Research for Improving the Accuracy of Image Classification Based on Semi-Supervision

DOI

10.2991/978-94-6463-540-9_95How to use a DOI?

Keywords

Image Classification; Semi-Supervision; Improving the Accuracy

Abstract

One of the core tasks of computer vision is image classification, which aims to distinguish different types of images based on various features. However, traditional image classification methods often rely on a large amount of labeled data to support them and obtaining large-scale, high-quality labeled data in practical applications is often very difficult. Insufficient data volume will affect the accuracy of image classification. In response to this issue, this article reviews semi-supervised learning methods to improve the performance of image classification. Specifically, this article selects collaborative training algorithms, self-training algorithms, and average teacher models, and applies them to the following aspects: The collaborative training strategy aims to improve the execution efficiency of image classification tasks by integrating multiple classifier algorithms and the Collaboration semi - Supervised Convolutional Neural Network (Co-S2CNN) algorithm. The self-training algorithm combines density peak and natural neighbor algorithms to reduce the weight of samples in low-density areas. The average teacher model combines the You Only Look Once (YOLO) algorithm and further introduces Strip Pooling Module (SPM) to improve the accuracy of strip object detection. Descriptive empirical research results indicate that these three hybrid algorithms can significantly improve the efficiency and accuracy of image classification.

Copyright

© 2024 The Author(s)

Open Access

Open Access This chapter is licensed under the terms of the Creative Commons Attribution-NonCommercial 4.0 International License (http://creativecommons.org/licenses/by-nc/4.0/), which permits any noncommercial use, sharing, adaptation, distribution and reproduction in any medium or format, as long as you give appropriate credit to the original author(s) and the source, provide a link to the Creative Commons license and indicate if changes were made.

Download article (PDF)

TY  - CONF
AU  - Ziyang Gu
AU  - Lihang Wang
AU  - Yueqian Zhang
PY  - 2024
DA  - 2024/10/16
TI  - Research for Improving the Accuracy of Image Classification Based on Semi-Supervision
BT  - Proceedings of the 2024 2nd International Conference on Image, Algorithms and Artificial Intelligence (ICIAAI 2024)
PB  - Atlantis Press
SP  - 950
EP  - 960
SN  - 2352-538X
UR  - https://doi.org/10.2991/978-94-6463-540-9_95
DO  - 10.2991/978-94-6463-540-9_95
ID  - Gu2024
ER  -