Semi-supervised Domain Adaptation via adversarial training

Abstract

Whilst convolutional neural networks (CNN) offer state-of-the-art performance for classification and detection tasks in computer vision, their successful adoption in defence applications is limited by the cost of labelled data and the inability to use crowd sourcing due to classification issues. Popular approaches to solve this problem use the expansive labelled data for training. It would be more cost-efficient to learn representations from the unlabelled data whilst leveraging labelled data from existing datasets, as empirically the performance of supervised learning is far greater than unsupervised-learning. In this paper we investigate the benefits of mixing Domain Adaptation and semi-supervised learning to train CNNs and showcase using adversarial training to tackle this issue.