A copy of this work was available on the public web and has been preserved in the Wayback Machine. The capture dates from 2016; you can also visit the original URL.
The file type is
Over the past years, Multiple Instance Learning (MIL) has proven to be an effective framework for learning with weakly labeled data. Applications of MIL to object detection, however, were limited to handling the uncertainties of manual annotations. In this paper, we propose a new MIL method for object detection that is capable of handling the noisier automatically obtained annotations. Our approach consists in first obtaining confidence estimates over the label space and, second, incorporatingdoi:10.1109/cvpr.2014.312 dblp:conf/cvpr/AliS14 fatcat:g5siops355gttca73ltrxoy4yi