Probabilistic Graphlet Cut: Exploiting Spatial Structure Cue for Weakly Supervised Image Segmentation
2013 IEEE Conference on Computer Vision and Pattern Recognition (CVPR) (2013)
Portland, OR, USA
June 23, 2013 to June 28, 2013
DOI Bookmark: http://doi.ieeecomputersociety.org/10.1109/CVPR.2013.249
Weakly supervised image segmentation is a challenging problem in computer vision field. In this paper, we present a new weakly supervised image segmentation algorithm by learning the distribution of spatially structured super pixel sets from image-level labels. Specifically, we first extract graph lets from each image where a graph let is a small-sized graph consisting of super pixels as its nodes and it encapsulates the spatial structure of those super pixels. Then, a manifold embedding algorithm is proposed to transform graph lets of different sizes into equal-length feature vectors. Thereafter, we use GMM to learn the distribution of the post-embedding graph lets. Finally, we propose a novel image segmentation algorithm, called graph let cut, that leverages the learned graph let distribution in measuring the homogeneity of a set of spatially structured super pixels. Experimental results show that the proposed approach outperforms state-of-the-art weakly supervised image segmentation methods, and its performance is comparable to those of the fully supervised segmentation models.
high-order, graphlet, weakly segmentation
L. Zhang, M. Song, Z. Liu, X. Liu, J. Bu and C. Chen, "Probabilistic Graphlet Cut: Exploiting Spatial Structure Cue for Weakly Supervised Image Segmentation," 2013 IEEE Conference on Computer Vision and Pattern Recognition(CVPR), Portland, OR, USA USA, 2013, pp. 1908-1915.