuan.Research on an Improved Method of Generative Adversarial Networks Image Coloring[J].,2020,30(07):56.[doi:10. 3969 / j. issn. 1673-629X. 2020. 07. 013]
[4]周传华,吴幸运,李 鸣.基于 WGAN 单帧人脸图像超分辨率算法[J].计算机技术与发展,2020,30(09):29.[doi:10. 3969 / j. issn. 1673-629X. 2020. 09. 006]
　ZHOU Chuan-hua,WU Xing-yun,LI Ming.Single Frame Face Images Super-resolution Algorithm Based on WGAN[J].,2020,30(07):29.[doi:10. 3969 / j. issn. 1673-629X. 2020. 09. 006]
[5]庄兴旺,丁岳伟.多维度注意力和语义再生的文本生成图像模型[J].计算机技术与发展,2020,30(12):27.[doi:10. 3969 / j. issn. 1673-629X. 2020. 12. 005]
　ZHUANG Xing-wang,DING Yue-wei.Text-to-image Model by Multidimensional Attention and Semantic Regeneration[J].,2020,30(07):27.[doi:10. 3969 / j. issn. 1673-629X. 2020. 12. 005]
[6]尹玉婷,肖秦琨.基于深度卷积生成对抗网络的图像生成[J].计算机技术与发展,2021,31(04):86.[doi:10. 3969 / j. issn. 1673-629X. 2021. 04. 015]
　YIN Yu-ting,XIAO Qin-kun.Image Generation Based on Deep Convolution GenerativeAdversarial Networks[J].,2021,31(07):86.[doi:10. 3969 / j. issn. 1673-629X. 2021. 04. 015]
[7]程换新,张志浩,刘文翰,等.基于生成对抗网络的图像识别[J].计算机技术与发展,2021,31(06):175.[doi:10. 3969 / j. issn. 1673-629X. 2021. 06. 031]
　CHENG Huan-xin,ZHANG Zhi-hao,LIU Wen-han,et al.Image Recognition Based on Generative Adversarial Network[J].,2021,31(07):175.[doi:10. 3969 / j. issn. 1673-629X. 2021. 06. 031]
[8]苑金辉,乔 艳,费烨琳,等.基于深度迁移学习的心脏 MRI 图像左心室分割[J].计算机技术与发展,2021,31(06):35.[doi:10. 3969 / j. issn. 1673-629X. 2021. 06. 007]
　YUAN Jin-hui,QIAO Yan,FEI Ye-lin,et al.Left Ventricular Segmentation in Cardiac MRI Images Based onDeep Transfer Learning[J].,2021,31(07):35.[doi:10. 3969 / j. issn. 1673-629X. 2021. 06. 007]
[9]王田丰,胡谷雨,王 睿,等.基于 AAE 的网络性能异常发现[J].计算机技术与发展,2021,31(07):113.[doi:10. 3969 / j. issn. 1673-629X. 2021. 07. 019]
　WANG Tian-feng,HU Gu-yu,WANG Rui,et al.AAE-based Anomaly Detection for Network Performance[J].,2021,31(07):113.[doi:10. 3969 / j. issn. 1673-629X. 2021. 07. 019]
[10]徐志鹏,卢官明,罗燕晴.基于 CycleGAN 的人脸素描图像生成[J].计算机技术与发展,2021,31(08):63.[doi:10. 3969 / j. issn. 1673-629X. 2021. 08. 011]
　XU Zhi-peng,LU Guan-ming,LUO Yan-qing.Face Sketch Image Generation Based on CycleGAN[J].,2021,31(07):63.[doi:10. 3969 / j. issn. 1673-629X. 2021. 08. 011]

更新日期/Last Update: 2022-07-10