Proximity Priors for Variational Semantic Segmentation and Recognition
Title | Proximity Priors for Variational Semantic Segmentation and Recognition |
Publication Type | Conference Paper |
Year of Publication | 2013 |
Authors | Bergbauer, J., Nieuwenhuis C., Souiai M., & Cremers D. |
Other Numbers | 3624 |
Abstract | In this paper, we introduce the concept of proximity priors into semantic segmentation in order to discourage thepresence of certain object classes (such as sheep andwolf ) in the vicinity of each other. Vicinity encompasses spatial distance as well as specific spatial directionssimultaneously, e.g. plates are found directly above tables, but do not fly over them. In this sense, our approachgeneralizes the co-occurrence prior by Ladickyet al. [3], which does not incorporate spatial information at all, andthe non-metric label distance prior by Strekalovskiyet al. [11], which only takes directly neighboring pixels intoaccount and often hallucinates ghost regions. We formulate a convex energy minimization problem with an exactrelaxation, which can be globally optimized. Results onthe MSRC benchmark show that the proposed approach reduces the number of mislabeled objects compared to previous co-occurrence approaches. |
Acknowledgment | This work was partially funded by the Deutscher Akademischer Austausch Dienst (DAAD) through a postdoctoral fellowship. |
URL | http://www.icsi.berkeley.edu/pubs/vision/proximitypriors13.pdf |
Bibliographic Notes | Proceedings of the Workshop on Graphical Models for Scene Understanding at the International Conference on Computer Vision 2013 (ICCV 2013), Sydney, Australia |
Abbreviated Authors | J. Bergbauer, C. Nieuwenhuis, M. Souiai, and D. Cremers |
ICSI Research Group | Vision |
ICSI Publication Type | Article in conference proceedings |