基于未知类语义约束自编码的零样本图像分类
作者:
作者单位:

中国矿业大学

作者简介:

通讯作者:

中图分类号:

TP273

基金项目:

国家自然科学基金项目(61976215, 62176259)


Zero-shot Image Classification Based on Unseen Class Semantic Constraint Autoencoder
Author:
Affiliation:

CUMT

Fund Project:

  • 摘要
  • |
  • 图/表
  • |
  • 访问统计
  • |
  • 参考文献
  • |
  • 相似文献
  • |
  • 引证文献
  • |
  • 资源附件
  • |
  • 文章评论
    摘要:

    为缓解传统零样本图像分类模型中存在的领域偏移问题,提出一种基于未知类语义约束自编码的零样本图像分类模型。首先,利用预训练的ResNet101网络提取所有已知类和未知类图像的视觉特征;其次,通过编码器将提取的图像深度视觉特征从视觉空间映射到语义空间;然后,通过解码器将映射后得到的语义向量重构为视觉特征向量。在语义自编码器的训练过程中,利用未知类图像的聚类视觉中心和未知类语义类原型的分布对齐施加约束,以缓解领域偏移问题;最后,基于经编码器预测得到的测试图像语义向量和各测试类语义类原型之间的相似性,采用最近邻算法实现零样本图像分类。AwA2和CUB数据集上的实验结果表明所提模型具有较高的分类准确度。

    Abstract:

    In order to alleviate the domain shift problem in traditional zero-shot image classification models, a zero-shot image classification model based on unknown-class semantic constraint autoencoder is proposed. Firstly, a pre-trained ResNet101 network is used to the extract visual features of all known-class and unknown-class images. Then, the extracted deep visual features are mapped from the visual space to semantic space through an encoder. Next, the obtained semantic vectors after mapping are reconstructed into the visual feature vectors through a decoder. In the training process of semantic autoencoder, a constraint is imposed based on the distribution alignment between the clustering visual centers of unknown-class images and the unknown-class semantic prototypes to alleviate the domain shift problem. Finally, based on the similarity between the semantic vector of testing image predicted by encoder and the semantic prototype of each testing class, the nearest neighbor algorithm is used to achieve zero-shot image classification. Experimental results on AwA2 and CUB datasets show that the proposed model has high classification accuracy.

    参考文献
    相似文献
    引证文献
引用本文
分享
文章指标
  • 点击次数:
  • 下载次数:
  • HTML阅读次数:
  • 引用次数:
历史
  • 收稿日期:2022-02-20
  • 最后修改日期:2022-11-22
  • 录用日期:2022-06-10
  • 在线发布日期: 2022-06-28
  • 出版日期: