A Simple Stochastic Regularization Technique for Avoiding Overfitting in Low Resource Image Classification

Abstract
Drop type technique, as a method that can effectively regulate the co-adaptations and prediction ability of neural network units, is widely used in model parameter optimization to reduce overfitting problems. However, low resource image classification faces serious overfitting problems, and the data sparsity problem weakens or even disappears the effectiveness of most regularization methods. This paper is inspired by the value iteration strategy and attempts a Drop type method based on Metcalfe's law, named Metcalfe-Drop. The experimental results indicate that using Metcalfe-Drop technique as a basis to determine parameter sharing is more effective than randomly controlling neurons according to a certain probability. Our code is available at https://gitee.com/giteetu/metcalfe-drop.git.
Description

CCS Concepts: Computing methodologies -> Image processing; Neural networks; Image representations

        
@inproceedings{
10.2312:pg.20231281
, booktitle = {
Pacific Graphics Short Papers and Posters
}, editor = {
Chaine, Raphaëlle
and
Deng, Zhigang
and
Kim, Min H.
}, title = {{
A Simple Stochastic Regularization Technique for Avoiding Overfitting in Low Resource Image Classification
}}, author = {
Ji, Ya Tu
and
Wang, Bai Lun
and
Dai, Ling Jie
and
Yao, Miao Miao
and
Li, Xiao Mei
and
Ren, Qing Dao Er Ji
and
Shi, Bao
and
Wu, Nier E.
and
Lu, Min
and
Liu, Na
and
Zhuang, Xu Fei
and
Xu, Xuan Xuan
and
Wang, Li
}, year = {
2023
}, publisher = {
The Eurographics Association
}, ISBN = {
978-3-03868-234-9
}, DOI = {
10.2312/pg.20231281
} }
Citation