• 主题
高级搜索  >
历史搜索 清空历史
首页> 外文会议>International conference on graphic and image processing >Scene Recognition based on Integrating Active Learning with Dictionary Learning
【24h】

Scene Recognition based on Integrating Active Learning with Dictionary Learning

机译：基于主动学习与词典学习相结合的场景识别

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

摘要

Scene recognition is a significant topic in the field of computer vision. Most of the existing scene recognition models require a large number of labeled training samples to achieve good performance. However, labeling image manually is a time consuming task and often unrealistic in practice. In order to gain satisfying recognition results when labeled samples are insufficient, this paper proposed a scene recognition algorithm named Integrating Active Learning and Dictionary Learning (IALDL). IALDL adopts projective dictionary pair learning (DPL) as classifier and introduces active learning mechanism into DPL for improving its performance. When constructing sampling criterion in active learning, IALDL considers both uncertainty and representativeness as the sampling criteria to effectively select the useful unlabeled samples from a given sample set for expanding the training dataset. Experiment results on three standard databases demonstrate the feasibility and validity of the proposed IALDL.
机译：场景识别是计算机视觉领域的重要课题。现有的大多数场景识别模型都需要大量带标签的训练样本才能获得良好的性能。但是，手动标记图像是一项耗时的任务，并且在实践中通常不切实际。为了在标记样本不足时获得令人满意的识别结果，本文提出了一种场景识别算法，称为主动学习与字典学习集成。 IALDL采用投影字典对学习（DPL）作为分类器，并将主动学习机制引入DPL以提高其性能。在构建主动学习中的采样标准时，IALDL会将不确定性和代表性作为采样标准，以从给定的样本集中有效选择有用的未标记样本以扩展训练数据集。在三个标准数据库上的实验结果证明了所提出的IALDL的可行性和有效性。

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