论文阅读 (三):An empirical study on image bag generators for multi-instance learning (2016)

文章目录

前言

  数据的生成是门艺术,文章地址:
  https://link.springer.com/article/10.1007/s10994-016-5560-1

摘要

  要点如下:

  1. 对九种包生成器 (bag generators)进行了比较学习,即Row1, SB1, SBN1, Blobworld2, kkk-meansSeg3, WavSeg4, JSEG-bag5, LBP6SIFT7
  2. 结论:
    2.1 采用密度采样 (dense sample)策略的包生成器效果更优;
    2.2 标准多示例假设不适用于图像分类任务 (这句话存疑)。

1 包生成器

  根据包生成器是否可以区分图像的语义成分 (semantic components),将其分为non-segmentation 包生成器segmentation 包生成器
  1)non-segmentation 包生成器Row, SB, SBN
  2)segmentation 包生成器Blobworld, kkk-meansSeg, WavSeg, JSEG-bag
  3)不属于以上,即local descriptorsLBP6, SIFT
  简单说来,non-segmentation就是划分方式与图像无关;local descriptors用于计算机视觉中描述某区域外观或形状的不同特征。

1.1 Row

  简单说来就是一行一个实例。

1.1.1 详细步骤

  1)给定任意一张图片,本文选择的是COREL数据源中的Tiger数据集。
论文阅读 (三):An empirical study on image bag generators for multi-instance learning (2016)
  2)滤波,‘mean’, ‘Gaussian’, ‘median’, 'bilateral’四种滤波的结果如下,此处默认选择Gaussian滤波:
论文阅读 (三):An empirical study on image bag generators for multi-instance learning (2016)
  3)更改图像大小,默认设置为8×88 \times 88×8:
论文阅读 (三):An empirical study on image bag generators for multi-instance learning (2016)
  4)

1.1.2 完整代码

2 支持代码


  1. Maron, O., & Ratan, A. L. (2001). Multiple-instance learning for natural scene classification. In Proceedings of 18th international conference on machine learning. Williamstown, MA, pp. 425–432. ↩︎ ↩︎ ↩︎

  2. Carson,C.,Belongie,S.,Greenspan,H.,&Malik,J.(2002).Blobworld: Image segmentation using expectation- maximization and its application to image querying.IEEE Transaction son Pattern Analysis and Machine Intelligence, 24(8), 1026–1038. ↩︎

  3. Zhang,Q.,Goldman,S.A.,Yu,W.,&Fritts,J.E.(2002).Content-based image retrieval using multiple-instance learning. In Proceedings of 19th international conference on machine learning. Sydney, Australia, pp. 682–689. ↩︎

  4. Zhang,C.C.,Chen,S.,&Shyu,M.(2004).Multiple object retrieval for image data bases using multiple instance learning and relevance feedback. In Proceedings of IEEE international conference on multimedia and expo. Sydney, Australia, pp. 775–778. ↩︎

  5. Liu, W., Xu, W. D., Li, L. H., & Li, G. L. (2008). Two new bag generators with multi-instance learning for image retrieval. In Proceedings of 3rd IEEE conference on industrial electronics and applications. Singapore, pp. 255 – 259. ↩︎

  6. Ojala, T., Pietikäinen, M., & Mäenpää, T. (2002). Multiresolution gray-scale and rotation invariant texture classification with local binary patterns.IEEE Transaction son Pattern Analysis and Machine Intelligence, 24(7), 971–987. ↩︎

  7. Lowe, D. G. (2004). Distinctive image features from scale-invariant keypoints. International Journal of Computer Vision, 60(2), 91–110. ↩︎

上一篇:python之unittest框架实现接口测试实例


下一篇:Efficient Segmentation: Learning Downsampling Near Semantic Boundaries学习语义分割边界附近的下采样