G-CNN: an Iterative Grid Based Object Detector
This addresses the speed and efficiency problem in object detection for computer vision applications, offering an incremental improvement over existing methods.
The paper tackles object detection by introducing G-CNN, an iterative grid-based method that eliminates the need for proposal algorithms, achieving comparable performance to Fast R-CNN with around 180 boxes instead of 2K, making detection faster.
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.