首页> 外文期刊>EURASIP journal on image and video processing >Per-Sample Multiple Kernel Approach for Visual Concept Learning
【24h】

Per-Sample Multiple Kernel Approach for Visual Concept Learning

机译:视觉概念学习的每样本多核方法

获取原文
           

摘要

Learning visual concepts from images is an important yet challenging problem in computer vision and multimedia research areas. Multiple kernel learning (MKL) methods have shown great advantages in visual concept learning. As a visual concept often exhibits great appearance variance, a canonical MKL approach may not generate satisfactory results when a uniform kernel combination is applied over the input space. In this paper, we propose a per-sample multiple kernel learning (PS-MKL) approach to take into account intraclass diversity for improving discrimination. PS-MKL determines sample-wise kernel weights according to kernel functions and training samples. Kernel weights as well as kernel-based classifiers are jointly learned. For efficient learning, PS-MKL employs a sample selection strategy. Extensive experiments are carried out over three benchmarking datasets of different characteristics including Caltech101, WikipediaMM, and Pascal VOC'07. PS-MKL has achieved encouraging performance, comparable to the state of the art, which has outperformed a canonical MKL.
机译:从图像中学习视觉概念是计算机视觉和多媒体研究领域中一个重要但具有挑战性的问题。在视觉概念学习中,多核学习(MKL)方法已显示出巨大的优势。由于视觉概念经常表现出很大的外观差异,因此当在输入空间上应用统一的内核组合时,规范的MKL方法可能无法产生令人满意的结果。在本文中,我们提出了一种基于样本的多核学习(PS-MKL)方法,以考虑类内多样性来改善歧视。 PS-MKL根据内核功能和训练样本确定按样本的内核权重。共同学习内核权重以及基于内核的分类器。为了有效学习,PS-MKL采用了样本选择策略。在三个具有不同特征的基准测试数据集上进行了广泛的实验,包括Caltech101,WikipediaMM和Pascal VOC'07。 PS-MKL取得了令人鼓舞的性能,可媲美最新的MKL,其性能优于标准MKL。

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