Semi-supervised learning with an open augmenting unknown class for cost-effective training and reliable classifications
Year: 2020
Type: preprint
Abstract: The ability to (a) train off partially labelled datasets and (b) ensure resulting networks separate data outside the domain of interest hugely expands the practical and cost-effective applicability of neural network classifiers. We design a classifier based off generative adversarial networks (GANs) that trains off a practical and cost-saving semi-supervised criteria which, specifically, allows novel classes within the unlabelled training set. Furthermore, we ensure the resulting classifier is capable of absolute novel class detection, be these from the semi-supervised unlabelled training set or a so-called open set. Results are both state-of-the-art and a first of its kind. We argue this technique greatly decreases training cost in respect to labelling while greatly improving the reliability of classifications.
Source: arXiv (Cornell University)
Authors: Emile R. Engelbrecht, Johan A. du Preez
Institution: Stellenbosch University
Language: English
Subfield: Artificial Intelligence
Field: Computer Science
Domain: Physical Sciences
Open Access status: green
OpenAlex ID: W3111610365