@InProceedings{JaumeAmores2010,
author="Jaume Amores
and David Geronimo
and Antonio Lopez",
title="Multiple instance and active learning for weakly-supervised object-class segmentation",
booktitle="3rd IEEE International Conference on Machine Vision",
year="2010",
optkeywords="Multiple Instance Learning",
optkeywords="Active Learning",
optkeywords="Object-class segmentation.",
abstract="In object-class segmentation, one of the most tedious tasks is to manually segment many object examples in order to learn a model of the object category. Yet, there has been little research on reducing the degree of manual annotation for object-class segmentation. In this work we explore alternative strategies which do not require full manual segmentation of the object in the training set. In particular, we study the use of bounding boxes as a coarser and much cheaper form of segmentation and we perform a comparative study of several Multiple-Instance Learning techniques that allow to obtain a model with this type of weak annotation. We show that some of these methods can be competitive, when used with coarse segmentations, with methods that require full manual segmentation of the objects. Furthermore, we show how to use active learning combined with this weakly supervised strategy. As we see, this strategy permits to reduce the amount of annotation and optimize the number of examples that require full manual segmentation in the training set.",
optnote="ADAS",
optnote="exported from refbase (http://refbase.cvc.uab.es/show.php?record=1429), last updated on Fri, 21 Feb 2014 15:51:55 +0100",
file=":http://refbase.cvc.uab.es/files/AGL2010b.pdf:PDF"
}