Semantic segmentation with second-order pooling

  • Authors:

  • João Carreira;Rui Caseiro;Jorge Batista;Cristian Sminchisescu

  • Affiliations:

  • Institute of Systems and Robotics, University of Coimbra, Portugal,Faculty of Mathematics and Natural Sciences, University of Bonn, Germany;Institute of Systems and Robotics, University of Coimbra, Portugal;Institute of Systems and Robotics, University of Coimbra, Portugal;Faculty of Mathematics and Natural Sciences, University of Bonn, Germany

  • Venue:
  • ECCV'12 Proceedings of the 12th European conference on Computer Vision - Volume Part VII
  • Year:
  • 2012

Quantified Score

Hi-index 0.00

Visualization

Abstract

Feature extraction, coding and pooling, are important components on many contemporary object recognition paradigms. In this paper we explore novel pooling techniques that encode the second-order statistics of local descriptors inside a region. To achieve this effect, we introduce multiplicative second-order analogues of average and max-pooling that together with appropriate non-linearities lead to state-of-the-art performance on free-form region recognition, without any type of feature coding. Instead of coding, we found that enriching local descriptors with additional image information leads to large performance gains, especially in conjunction with the proposed pooling methodology. We show that second-order pooling over free-form regions produces results superior to those of the winning systems in the Pascal VOC 2011 semantic segmentation challenge, with models that are 20,000 times faster.