You are here

IMPROVING SPATIAL CODIFICATION IN SEMANTIC SEGMENTATION

Authors: 

Carles Ventura, Xavier Giro ́-i-Nieto, Vero ́nica Vilaplana, Kevin McGuinness, Ferran Marques, Noel O'Connor

Publication Type: 
Refereed Conference Meeting Proceeding
Abstract: 
This paper explores novel approaches for improving the spatial cod- ification 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 intermedi- ate 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.
Conference Name: 
IEEE Intl Conf on Image Processing
Digital Object Identifer (DOI): 
10.NA
Publication Date: 
27/09/2015
Conference Location: 
Canada
Research Group: 
Institution: 
Dublin City University (DCU)
Open access repository: 
Yes