G-CNN: An Iterative Grid Based Object Detector

Abstract

We introduce G-CNN, an object detection technique based on CNNs which works without proposal algorithms. G-CNN starts with a multi-scale grid of fixed bounding boxes. We train a regressor to move and scale elements of the grid towards objects iteratively. G-CNN models the problem of object detection as finding a path from a fixed grid to boxes tightly surrounding the objects. G-CNN with around 180 boxes in a multi-scale grid performs comparably to Fast R-CNN which uses around 2K bounding boxes generated with a proposal technique. This strategy makes detection faster by removing the object proposal stage as well as reducing the number of boxes to be processed.

Cite

Text

Najibi et al. "G-CNN: An Iterative Grid Based Object Detector." Conference on Computer Vision and Pattern Recognition, 2016. doi:10.1109/CVPR.2016.260

Markdown

[Najibi et al. "G-CNN: An Iterative Grid Based Object Detector." Conference on Computer Vision and Pattern Recognition, 2016.](https://mlanthology.org/cvpr/2016/najibi2016cvpr-gcnn/) doi:10.1109/CVPR.2016.260

BibTeX

@inproceedings{najibi2016cvpr-gcnn,
  title     = {{G-CNN: An Iterative Grid Based Object Detector}},
  author    = {Najibi, Mahyar and Rastegari, Mohammad and Davis, Larry S.},
  booktitle = {Conference on Computer Vision and Pattern Recognition},
  year      = {2016},
  doi       = {10.1109/CVPR.2016.260},
  url       = {https://mlanthology.org/cvpr/2016/najibi2016cvpr-gcnn/}
}