Segmentation Driven Object Detection with Fisher Vectors

Ramazan Gokberk Cinbis, Jakob Verbeek, Cordelia Schmid; Proceedings of the IEEE International Conference on Computer Vision (ICCV), 2013, pp. 2968-2975

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.

Related Material


[pdf]
[bibtex]
@InProceedings{Cinbis_2013_ICCV,
author = {Gokberk Cinbis, Ramazan and Verbeek, Jakob and Schmid, Cordelia},
title = {Segmentation Driven Object Detection with Fisher Vectors},
booktitle = {Proceedings of the IEEE International Conference on Computer Vision (ICCV)},
month = {December},
year = {2013}
}