Class Balanced Loss for Image Classification

In the study of image classification, neural network learning relies heavily on datasets. Due to variability in the difficulty of collecting images in reality, datasets tend to have class imbalance problems, which undoubtedly increases the difficulty of classification. During the training of a neura...

Full description

Saved in:
Bibliographic Details
Published in:IEEE access 2020, Vol.8, p.81142-81153
Main Authors: Wang, Lin, Wang, Chaoli, Sun, Zhanquan, Cheng, Shuqun, Guo, Lei
Format: Article
Language:English
Subjects:
accuracy
class imbalance
Classification
Data models
Datasets
Deep learning
Image classification
Indexes
loss
Neural networks
Surgery
Training
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:In the study of image classification, neural network learning relies heavily on datasets. Due to variability in the difficulty of collecting images in reality, datasets tend to have class imbalance problems, which undoubtedly increases the difficulty of classification. During the training of a neural network, classes with a large number of images are naturally trained more often than classes with a small number of images. Because of imbalanced training, the classification ability of neural networks on test and validation sets differs greatly in different categories. The test results of more training classes are better, and the test results of classes with less training are poor. In this paper, we propose two kinds of balanced loss functions, namely, CEFL loss and CEFL2 loss, by rebalancing the cross-entropy loss function and focal loss function. The experimental results show that the proposed loss functions are significantly able to improve classification accuracy on class-imbalanced datasets.
ISSN:2169-3536
2169-3536
DOI:10.1109/ACCESS.2020.2991237