Multiple-Instance Learning from Multiple Perspectives: Combining Models for Multiple-Instance Learning
Abstract
Multiple-Instance learning (MIL), which relaxes training annotation granularity from instance level to instance collection (bag) level by applying bag concept, obtains increasing attentions from computer vision community. Due to its flexible annotation mechanism, MIL has been naturally utilized on a variety of computer vision problems. And numerous models have been proposed, each of which is ingeniously designed to catch certain characteristics of MIL. However different models only perform well on certain tasks, and further improvement can hardly be achieved.
Cite
Text
Zhang et al. "Multiple-Instance Learning from Multiple Perspectives: Combining Models for Multiple-Instance Learning." IEEE/CVF Winter Conference on Applications of Computer Vision, 2012. doi:10.1109/WACV.2012.6163044Markdown
[Zhang et al. "Multiple-Instance Learning from Multiple Perspectives: Combining Models for Multiple-Instance Learning." IEEE/CVF Winter Conference on Applications of Computer Vision, 2012.](https://mlanthology.org/wacv/2012/zhang2012wacv-multiple/) doi:10.1109/WACV.2012.6163044BibTeX
@inproceedings{zhang2012wacv-multiple,
title = {{Multiple-Instance Learning from Multiple Perspectives: Combining Models for Multiple-Instance Learning}},
author = {Zhang, Bang and Wang, Yang and Wang, Wei},
booktitle = {IEEE/CVF Winter Conference on Applications of Computer Vision},
year = {2012},
pages = {481-487},
doi = {10.1109/WACV.2012.6163044},
url = {https://mlanthology.org/wacv/2012/zhang2012wacv-multiple/}
}