21 July 2017 Weakly supervised semantic segmentation using fore-background priors
Author Affiliations +
Proceedings Volume 10420, Ninth International Conference on Digital Image Processing (ICDIP 2017); 104204V (2017) https://doi.org/10.1117/12.2281687
Event: Ninth International Conference on Digital Image Processing (ICDIP 2017), 2017, Hong Kong, China
Abstract
Weakly-supervised semantic segmentation is a challenge in the field of computer vision. Most previous works utilize the labels of the whole training set and thereby need the construction of a relationship graph about image labels, thus result in expensive computation. In this study, we tackle this problem from a different perspective. We proposed a novel semantic segmentation algorithm based on background priors, which avoids the construction of a huge graph in whole training dataset. Specifically, a random forest classifier is obtained using weakly supervised training data .Then semantic texton forest (STF) feature is extracted from image superpixels. Finally, a CRF based optimization algorithm is proposed. The unary potential of CRF derived from the outputting probability of random forest classifier and the robust saliency map as background prior. Experiments on the MSRC21 dataset show that the new algorithm outperforms some previous influential weakly-supervised segmentation algorithms. Furthermore, the use of efficient decision forests classifier and parallel computing of saliency map significantly accelerates the implementation.
© (2017) COPYRIGHT Society of Photo-Optical Instrumentation Engineers (SPIE). Downloading of the abstract is permitted for personal use only.
Zheng Han, Zhitao Xiao, Mingjun Yu, "Weakly supervised semantic segmentation using fore-background priors", Proc. SPIE 10420, Ninth International Conference on Digital Image Processing (ICDIP 2017), 104204V (21 July 2017); doi: 10.1117/12.2281687; https://doi.org/10.1117/12.2281687
PROCEEDINGS
8 PAGES


SHARE
Back to Top