Sparse Dictionaries for Semantic Segmentation

  • Lingling Tao
  • Fatih Porikli
  • René Vidal
Conference paper

DOI: 10.1007/978-3-319-10602-1_36

Part of the Lecture Notes in Computer Science book series (LNCS, volume 8693)
Cite this paper as:
Tao L., Porikli F., Vidal R. (2014) Sparse Dictionaries for Semantic Segmentation. In: Fleet D., Pajdla T., Schiele B., Tuytelaars T. (eds) Computer Vision – ECCV 2014. ECCV 2014. Lecture Notes in Computer Science, vol 8693. Springer, Cham

Abstract

A popular trend in semantic segmentation is to use top-down object information to improve bottom-up segmentation. For instance, the classification scores of the Bag of Features (BoF) model for image classification have been used to build a top-down categorization cost in a Conditional Random Field (CRF) model for semantic segmentation. Recent work shows that discriminative sparse dictionary learning (DSDL) can improve upon the unsupervised K-means dictionary learning method used in the BoF model due to the ability of DSDL to capture discriminative features from different classes. However, to the best of our knowledge, DSDL has not been used for building a top-down categorization cost for semantic segmentation. In this paper, we propose a CRF model that incorporates a DSDL based top-down cost for semantic segmentation. We show that the new CRF energy can be minimized using existing efficient discrete optimization techniques. Moreover, we propose a new method for jointly learning the CRF parameters, object classifiers and the visual dictionary. Our experiments demonstrate that by jointly learning these parameters, the feature representation becomes more discriminative and the segmentation performance improves with respect to that of state-of-the-art methods that use unsupervised K-means dictionary learning.

Keywords

discriminative sparse dictionary learning conditional random fields semantic segmentation 

Preview

Unable to display preview. Download preview PDF.

Unable to display preview. Download preview PDF.

Copyright information

© Springer International Publishing Switzerland 2014

Authors and Affiliations

  • Lingling Tao
    • 1
  • Fatih Porikli
    • 2
  • René Vidal
    • 1
  1. 1.Center for Imaging ScienceJohns Hopkins UniversityUSA
  2. 2.Australian National University & NICTA ICTAustralia

Personalised recommendations