欢迎访问《图学学报》 分享到:

图学学报 ›› 2022, Vol. 43 ›› Issue (4): 641-650.DOI: 10.11996/JG.j.2095-302X.2022040641

• 图像处理与计算机视觉 • 上一篇    下一篇

基于域自适应的云南重彩画无监督情感识别

  

  1. 1. 云南大学信息技术中心,云南 昆明 650500; 2. 云南大学信息学院,云南 昆明 650500
  • 出版日期:2022-08-31 发布日期:2022-08-15
  • 通讯作者: 徐丹(1968),女,教授,博士。主要研究方向为图形学、计算机视觉、图像分析与理解、数字文化保护及图像情感计算等
  • 基金资助:
    国家自然科学基金项目(61761046);云南省“云岭学者”专项(YNWR-YLXZ-2018-022);云南省教育厅研究项目(2021J0029)

Unsupervised emotion recognition of Yunnan Heavy Color Paintings based on domain adaptation

  1. 1. Information Technology Center, Yunnan University, Kunming Yunnan 650500, China;
    2. School of Information Science and Engineering, Yunnan University, Kunming Yunnan 650500, China
  • Online:2022-08-31 Published:2022-08-15
  • Contact: XU Dan (1968), professor, Ph.D. Her main research interests cover graphics, computer vision, image analysis and understanding, digital culture preservation, image emotion computing, etc. E-mail:danxu@ynu.edu.cn
  • Supported by:
    National Natural Science Foundation of China (61761046); Applied Basic Research Key Project of Yunnan (YNWR-YLXZ-2018-022);
    Scientific Research Project of Yunnan Province Education Department (2021J0029)

摘要:

计算机视觉中,深度学习之所以取得如此巨大的突破,均得益于可获得的大规模标记数据集,而在图像情感分析中,由于情感语义的模糊性,导致图像情感标注困难,公开可获得图像情感数据集较少,其规模也小,制约了基于深度学习的图像情感分析性能。情感语义具有其特有的有序性和极性分组特征,而已有的图像情感分析方法中很少关注到情感语义的这些本质特征。基于域自适方法,考虑情感语义的本质特征,提出一种基于推土机距离的情感语义对齐方式,将带标记的情感数据集的训练模型更好地迁移到无标记的情感数据集上,实现无监督的图像情感分析,解决情感数据集标注困难的问题。该方法应用于创建的云南重彩画数据集,实验结果表明,其能有效地对齐源域和目标域数据,实现无监督的情感数据集自动标注,有利于扩充图像情感数据集规模。

关键词: 域自适应, 云南重彩画, 推土机距离, 无监督, 自动标注

Abstract:

Thanks to the large-scale labeled datasets available, deep learning has made a great breakthrough in computer vision. However, due to the ambiguity of emotion semantics, it is hard to annotate the emotional labels for images. Thus, only a few small-scale image emotion datasets are open and available, restricting the performance of image emotion analysis based on deep learning. The semantics of emotions have unique characteristics, such as order and polarity, but few studies have paid attention to these essential characteristics in image emotion analysis. Thus, in the paper, based on domain adaptation, considering the essential characteristics of emotion semantics, that is, the ordered and grouped polarity, we proposed to measure emotion semantic differences through earth mover’s distance (EMD). The goal is to better transfer the trained model with labeled emotion dataset to unlabeled emotion dataset and complete the unsupervised image emotion analysis. The Yunnan Heavy Color Paintings Emotion dataset was created in this paper, and was applied to our proposed method. The experimental results demonstrate that the proposed method can effectively align the emotional semantics between the source domain and the target domain, realizing the unsupervised automatic annotation of emotion dataset, thus expanding the size of the image emotion dataset.

Key words: domain adaptation, Yunnan Heavy Color Paintings, earth mover’s distance, unsupervised, automatic annotation

中图分类号: