...
  • 主题
高级搜索  >
历史搜索 清空历史
首页> 外文期刊>Multimedia, IEEE Transactions on >Semi-Supervised Bi-Dictionary Learning for Image Classification With Smooth Representation-Based Label Propagation
【24h】

Semi-Supervised Bi-Dictionary Learning for Image Classification With Smooth Representation-Based Label Propagation

机译：使用基于平滑表示的标签传播进行图像分类的半监督双向学习

获取原文
获取原文并翻译 | 示例
   

获取外文期刊封面封底 >>

       
页面导航
  • 摘要
  • 著录项
  • 相似文献
  • 相关主题

摘要

In this paper, we propose semi-supervised bi-dictionary learning for image classification with smooth representation-based label propagation (SRLP). Natural images contain complex contents of multiple objects with complicated background, clutter, and occlusions, which prevents image features from belonging to a specific category. Therefore, we employ reconstruction-based classification to implement discriminative dictionary learning in a probabilistic manner. We jointly learn a discriminative dictionary called anchor in the feature space and its corresponding soft label called anchor label in the label space, where the combination of anchor and anchor label is referred to as bi-dictionary. The learnt bi-dictionary is utilized to bridge the semantic gap in image classification. First, SRLP constructs smoothed reconstruction problems for bi-dictionary learning. Then, SRLP produces the reconstruction coefficients in the feature space over the anchor to infer soft labels of samples in the label space. Experimental results demonstrate that the proposed method is capable of learning a pair of discriminative dictionaries for image classification in the feature and label spaces and outperforms the-state-of-the-art reconstruction-based classification ones.
机译：在本文中，我们提出了基于图像表示的标签传播（SRLP）的图像分类的半监督双向学习方法。自然图像包含具有复杂背景，杂波和遮挡的多个对象的复杂内容，从而阻止了图像特征属于特定类别。因此，我们采用基于重构的分类以概率方式实现判别词典学习。我们共同学习了一个在特征空间中称为“锚点”的判别词典，以及在标签空间中与其对应的称为“锚点标签”的软标签，其中锚点和锚点标签的组合称为双向词典。学习到的字典被用来弥合图像分类中的语义鸿沟。首先，SRLP构建用于双字典学习的平滑重构问题。然后，SRLP在锚点上方的特征空间中生成重构系数，以推断标签空间中样本的软标签。实验结果表明，该方法能够学习特征和标签空间中的一对用于图像分类的判别词典，性能优于基于最新重构的分类方法。

著录项

相似文献

  • 外文文献
  • 中文文献
  • 专利
获取原文

客服邮箱：kefu@zhangqiaokeyan.com

京公网安备：11010802029741号 ICP备案号：京ICP备15016152号-6 六维联合信息科技 (北京) 有限公司©版权所有

  • 客服微信

  • 服务号