Segmentation Driven Object Detection with Fisher Vectors

Creative Commons License

Cinbiş R. G., Verbeek J., Schmid C.

IEEE International Conference on Computer Vision (ICCV), Sydney, Australia, 1 - 08 December 2013, pp.2968-2975 identifier identifier

  • Publication Type: Conference Paper / Full Text
  • Volume:
  • Doi Number: 10.1109/iccv.2013.369
  • City: Sydney
  • Country: Australia
  • Page Numbers: pp.2968-2975
  • Middle East Technical University Affiliated: No

Abstract

We present an object detection system based on the Fisher vector (FV) image representation computed over SIFT and color descriptors. For computational and storage efficiency, we use a recent segmentation-based method to generate class-independent object detection hypotheses, in combination with data compression techniques. Our main contribution is a method to produce tentative object segmentation masks to suppress background clutter in the features. Re-weighting the local image features based on these masks is shown to improve object detection significantly. We also exploit contextual features in the form of a full-image FV descriptor, and an inter-category rescoring mechanism. Our experiments on the PASCAL VOC 2007 and 2010 datasets show that our detector improves over the current state-of-the-art detection results.