Learning Object Relationships
via Graph-based Context Model



In this paper, we propose a novel framework for modeling image-dependent contextual relationships using graph-based context model. This approach enables us to selectively utilize the contextual relationships suitable for an input query image. We introduce a context link view of contextual knowledge, where the relationship between a pair of annotated regions is represented as a context link on a similarity graph of regions. Link analysis techniques are used to estimate the pairwise context scores of all pairs of unlabeled regions in the input image. Our system integrates the learned context scores into a Markov Random Field (MRF) framework in the form of pairwise cost and infers the semantic segmentation result by MRF optimization. Experimental results on object class segmentation show that the proposed graph-based context model outperforms the current state-of-the-art methods.



CVPR 2012 paper


CVPR 2012 poster


CVPR 2012 code

SiftFlow dataset

We achieved:

ProposedProposed with smoothness
Pixelwise Accuracy77.5378.22
Classwise Accuracy33.0232.78

(Note that these differ slightly from the original paper)

Entire result images