Top-K Pseudo Labeling for Semi-Supervised Image Classification

Yi Jiang, Hui Sun

Source Title: International Journal of Data Warehousing and Mining (IJDWM)19(2)

ISSN: 1548-3924|EISSN: 1548-3932|EISBN13: 9781668488157|DOI: 10.4018/IJDWM.316150

MLA

Jiang, Yi, and Hui Sun. "Top-K Pseudo Labeling for Semi-Supervised Image Classification." IJDWM vol.19, no.2 2023: pp.1-18. http://doi.org/10.4018/IJDWM.316150

APA

Jiang, Y. & Sun, H. (2023). Top-K Pseudo Labeling for Semi-Supervised Image Classification. International Journal of Data Warehousing and Mining (IJDWM), 19(2), 1-18. http://doi.org/10.4018/IJDWM.316150

Chicago

Jiang, Yi, and Hui Sun. "Top-K Pseudo Labeling for Semi-Supervised Image Classification," International Journal of Data Warehousing and Mining (IJDWM) 19, no.2: 1-18. http://doi.org/10.4018/IJDWM.316150

Export Reference

Favorite Full-Issue Download

View Full Text HTML

View Full Text PDF

Abstract

In this paper, a top-k pseudo labeling method for semi-supervised self-learning is proposed. Pseudo labeling is a key technology in semi-supervised self-learning. Briefly, the quality of the pseudo label generated largely determined the convergence of the neural network and the accuracy obtained. In this paper, the authors use a method called top-k pseudo labeling to generate pseudo label during the training of semi-supervised neural network model. The proposed labeling method helps a lot in learning features from unlabeled data. The proposed method is easy to implement and only relies on the neural network prediction and hyper-parameter k. The experiment results show that the proposed method works well with semi-supervised learning on CIFAR-10 and CIFAR-100 datasets. Also, a variant of top-k labeling for supervised learning named top-k regulation is proposed. The experiment results show that various models can achieve higher accuracy on test set when trained with top-k regulation.