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...
Saved in:
Published in | Multimedia tools and applications Vol. 81; no. 17; pp. 24225 - 24243 |
---|---|
Main Authors | , , |
Format | Journal Article |
Language | English |
Published |
New York
Springer US
01.07.2022
Springer Nature B.V |
Subjects | |
Online Access | Get full text |
Cover
Loading…
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 |