A survey on semi-supervised learning

Abstract

Semi-supervised learning is the branch of machine learning concerned with using labelled as well as unlabelled data to perform certain learning tasks. Conceptually situated between supervised and unsupervised learning, it permits harnessing the large amounts of unlabelled data available in many use cases in combination with typically smaller sets of labelled data. In recent years, research in this area has followed the general trends observed in machine learning, with much attention directed at neural network-based models and generative learning. The literature on the topic has also expanded in volume and scope, now encompassing a broad spectrum of theory, algorithms and applications. However, no recent surveys exist to collect and organize this knowledge, impeding the ability of researchers and engineers alike to utilize it. Filling this void, we present an up-to-date overview of semi-supervised learning methods, covering earlier work as well as more recent advances. We focus primarily on semi-supervised classification, where the large majority of semi-supervised learning research takes place. Our survey aims to provide researchers and practitioners new to the field as well as more advanced readers with a solid understanding of the main approaches and algorithms developed over the past two decades, with an emphasis on the most prominent and currently relevant work. Furthermore, we propose a new taxonomy of semi-supervised classification algorithms, which sheds light on the different conceptual and methodological approaches for incorporating unlabelled data into the training process. Lastly, we show how the fundamental assumptions underlying most semi-supervised learning algorithms are closely connected to each other, and how they relate to the well-known semi-supervised clustering assumption.

Inf-Net: Automatic COVID-19 Lung Infection Segmentation from CT Images

“…The main goal of semi-supervised learning (SSL) is to improve model performance using a limited number of labeled data and a large amount of unlabeled data [37]. Currently, there is increasing focus on training deep neural network using the SSL strategy [38]. These methods often optimize a supervised loss on labeled data along with an unsupervised loss imposed on either unlabeled data [39] or both the labeled and unlabeled data [40], [41].…”

Co-Training for On-Board Deep Object Detection

“…In contrast to AL, other approaches do not assume human oracles in the labeling loop. For instance, this is the case of semisupervised learning (SSL) algorithms [6,38,40], which assume the availability of a large number or raw unlabeled data together with a relatively small number of labeled data. Then, a model must be trained using the unlabeled and labeled data (without human intervention), with the goal of being more accurate than if only the labeled data were used.…”

Semantic and Generalized Entropy Loss Functions for Semi-Supervised Deep Learning

“…The primary objective of semi-supervised learning is to use unlabeled observations to develop better learning procedures. However, this is not always easy or even possible [ 22 ]. As mentioned earlier, unmarked observations are useful only if they contain relevant information for predicting labels that are not included in the labeled data itself or cannot be easily extracted.…”