Paper Semi-supervised Deep Learning for Image Classification with Distribution Mismatch

This paper is a deep review of the state-of-the-art semi-supervised deep learning methods, focusing on methods dealing with the distribution mismatch setting. Since under real world usage scenarios, a distribution mismatch might occur between the labelled and unlabelled datasets. 

The article has been published in the IEEE Transactions on Artificial Intelligence journal. Professor Saúl Calderón participates in this paper with collaborators from De Montfort University, United Kingdom. The preprint can be found at the following link: https://arxiv.org/pdf/2203.00190.pdf