Facial reconstruction

Search LJMU Research Online

Browse Repository | Browse E-Theses

Few-shot Classifier GAN

Ali-Gombe, A, Elyan, E, Savoye, Y and Jayne, C (2018) Few-shot Classifier GAN. In: International joint conference on neural networks (IJCNN 2018) . (2018 International Joint Conference on Neural Networks (IJCNN), 8-13 July 2018, Rio de Janeiro, Brazil).

ijcnn18.pdf - Accepted Version

Download (16MB) | Preview


Fine-grained image classification with a few-shot classifier is a highly challenging open problem at the core of a numerous data labeling applications. In this paper, we present Few-shot Classifier Generative Adversarial Network as an approach for few-shot classification. We address the problem of few-shot classification by designing a GAN in which the discriminator and the generator compete to output labeled data in any case. In contrast to previous methods, our techniques generate then classify images into multiple fake or real classes. A key innovation of our adversarial approach is to allow fine-grained classification using multiple fake classes with semi-supervised deep learning. A major strength of our techniques lies in its label-agnostic characteristic, in the sense that the system handles both labeled and unlabeled data during training. We validate quantitatively our few-shot classifier on the MNIST and SVHN datasets by varying the ratio of labeled data over unlabeled data in the training set. Our quantitative analysis demonstrates that our techniques produce better classification performance when using multiple fake classes and larger amount of unlabelled data.

Item Type: Conference or Workshop Item (Paper)
Additional Information: © 2018 IEEE.
Subjects: Q Science > QA Mathematics > QA75 Electronic computers. Computer science
Q Science > QA Mathematics > QA76 Computer software
Divisions: Computer Science & Mathematics
Publisher: IEEE
Date Deposited: 24 Oct 2019 08:55
Last Modified: 13 Apr 2022 15:17
DOI or ID number: 10.1109/IJCNN.2018.8489387
URI: https://researchonline.ljmu.ac.uk/id/eprint/11624
View Item View Item