Sciweavers

Share
ICCV
2011
IEEE

Segmentation as Selective Search for Object Recognition

8 years 2 months ago
Segmentation as Selective Search for Object Recognition
Software available at http://disi.unitn.it/~uijlings or http://koen.me/research/ For object recognition, the current state-of-the-art is based on exhaustive search. However, to enable the use of more expensive features and classifiers and thereby progress beyond the state-of-the-art, a selective search strategy is needed. Therefore, we adapt segmentation as a selective search by reconsidering segmentation: We propose to generate many approximate locations over few and precise object delineations because (1) an object whose location is never generated can not be recognised and (2) appearance and immediate nearby context are most effective for object recognition. Our method is class-independent and is shown to cover 96.7% of all objects in the Pascal VOC 2007 test set using only 1,536 locations per image. Our selective search enables the use of the more expensive bag-of-words method which we use to substantially improve the state-of-the-art by up to 8.5% for 8 out of 20 classes on ...
K van de Sande, J Uijlings, T Gevers, A Smeulders
Added 14 Oct 2011
Updated 22 Dec 2011
Type Conference
Year 2011
Where ICCV
Authors K van de Sande, J Uijlings, T Gevers, A Smeulders
Comments (0)
books