Deep learning for class-generic object detection

Brody Huval, Adam Coates, Andrew Ng

Decision: submitted, no decision

Abstract: We investigate the use of deep neural networks for the 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% performance increase on the ImageNet recognition challenge.