An Overview of Deep Semi-Supervised Learning

TL;DR

This paper provides a comprehensive overview of deep semi-supervised learning, highlighting its importance in reducing labeled data requirements for deep neural networks and summarizing key approaches in the field.

Contribution

It offers a detailed survey of the main semi-supervised learning methods applied to deep neural networks, emphasizing their role in data-efficient learning.

Findings

Semi-supervised methods improve data efficiency in deep learning.

Various approaches are effective in reducing labeled data needs.

The field is rapidly evolving with new techniques emerging.

Abstract

Deep neural networks demonstrated their ability to provide remarkable performances on a wide range of supervised learning tasks (e.g., image classification) when trained on extensive collections of labeled data (e.g., ImageNet). However, creating such large datasets requires a considerable amount of resources, time, and effort. Such resources may not be available in many practical cases, limiting the adoption and the application of many deep learning methods. In a search for more data-efficient deep learning methods to overcome the need for large annotated datasets, there is a rising research interest in semi-supervised learning and its applications to deep neural networks to reduce the amount of labeled data required, by either developing novel methods or adopting existing semi-supervised learning frameworks for a deep learning setting. In this paper, we provide a comprehensive overview of deep semi-supervised learning, starting with an introduction to the field, followed by a summarization of the dominant semi-supervised approaches in deep learning.