Research Area:  Machine Learning

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.

Keywords:  
Machine Learning
Deep neural networks
Supervised learning
Semi-supervised learning
Deep learning

Author(s) Name:  Yassine Ouali, Céline Hudelot, Myriam Tami

Publisher name:  arXiv:2006.05278

DOI:  10.48550/arXiv.2006.05278

Volume Information:  

Paper Link:   https://arxiv.org/abs/2006.05278