Weakly supervised semantic segmentation with superpixel embedding

Frank Z. Xing, Erik Cambria, Win-Bin Huang, Yang Xu

Abstract

In this paper, we propose to use contexts of superpixels as a prior to improve semantic segmentation by the CRF framework. A graphical model is constructed on over-segmented images. Our main contribution is to take the concept of “superpixel embedding” into consideration, which is formalized as a potential item for optimizing the energy of the whole graph. We also introduce two ways of calculating this embedding potential. Experiments on several popular datasets, e.g., MRSC-21 and PASCAL VOC, illustrate that our approach enhances the performance of a previously proposed segmentation model without embedding. The accuracy results are comparable to some fully supervised methods.
BibTeX
@inproceedings{xing2016weakly,
  author = {Frank Z. Xing and Erik Cambria and Win-Bin Huang and Yang Xu},
  title = {{Weakly supervised semantic segmentation with superpixel embedding}},
  booktitle = {ICIP},
  year = {2016},
  doi = {10.1109/icip.2016.7532562},
}

Loading related content...

Figure