Weighted Feature Pyramid Networks for Object Detection

Feature Pyramid Networks (FPN) is a popular feature extraction. However, FPN and its variants do not investigate the influence of resolution information and semantic information in the object detection. Thus, FPN and its variants cannot detect some objects on challenging images. In this paper, based...

Full description

Saved in:
Bibliographic Details
Published in:2019 IEEE Intl Conf on Parallel & Distributed Processing with Applications, Big Data & Cloud Computing, Sustainable Computing & Communications, Social Computing & Networking (ISPA/BDCloud/SocialCom/SustainCom) pp. 1500 - 1504
Main Authors: Li, Xiaohan, Lai, Taotao, Wang, Shuaiyu, Chen, Quan, Yang, Changcai, Chen, Riqing, Lin, Jinxun, Zheng, Fu
Format: Conference Proceeding
Language:English
Published: IEEE 01.12.2019
Subjects:
Agriculture
Big Data
Feature extraction
Forestry
gaussian kernel function
Kernel
Object detection
resolution information
semantic information
Semantics
Weighted feature pyramid networks
Online Access:Get full text
Tags: Add Tag
No Tags, Be the first to tag this record!
Description
Summary:Feature Pyramid Networks (FPN) is a popular feature extraction. However, FPN and its variants do not investigate the influence of resolution information and semantic information in the object detection. Thus, FPN and its variants cannot detect some objects on challenging images. In this paper, based on FPN, we propose to use gaussian kernel function to assign different weight values to semantic information and resolution information for different images in the object detection. The proposed method, is called a Weighted Feature Pyramid Network (WFPN), and shows significant improvement over the traditional feature pyramids in several applications. Using WFPN in Faster R-CNN system, the proposed method achieves better performance on the PASCAL detection benchmark.
DOI:10.1109/ISPA-BDCloud-SustainCom-SocialCom48970.2019.00217