Segmentation Driven Object Detection with Fisher Vectors

Ramazan Gokberk Cinbis; Jakob Verbeek; Cordelia Schmid

Segmentation Driven Object Detection with Fisher Vectors

Ramazan Gokberk Cinbis ¹ Jakob Verbeek ¹ Cordelia Schmid ¹

1 LEAR - Learning and recognition in vision

Inria Grenoble - Rhône-Alpes, LJK - Laboratoire Jean Kuntzmann, INPG - Institut National Polytechnique de Grenoble

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 VOC 2007 and 2010 datasets show that our detector improves over the current state-of-the-art detection results.

Keywords : object detection Fisher vectors

Document type :

Conference papers

Domain :

Computer Science [cs] / Computer Vision and Pattern Recognition [cs.CV]

Complete list of metadatas

https://hal.inria.fr/hal-00873134
Contributor : Thoth Team <>
Submitted on : Monday, February 10, 2014 - 4:12:21 PM
Last modification on : Tuesday, March 12, 2019 - 5:20:03 PM
Long-term archiving on : Sunday, April 9, 2017 - 10:18:10 AM

Segmentation Driven Object Detection with Fisher Vectors

Files

Identifiers

Collections

Citation

Export

Metrics

3208

4067

Contact

Segmentation Driven Object Detection with Fisher Vectors

Files

Identifiers

Collections

Citation

Export

Share

Metrics

3208

4067

Contact