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

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, $k$-meansSeg³, WavSeg⁴, JSEG-bag⁵, LBP⁶和SIFT⁷。
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 包生成器和segmentation 包生成器。
  1）non-segmentation 包生成器：Row, SB, SBN；
  2）segmentation 包生成器：Blobworld, $k$-meansSeg, WavSeg, JSEG-bag；
  3）不属于以上，即local descriptors：LBP6, 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

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。

  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：

  3）更改图像大小，默认设置为 $8 \times 8$：

  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. ↩︎

   扫描二维码关注公众号，回复： 11171604 查看本文章

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. ↩︎