Proximity Priors for Variational Semantic Segmentation and Recognition

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. [3], which does not incorporate spatial information at all, and the non-metric label distance prior by Strekalovskiy et al. [11], 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.