Object Instance Sharing by Enhanced Bounding Box Correspondence
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 align-
ment 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: bound-
ing 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.
"Object Instance Sharing by Enhanced Bounding Box Correspondence"
Santosh K. Divvala, Alexei A. Efros, Martial Hebert
British Machine Vision Conference (BMVC) 2012.