Optimizing the Relevance-Redundancy Tradeoff for Efficient Semantic Segmentation

Conference paper

DOI: 10.1007/978-3-319-18461-6_20

Part of the Lecture Notes in Computer Science book series (LNCS, volume 9087)
Cite this paper as:
Hazırbaş C., Diebold J., Cremers D. (2015) Optimizing the Relevance-Redundancy Tradeoff for Efficient Semantic Segmentation. In: Aujol JF., Nikolova M., Papadakis N. (eds) Scale Space and Variational Methods in Computer Vision. SSVM 2015. Lecture Notes in Computer Science, vol 9087. Springer, Cham

Abstract

Semantic segmentation aims at jointly computing a segmentation and a semantic labeling of the image plane. The main ingredient is an efficient feature selection strategy. In this work we perform a systematic information-theoretic evaluation of existing features in order to address the question which and how many features are appropriate for an efficient semantic segmentation. To this end, we discuss the tradeoff between relevance and redundancy and present an information-theoretic feature evaluation strategy. Subsequently, we perform a systematic experimental validation which shows that the proposed feature selection strategy provides state-of-the-art semantic segmentations on five semantic segmentation datasets at significantly reduced runtimes. Moreover, it provides a systematic overview of which features are the most relevant for various benchmarks.

Keywords

Feature analysis Feature selection Image segmentation Semantic scene understanding 

Preview

Unable to display preview. Download preview PDF.

Unable to display preview. Download preview PDF.

Copyright information

© Springer International Publishing Switzerland 2015

Authors and Affiliations

  • Caner Hazırbaş
    • 1
  • Julia Diebold
    • 1
  • Daniel Cremers
    • 1
  1. 1.Technical University of MunichMunichGermany

Personalised recommendations