Deep learning for class-generic object detection

12/24/2013

∙

by   Brody Huval, et al.

∙

0

∙

share

We investigate the use of deep neural networks for the novel task of class generic object detection. We show that neural networks originally designed for image recognition can be trained to detect objects within images, regardless of their class, including objects for which no bounding box labels have been provided. In addition, we show that bounding box labels yield a 1 increase on the ImageNet recognition challenge.