Improving Spatial Codification in Semantic Segmentation
Abstract
This paper explores novel approaches for improving the spatial codification for the pooling of local descriptors to solve the semantic segmentation problem. We propose to partition the image into three regions for each object to be described: Figure, Border and Ground. This partition aims at minimizing the influence of the image context on the object description and vice versa by introducing an intermediate zone around the object contour. Furthermore, we also propose a richer visual descriptor of the object by applying a Spatial Pyramid over the Figure region. Two novel Spatial Pyramid configurations are explored: Cartesian-based and crown-based Spatial Pyramids. We test these approaches with state-of-the-art techniques and show that they improve the Figure-Ground based pooling in the Pascal VOC 2011 and 2012 semantic segmentation challenges.
Cite
@article{arxiv.1505.07409,
title = {Improving Spatial Codification in Semantic Segmentation},
author = {Carles Ventura and Xavier Giró-i-Nieto and Verónica Vilaplana and Kevin McGuinness and Ferran Marqués and Noel E. O'Connor},
journal= {arXiv preprint arXiv:1505.07409},
year = {2016}
}
Comments
Paper accepted at the IEEE International Conference on Image Processing, ICIP 2015. Quebec City, 27-30 September. Project page: https://imatge.upc.edu/web/publications/improving-spatial-codification-semantic-segmentation