A Unified Generative Adversarial Network Training via Self-Labeling and Self-Attention

Watanabe, Tomoki; Favaro, Paolo (2021). A Unified Generative Adversarial Network Training via Self-Labeling and Self-Attention. Proceedings of machine learning research, 139, pp. 11024-11034. PMLR

Text Conference_A_Unified_Generative_Adversarial_Network_Training_via_Self-Labeling_and_Self_Attention.pdf - Published Version Restricted to registered users only Available under License Publisher holds Copyright. Download (9MB)

We propose a novel GAN training scheme that can handle any level of labeling in a unified manner. Our scheme introduces a form of artificial labeling that can incorporate manually defined labels, when available, and induce an alignment between them. To define the artificial labels, we exploit the assumption that neural network generators can be trained more easily to map nearby latent vectors to data with semantic similarities, than across separate categories. We use generated data samples and their corresponding artificial conditioning labels to train a classifier. The classifier is then used to self-label real data. To boost the accuracy of the self-labeling, we also use the exponential moving average of the classifier. However, because the classifier might still make mistakes, especially at the beginning of the training, we also refine the labels through self-attention, by using the labeling of real data samples only when the classifier outputs a high classification robability score. We evaluate our approach on CIFAR-10, STL-10 and SVHN, and show that both self-labeling and self-attention consistently improve the quality of generated data. More surprisingly, we find that the proposed scheme can even outperform classconditional GANs.

Interest & Impact

Downloads

1 since deposited on 10 May 2022
0 in the past 12 months

Citations

5 Citations in Web of Science ®
6 Citations in Scopus

Search

in Google Scholar™

Services

Actions (login required)

Edit item

Actions (login required)

Edit item