article · 2013
DIVVALA et al.: OBJECT INSTANCE SHARING 1 Object Instance Sharing by Enhanced Bounding Box Correspondence
Santosh K. Divvala, Alexei A. Efros, Martial Hebert
Cited by 0Abstract and details only
Abstract
Most contemporary object detection approaches assume each object instance in the training data to be uniquely represented by a single bounding box. In this paper, we go beyond this conventional view by allowing an object instance to be described by multiple bounding boxes. The new bounding box annotations are determined based on the alignment of an object instance with the other training instances in the dataset. Our proposal enables the training data to be reused multiple times for training richer multi-component category models. We operationalize this idea by two complementary operations: bounding box shrinking, which finds subregions of an object instance that could be shared; and bounding box enlarging, which enlarges object instances to include local contextual cues. We empirically validate our approach on the PASCAL VOC detection dataset. 1
Cite this paper
Divvala, S. K., Efros, A. A., & Hebert, M. (2013). DIVVALA et al.: OBJECT INSTANCE SHARING 1 Object Instance Sharing by Enhanced Bounding Box Correspondence.
Divvala, Santosh K., et al. “DIVVALA et al.: OBJECT INSTANCE SHARING 1 Object Instance Sharing by Enhanced Bounding Box Correspondence.” 2013.
Divvala, Santosh K., Alexei A. Efros, and Martial Hebert. 2013. “DIVVALA et al.: OBJECT INSTANCE SHARING 1 Object Instance Sharing by Enhanced Bounding Box Correspondence.”
Divvala, S.K., Efros, A.A. and Hebert, M. (2013) ‘DIVVALA et al.: OBJECT INSTANCE SHARING 1 Object Instance Sharing by Enhanced Bounding Box Correspondence’.
@article{divvala2013divvala,
title = {{DIVVALA et al.: OBJECT INSTANCE SHARING 1 Object Instance Sharing by Enhanced Bounding Box Correspondence}},
author = {Divvala, Santosh K. and Efros, Alexei A. and Hebert, Martial},
year = {2013}
}Made from the index record. Check names, capitalisation and page numbers against the paper. Need another style? AI for Research has over 10,000.