Description: The package includes the MATLAB codes of the nine image bag generators algorithms used in our
Machine Learning paper for multi-instance learning. Multi-instance learning (MIL) has been widely used on diverse applications involving complicated data objects such as images, where people use a bag generator to represent an original data object as a bag of instances, and then employ MIL algorithms. Many powerful MIL algorithms have been developed during the past decades, but the bag generators have rarely been studied although they affect the performance seriously. Considering that MIL has been found particularly useful in image tasks, in our paper, we empirically study the utility of nine state-of-the-art image bag generators in the literature, i.e., Row, SB, SBN, k-meansSeg, Blobworld, WavSeg, JSEG-bag, LBP and SIFT. From the 6,923 (9 bag generators, 7 learning algorithms, 4 patch sizes and 43 data sets) configurations of experiments we make two significant new observations: (1) Bag generators with a dense sampling strategy perform better than those with other strategies; (2) The standard MIL assumption of learning algorithms is not suitable for image classification tasks.
References: Xiu-Shen Wei and Zhi-Hua Zhou. An Empirical Study on Image Bag Generators for Multi-Instance Learning. Machine Learning, in press.
ATTN: This packages are free for academic usage. You can run them at your own risk. For other purposes, please contact Prof. Zhi-Hua Zhou (zhouzh.gm@gmail.com).
ATTN2: This packages were developed by Mr. Xiu-Shen Wei (weixs@lamda.nju.edu.cn). For any problem concerning the code, please feel free to contact Mr. Wei.
Download: [
code] (4.19MB)