Few-shot classifier GAN.
Ali-Gombe, Adamu; Elyan, Eyad; Savoye, Yann; Jayne, Chrisina
Doctor Eyad Elyan firstname.lastname@example.org
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.
|Start Date||Jul 8, 2018|
|Publication Date||Jul 23, 2018|
|Publisher||Institute of Electrical and Electronics Engineers|
|Institution Citation||ALI-GOMBE, A., ELYAN, E., SAVOYE, Y. and JAYNE, C. 2018. Few-shot classifier GAN. In Proceedings of the 2018 International joint conference on neural networks (IJCNN 2018), 8-13 July 2018, Rio de Janeiro, Brazil. Piscataway, NJ: IEEE [online], article number 8489387. Available from: https://doi.org/10.1109/IJCNN.2018.8489387|
|Keywords||Image classification; Fewshot classification; Generative adversarial networks|
ALI-GOMBE 2018 Few-shot classifier GAN
You might also like
Multiple fake classes GAN for data augmentation in face image dataset.
Symbols classification in engineering drawings.
Spatial effects of video compression on classification in convolutional neural networks.
New trends on digitisation of complex engineering drawings.
Deep learning based approaches for imitation learning.