Curvature-Driven Deformable Convolutional Networks for End-To-End Object Detection

Recently, deformable convolution networks have shown the superior performance in object detection due to its ability to adapt to the geometric variations of object. These methods learn the offset fields under the supervision of localization and recognition. Nevertheless, the spatial support of these...

Full description

Saved in:
Bibliographic Details
Published in:Mobile information systems 2022-02, Vol.2022, p.1-11
Main Authors: Gu, Xiaodong, Fu, Ying
Format: Article
Language:English
Subjects:
Algorithms
Boxes
Classification
Convolution
Curvature
Deformation
Entropy (Information theory)
Feature maps
Formability
Learning
Localization
Networks
Neural networks
Object recognition
Predictions
Sensors
Statistical analysis
Citations: Items that this one cites
Items that cite this one
Online Access:Get full text
Tags: Add Tag
No Tags, Be the first to tag this record!
Description
Summary:Recently, deformable convolution networks have shown the superior performance in object detection due to its ability to adapt to the geometric variations of object. These methods learn the offset fields under the supervision of localization and recognition. Nevertheless, the spatial support of these networks may be inexact because the offsets are learned implicitly via extra convolutional layer. In this work, we present curvature-driven deformable convolutional networks (C-DCNets) that adopt explicit geometric property of the preceding feature maps to enhance the deformability of convolution operation and make the networks easier to focus on pertinent image region. To be consistent with postprocessing technology of object detection, we multiply the class prediction probability by the similarity of predicted boxes and ground truth boxes as the final class prediction probability and substitute it into the binary cross entropy loss function. The obtained loss function correlates the bounding box regression and classification. Experimental results on PASCAL VOC and COCO data set show that C-DCNets-based YOLOv4 with the proposed loss function outperforms state-of-the-art algorithms.
ISSN:1574-017X
1875-905X
DOI:10.1155/2022/7556022