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.
@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)