Publications
Detailed Information
KL-DIVERGENCE-BASED REGION PROPOSAL NETWORK FOR OBJECT DETECTION
Cited 2 time in
Web of Science
Cited 5 time in Scopus
- Authors
- Issue Date
- 2020-10
- Publisher
- IEEE
- Citation
- 2020 IEEE INTERNATIONAL CONFERENCE ON IMAGE PROCESSING (ICIP), Vol.2020-October, pp.2001-2005
- Abstract
- 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.
- ISSN
- 1522-4880
- Files in This Item:
- There are no files associated with this item.
Related Researcher
- Graduate School of Convergence Science & Technology
- Department of Intelligence and Information
Item View & Download Count
Items in S-Space are protected by copyright, with all rights reserved, unless otherwise indicated.