Abstract
We introduce G-CNN, an object detection techniquebased on CNNs which works without proposal algorithms.G-CNN starts with a multi-scale grid of fixed boundingboxes. We train a regressor to move and scale elementsof 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 makesdetection faster by removing the object proposal stage aswell as reducing the number of boxes to be processed.