Proximity priors for variational semantic segmentation and recognition
Bergbauer J, Nieuwenhuis C, Souiai M, Cremers D (2013)
Publication Type: Conference contribution
Publication year: 2013
Publisher: Institute of Electrical and Electronics Engineers Inc.
Pages Range: 15-21
Conference Proceedings Title: Proceedings of the IEEE International Conference on Computer Vision
Event location: AUS
ISBN: 9781479930227
Abstract
In this paper, we introduce the concept of proximity priors into semantic segmentation in order to discourage the presence of certain object classes (such as 'sheep' and 'wolf') 'in the vicinity' of each other. 'Vicinity' encompasses spatial distance as well as specific spatial directions simultaneously, e.g. 'plates' are found directly above 'tables', but do not fly over them. In this sense, our approach generalizes the co-occurrence prior by Lad icky et al., which does not incorporate spatial information at all, and the non-metric label distance prior by Strekalovskiy et al., which only takes directly neighboring pixels into account and often hallucinates ghost regions. We formulate a convex energy minimization problem with an exact relaxation, which can be globally optimized. Results on the MSRC benchmark show that the proposed approach reduces the number of mislabeled objects compared to previous co-occurrence approaches. © 2013 IEEE.
Involved external institutions
Technische Universität München (TUM)
Germany (DE)
University of California, Berkeley
United States (USA) (US)
Germany (DE)
University of California, Berkeley
United States (USA) (US)
How to cite
APA:
Bergbauer, J., Nieuwenhuis, C., Souiai, M., & Cremers, D. (2013). Proximity priors for variational semantic segmentation and recognition. In Proceedings of the IEEE International Conference on Computer Vision (pp. 15-21). AUS: Institute of Electrical and Electronics Engineers Inc..
MLA:
Bergbauer, Julia, et al. "Proximity priors for variational semantic segmentation and recognition." Proceedings of the 2013 14th IEEE International Conference on Computer Vision Workshops, ICCVW 2013, AUS Institute of Electrical and Electronics Engineers Inc., 2013. 15-21.
BibTeX: Download