KL-Divergence-Based Region Proposal Network for Object Detection
This work addresses object detection for computer vision applications, offering an incremental improvement by refining region proposal networks.
The paper tackles the problem of region proposal learning in object detection by proposing a method that incorporates bounding box offset uncertainty into the objectness score, redefining it as a KL-divergence minimization problem. It achieves 2.6% and 2.0% AP improvements on MS COCO test-dev with Faster R-CNN and R-FCN backbones, respectively.
The learning of the region proposal in object detection using the deep neural networks (DNN) is divided into two tasks: binary classification and bounding box regression task. However, traditional RPN (Region Proposal Network) defines these two tasks as different problems, and they are trained independently. In this paper, we propose a new region proposal learning method that considers the bounding box offset's uncertainty in the objectness score. Our method redefines RPN to a problem of minimizing the KL-divergence, difference between the two probability distributions. We applied KL-RPN, which performs region proposal using KL-Divergence, to the existing two-stage object detection framework and showed that it can improve the performance of the existing method. Experiments show that it achieves 2.6% and 2.0% AP improvements on MS COCO test-dev in Faster R-CNN with VGG-16 and R-FCN with ResNet-101 backbone, respectively.