DeepAI AI Chat
Log In Sign Up

KL-Divergence-Based Region Proposal Network for Object Detection

by   Geonseok Seo, et al.

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 Faster R-CNN with VGG-16 and R-FCN with ResNet-101 backbone, respectively.


page 1

page 2


F2DNet: Fast Focal Detection Network for Pedestrian Detection

Two-stage detectors are state-of-the-art in object detection as well as ...

WSOD^2: Learning Bottom-up and Top-down Objectness Distillation for Weakly-supervised Object Detection

We study on weakly-supervised object detection (WSOD) which plays a vita...

Interpretable R-CNN

This paper presents a method of learning qualitatively interpretable mod...

Detecting Lesion Bounding Ellipses With Gaussian Proposal Networks

Lesions characterized by computed tomography (CT) scans, are arguably of...

AttentionNet: Aggregating Weak Directions for Accurate Object Detection

We present a novel detection method using a deep convolutional neural ne...

YOLO – You only look 10647 times

With this work we are explaining the "You Only Look Once" (YOLO) single-...

Conifer Seedling Detection in UAV-Imagery with RGB-Depth Information

Monitoring of reforestation is currently being considerably streamlined ...