Year: 2020
Type: preprint
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.
Source: arXiv (Cornell University)
Authors: Ouali, Yassine, Hudelot, Céline, Tami, Myriam
Language: English
Subfield: Artificial Intelligence
Field: Computer Science
Domain: Physical Sciences
Open Access status: green
Funder: Université Paris-Saclay
OpenAlex ID: W3034749675
