Contextual Object Detection using Set-based Classification

Ramazan Gokberk Cinbis 1 Stan Sclaroff 2
1 LEAR - Learning and recognition in vision
Inria Grenoble - Rhône-Alpes, LJK - Laboratoire Jean Kuntzmann, INPG - Institut National Polytechnique de Grenoble
Abstract : We propose a new model for object detection that is based on set representations of the contextual elements. In this formulation, relative spatial locations and relative scores between pairs of detections are considered as sets of unordered items. Directly training classification models on sets of unordered items, where each set can have varying cardinality can be difficult. In order to overcome this problem, we propose SetBoost, a discriminative learning algorithm for building set classifiers. The SetBoost classifiers are trained to rescore detected objects based on object-object and object-scene context. Our method is able to discover composite relationships, as well as intra-class and inter-class spatial relationships between objects. The experimental evidence shows that our set-based formulation performs comparable to or better than existing contextual methods on the SUN and the VOC 2007 benchmark datasets.
Document type :
Conference papers
Complete list of metadatas

Cited literature [24 references]  Display  Hide  Download


https://hal.inria.fr/hal-00756638
Contributor : Thoth Team <>
Submitted on : Friday, November 23, 2012 - 1:54:58 PM
Last modification on : Monday, December 17, 2018 - 11:22:02 AM
Long-term archiving on : Sunday, February 24, 2013 - 3:51:09 AM

Files

setboost_toappear.pdf
Files produced by the author(s)

Identifiers

Collections

Citation

Ramazan Gokberk Cinbis, Stan Sclaroff. Contextual Object Detection using Set-based Classification. ECCV 2012 - European Conference on Computer Vision, Oct 2012, Firenze, Italy. pp.43-57, ⟨10.1007/978-3-642-33783-3_4⟩. ⟨hal-00756638⟩

Share

Metrics

Record views

655

Files downloads

690