# Improving Spatial Codification in Semantic Segmentation

Source: [Improving Spatial Codification in Semantic Segmentation](<https://www.sota2.com/research/paper/68fa62ea1e209131ce9fbd20>)

Collection index: [llms.txt](<https://www.sota2.com/research/llms.txt>)

Data updated: 2025-10-25T20:29:18.716Z

Authors: Carles Ventura, Xavier Gir\\'o-i-Nieto, Ver\\'onica Vilaplana, Kevin McGuinness, Ferran Marqu\\'es, Noel E. O'Connor

Published: 2015-05-27T17:26:39.000Z

## 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.

## Recorded benchmark results

A research result applies to its stated dataset, split, metric and evaluation configuration. Compare like-for-like settings, preserve the metric's unit and direction, and distinguish paper-reported results from independent reproduction. The best result recorded here is not a claim of exhaustive, current global coverage.

## Original sources and implementation

[Original paper](<https://arxiv.org/abs/1505.07409>)

[PDF](<https://arxiv.org/pdf/1505.07409.pdf>)