Kl-Divergence-Based Region Proposal Network For Object Detection

  title={Kl-Divergence-Based Region Proposal Network For Object Detection},
  author={Geonseok Seo and Jaeyoung Yoo and Jaeseok Choi and Nojun Kwak},
  journal={2020 IEEE International Conference on Image Processing (ICIP)},
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… 

Figures and Tables from this paper

Dynamic Iterative Refinement for Efficient 3D Hand Pose Estimation
A tiny deep neural network of which partial layers are recursively exploited for refining its previous estimations, which consistently outperforms state-of-the-art 2D/3D hand pose estimation approaches in terms of both accuracy and efficiency for widely used benchmarks.


Faster R-CNN: Towards Real-Time Object Detection with Region Proposal Networks
This work introduces a Region Proposal Network (RPN) that shares full-image convolutional features with the detection network, thus enabling nearly cost-free region proposals and further merge RPN and Fast R-CNN into a single network by sharing their convolutionAL features.
Bounding Box Regression With Uncertainty for Accurate Object Detection
A novel bounding box regression loss that greatly improves the localization accuracies of various architectures with nearly no additional computation and allows us to merge neighboring bounding boxes during non-maximum suppression (NMS), which further improves the globalization performance.
R-FCN: Object Detection via Region-based Fully Convolutional Networks
This work presents region-based, fully convolutional networks for accurate and efficient object detection, and proposes position-sensitive score maps to address a dilemma between translation-invariance in image classification and translation-variance in object detection.
Rich Feature Hierarchies for Accurate Object Detection and Semantic Segmentation
This paper proposes a simple and scalable detection algorithm that improves mean average precision (mAP) by more than 30% relative to the previous best result on VOC 2012 -- achieving a mAP of 53.3%.
Grid R-CNN
This paper proposes a novel object detection framework named Grid R-CNN, which adopts a grid guided localization mechanism for accurate object detection, and designs a multi-point supervision formulation to encode more clues in order to reduce the impact of inaccurate prediction of specific points.
Cascade R-CNN: Delving Into High Quality Object Detection
A simple implementation of the Cascade R-CNN is shown to surpass all single-model object detectors on the challenging COCO dataset, and experiments show that it is widely applicable across detector architectures, achieving consistent gains independently of the baseline detector strength.
Feature Pyramid Networks for Object Detection
This paper exploits the inherent multi-scale, pyramidal hierarchy of deep convolutional networks to construct feature pyramids with marginal extra cost and achieves state-of-the-art single-model results on the COCO detection benchmark without bells and whistles.
SINet: A Scale-Insensitive Convolutional Neural Network for Fast Vehicle Detection
A scale-insensitive convolutional neural network (SINet) for fast detecting vehicles with a large variance of scales is presented and a context-aware RoI pooling to maintain the contextual information and original structure of small scale objects is presented.
Occluded Pedestrian Detection Through Guided Attention in CNNs
A simple and compact method based on the FasterRCNN architecture for occluded pedestrian detection with significant improvement on the heavy occlusion subset, and on CityPersons and on Caltech it outperform the state-of-the-art method by 4pp.
Detecting Faces Using Region-based Fully Convolutional Networks
A region-based face detector applying deep networks in a fully convolutional fashion, named Face R-FCN, based on Region-based Fully Convolutional Networks (R- FCN), which achieves superior performance over state-of-the-arts benchmarks.