期刊文献+

Multi-task multi-label multiple instance learning

Multi-task multi-label multiple instance learning
原文传递
导出
摘要 For automatic object detection tasks,large amounts of training images are usually labeled to achieve more reliable training of the object classifiers;this is cost-expensive since it requires hiring professionals to label large-scale training images.When a large number of object classes come into view,the issue of obtaining a large enough amount of the labeled training images becomes more critical.There are three potential solutions to reduce the burden for image labeling:(1) allowing people to provide the object labels loosely at the image level rather than at the object level(e.g.,loosely-tagged images without identifying the exact object locations in the images) ;(2) harnessing large-scale collaboratively-tagged images that are available on the Internet;and,(3) developing new machine learning algorithms that can directly leverage large-scale collaboratively-or loosely-tagged images for achieving more eective training of a large number of object classifiers.Based on these observations,a multi-task multi-label multiple instance learning(MTML-MIL) algorithm is developed in this paper by leveraging both inter-object correlations and large-scale loosely-labeled images for object classifier training.By seamlessly integrating multi-task learning,multi-label learning,and multiple instance learning,our MTML-MIL algorithm can achieve more accurate training of a large number of inter-related object classifiers(where an object network is constructed for determining the inter-related learning tasks directly in the feature space rather than in the label space) .Our experimental results have shown that our MTML-MIL algorithm can achieve higher detection accuracy rates for automatic object detection. For automatic object detection tasks,large amounts of training images are usually labeled to achieve more reliable training of the object classifiers;this is cost-expensive since it requires hiring professionals to label large-scale training images.When a large number of object classes come into view,the issue of obtaining a large enough amount of the labeled training images becomes more critical.There are three potential solutions to reduce the burden for image labeling:(1) allowing people to provide the object labels loosely at the image level rather than at the object level(e.g.,loosely-tagged images without identifying the exact object locations in the images) ;(2) harnessing large-scale collaboratively-tagged images that are available on the Internet;and,(3) developing new machine learning algorithms that can directly leverage large-scale collaboratively-or loosely-tagged images for achieving more eective training of a large number of object classifiers.Based on these observations,a multi-task multi-label multiple instance learning(MTML-MIL) algorithm is developed in this paper by leveraging both inter-object correlations and large-scale loosely-labeled images for object classifier training.By seamlessly integrating multi-task learning,multi-label learning,and multiple instance learning,our MTML-MIL algorithm can achieve more accurate training of a large number of inter-related object classifiers(where an object network is constructed for determining the inter-related learning tasks directly in the feature space rather than in the label space) .Our experimental results have shown that our MTML-MIL algorithm can achieve higher detection accuracy rates for automatic object detection.
出处 《Journal of Zhejiang University-Science C(Computers and Electronics)》 SCIE EI 2010年第11期860-871,共12页 浙江大学学报C辑(计算机与电子(英文版)
关键词 Object network Loosely tagged images Multi-task learning Multi-label learning Multiple instance learning Object network, Loosely tagged images, Multi-task learning, Multi-label learning, Multiple instance learning
  • 相关文献

参考文献28

  • 1Boutell, 2004 tion. M.R., Luo, J., Shen, X., Brown, C.M., Learning multi-label scene classifica- Pattern Recogn., 37(9):1757-1771. [doi:10 1016/j.patcog.2004.03.009].
  • 2Chen, Y., Bi, J., Wang, J.Z., 2006. MILES: multiple instance learning via embedded instance selection. IEEE Trans. PAMI, 28(12):1931-1947. [doi:10.1109/TPAMI.2006.248].
  • 3Deng, Y., Manjunath, B.S., 1999. Color Image Segmentation. IEEE CVPR, p.2446-2451. [doi: 10.1109/CVPR. 1999.784719].
  • 4Evgeniou, T., Micchelli, C.A., Pontil, M., 2005. Learning multiple tasks with kernel methods. J. Mach. Learn. Res., 6:615-637.
  • 5Fan, J., Gao, Y., Luo, H., 2004. Multi-Level Annotation of Natural Scenes Using Dominant Image Components and Semantic Image Concepts. ACM Multimedia, p.540-547. [doi:10.1145/1027527.1027660].
  • 6Fan, J., Luo, H., Gao, Y., Jain, R., 2007. Incorporating concept ontology for hierarchical video classification, annotation and visualization. IEEE Trans. Multimedia, 9(5):939-957. [doi:10.1109/TMM.2007.900143].
  • 7Fan, J., Gao, Y., Luo, H., 2008a. Integrating concept ontology and multi-task learning to achieve more effective classifier training for multi-level image annotation. IEEE Trans. Image Process., 17(3):407- 426. [doi: 10.1109/TIP.2008.916999].
  • 8Fan, J., Gao, Y., Luo, H., Jain, R., 2008b. Mining multi-level image semantics via hierarchical classification IEEE Trans. Multimedia, 10(1):167-187. [doi:10.1109/TMM.2007.911775].
  • 9Fan, J., Shen, Y., Zhou, N., Gao, Y., 2010. Harvesting Large-Scale Weakly-Tagged Image Databases from the Web. IEEE CVPR, p.802-809. [doi:10. 1109/CVPR.2010.5540135].
  • 10Fan, R., Chen, P., Lin, C.J., 2005. Working set selection using the second order information for training SVM. J. Mach. Learn. Res., 6:1889-1918.

相关作者

内容加载中请稍等...

相关机构

内容加载中请稍等...

相关主题

内容加载中请稍等...

浏览历史

内容加载中请稍等...
;
使用帮助 返回顶部