Multi-layer collaborative optimization fusion for semi-supervised learning

doi:10.1016/j.cja.2023.07.032

Multi-layer collaborative optimization fusion for semi-supervised learning

2023-11-01

0

OA

AI

DOI：10.1016/j.cja.2023.07.032

Original

Save

View PDF

Abstract

En 中文

Recently, the Cooperative Training Algorithm (CTA), a well-known Semi-Supervised Learning (SSL) technique, has garnered significant attention in the field of image classification. However, traditional CTA approaches face challenges such as high computational complexity and low classification accuracy. To overcome these limitations, we present a novel approach called Weighted fusion based Cooperative Training Algorithm (W-CTA), which leverages the cooperative training technique and unlabeled data to enhance classification performance. Moreover, we introduce the K-means Cooperative Training Algorithm (km-CTA) to prevent the occurrence of local optima during the training phase. Finally, we conduct various experiments to verify the performance of the proposed methods. Experimental results show that W-CTA and km-CTA are effective and efficient on CIFAR-10 dataset. (c) 2023 Production and hosting by Elsevier Ltd. on behalf of Chinese Society of Aeronautics and Astronautics. This is an open access article under the CC BY-NC-ND license (http://creativecommons.org/ licenses/by-nc-nd/4.0/).

Keywords:

Collaborative training

Fusion

Image classification

K-means algorithm

Semi-supervised learning

Multi-layer collaborative optimization fusion for semi-supervised learning

Abstract

AI Summary

Journal

Organization