G-CNN: An Iterative Grid Based Object Detector

• Published in: 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR) pp. 2369 - 2377
• Main Authors: Najibi, Mahyar, Rastegari, Mohammad, Davis, Larry S.
• Format: Conference Proceeding
• Language: English
• Published: IEEE 01.06.2016
• Subjects: Computer architecture; Detectors; Iterative methods; Object detection; Proposals; Strain; Training
• ISSN: 1063-6919
• DOI: 10.1109/CVPR.2016.260

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.