Deep Learning for Class-Generic Object Detection
Abstract
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% performance increase on the ImageNet recognition challenge.
Cite
Text
Huval et al. "Deep Learning for Class-Generic Object Detection." International Conference on Learning Representations, 2014.Markdown
[Huval et al. "Deep Learning for Class-Generic Object Detection." International Conference on Learning Representations, 2014.](https://mlanthology.org/iclr/2014/huval2014iclr-deep/)BibTeX
@inproceedings{huval2014iclr-deep,
title = {{Deep Learning for Class-Generic Object Detection}},
author = {Huval, Brody and Coates, Adam and Ng, Andrew Y.},
booktitle = {International Conference on Learning Representations},
year = {2014},
url = {https://mlanthology.org/iclr/2014/huval2014iclr-deep/}
}