A MBGD enhancement method for imbalance smoothing

This paper addresses foreground-foreground imbalance in object detection. Firstly, we introduce Mini-batch Stochastic Gradient Descent (MBGD) with YOLO and the foreground-foreground imbalance problem. Then T -distribution is devised and proved to smoothen the imbalanced distribution and allocate at...

Full description

Saved in:
Bibliographic Details
Published inMultimedia tools and applications Vol. 81; no. 17; pp. 24225 - 24243
Main Authors Ai, Xusheng, Sheng, Victor S., Li, Chunhua
Format Journal Article
LanguageEnglish
Published New York Springer US 01.07.2022
Springer Nature B.V
Subjects
Accuracy
Age
Classification
Computer Communication Networks
Computer Science
Data Structures and Information Theory
Datasets
Multimedia
Multimedia Information Systems
Object recognition
Probability distribution
Sensors
Smoothing
Special Purpose and Application-Based Systems
Surveillance
YOLO
Mini-batch stochastic gradient descent
Foreground-foreground imbalance
Object detection
Online AccessGet full text

Cover

More Information
Summary:This paper addresses foreground-foreground imbalance in object detection. Firstly, we introduce Mini-batch Stochastic Gradient Descent (MBGD) with YOLO and the foreground-foreground imbalance problem. Then T -distribution is devised and proved to smoothen the imbalanced distribution and allocate at least a representative for each class. Furthermore, Mini-Batch Imbalance Smoothing method (MB-IS) is proposed to address the foreground-foreground imbalance by following T -distribution and proportionally assigning class weights in a mini-batch. Finally, Extensive experiments on our own transaction dataset and VOC2007 dataset demonstrate the superiority of MB-IS with certain mini-batch size.
ISSN:1380-7501
1573-7721
DOI:10.1007/s11042-022-12697-3