English

G-CNN: an Iterative Grid Based Object Detector

Computer Vision and Pattern Recognition 2016-04-27 v2

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.

Keywords

Cite

@article{arxiv.1512.07729,
  title  = {G-CNN: an Iterative Grid Based Object Detector},
  author = {Mahyar Najibi and Mohammad Rastegari and Larry S. Davis},
  journal= {arXiv preprint arXiv:1512.07729},
  year   = {2016}
}

Comments

To appear in Proceedings of IEEE Conference on Computer Vision and Pattern Recognition (CVPR), 2016. (Spotlight)

R2 v1 2026-06-22T12:17:23.065Z