Classification of Long-Tailed Data Based on Bilateral-Branch Generative Network with Time-Supervised Strategy

Yalin Huang,Yangkang Ou,Zeng Zhigao,Lingwei Kong,Yan-Hui Zhu,Hou-Sheng Su

doi:10.1155/2021/8667868

Yalin Huang, Yangkang Ou + Show 4 more

Open Access

https://doi.org/10.1155/2021/8667868

Copy DOI

Journal: Complexity	Publication Date: Nov 2, 2021
Citations: 1	License type: CC BY 4.0

Affiliation: Hunan University of Technology

Abstract

In the face of the long-tailed data distribution that widely exists in real-world datasets, this paper proposes a bilateral-branch generative network model. The data of the second branch is constructed by resampling the generative network training method to improve the data quality. A bilateral-branch network model is used to curb the risk of gradient explosion and to avoid over-fitting and under-fitting with the combined effect of different data branches. Meanwhile, Time-supervised strategy is introduced to improve the model's operational efficiency and ability to cope with extreme conditions by supervising and collaboratively controlling of the bilateral-branch generative network with time-invariant parameters. Time supervised strategy could ensure the accuracy of the model while reducing the number of iterations. Experimental results on two publicly available datasets, CIFAR10 and CIFAR100, show that the proposed method effectively improves the performance of long-tail data classification.

Highlights

With the rapid development of convolution neural network algorithms in recent years, there has been a very impressive improvement in the performance of image classification
The accuracy drops significantly due to the small influence of the data in the second branch of the model, but as the number of training sessions increases, the accuracy of the Bilateral-Branch Network (BBN) algorithm and our algorithm always steadily exceeds that of the M2m algorithm with the effect of the data in the second branch. is indicates that the pure data generation model can achieve a high accuracy rate within a smaller number of training sessions, but the final accuracy ceiling of the model is not high
Benefiting from the role of the data generation network, the BBGN network model constructed by the generation method with the time-supervision strategy can significantly improve the accuracy of the model in the case of very extreme data distribution

Summary

Introduction

With the rapid development of convolution neural network algorithms in recent years, there has been a very impressive improvement in the performance of image classification. The success is inextricably linked to the available high-quality large-scale datasets, such as ImageNet ILSVRC 2012 [1], MS COCO [2] and Places Database [3] Compared to these high-quality datasets, realworld datasets are always biased and it is difficult to ensure a uniform distribution of data, and more often than not, certain classes of data are very abundant while certain remaining classes are very scarce, which leads to a long-tail distribution of data [4, 5] and affects the performance of image classification. The SMOTE algorithm [11] merely repeats and abandons the original data in the process of resampling It changes the data distribution, it cannot bring more classified information to the deep learning model. We track the accuracy of the classification results of different models on the test set during the training process and plot it as a line graph, which can visualize the difference of different models during the training process

Methods

Results

Conclusion