Sciweavers

Share
CVPR
2010
IEEE

Towards Weakly Supervised Semantic Segmentation by Means of Multiple Instance and Multitask Learning.

9 years 9 months ago
Towards Weakly Supervised Semantic Segmentation by Means of Multiple Instance and Multitask Learning.
We address the task of learning a semantic segmentation from weakly supervised data. Our aim is to devise a system that predicts an object label for each pixel by making use of only image level labels during training – the information whether a certain object is present or not in the image. Such coarse tagging of images is faster and easier to obtain as opposed to the tedious task of pixelwise labeling required in state of the art systems. We cast this task naturally as a multiple instance learning (MIL) problem. We use Semantic Texton Forest (STF) as the basic framework and extend it for the MIL setting. We make use of multitask learning (MTL) to regularize our solution. Here, an external task of geometric context estimation is used to improve on the task of semantic segmentation. We report experimental results on the MSRC21 and the very challenging VOC2007 datasets. On MSRC21 dataset we are able, by using 276 weakly labeled images, to achieve the performance of a supervised STF tr...
Alexander Vezhnevets, Joachim Buhmann
Added 17 Apr 2010
Updated 14 May 2010
Type Conference
Year 2010
Where CVPR
Authors Alexander Vezhnevets, Joachim Buhmann
Comments (0)
books