Institutions | About Us | Help | Gaeilge
rian logo


Mark
Go Back
Use of neural signals to evaluate the quality of generative adversarial network performance in facial image generation
Wang, Zhengwei; Healy, Graham; Smeaton, Alan F.; Ward, Tomás E.
There is a growing interest in using generative adversarial networks (GANs) to produce image content that is indistinguishable from real images as judged by a typical person. A number of GAN variants for this purpose have been proposed; however, evaluating GAN performance is inherently difficult because current methods for measuring the quality of their output are not always consistent with what a human perceives. We propose a novel approach that combines a brain-computer interface (BCI) with GANs to generate a measure we call Neuroscore, which closely mirrors the behavioral ground truth measured from participants tasked with discerning real from synthetic images. This technique we call a neuro-AI interface, as it provides an interface between a human’s neural systems and an AI process. In this paper, we first compare the three most widely used metrics in the literature for evaluating GANs in terms of visual quality and compare their outputs with human judgments. Secondly, we propose and demonstrate a novel approach using neural signals and rapid serial visual presentation (RSVP) that directly measures a human perceptual response to facial production quality, independent of a behavioral response measurement. The correlation between our proposed Neuroscore and human perceptual judgments has Pearson correlation statistics: r(48) = − 0.767, p = 2.089e − 10. We also present the bootstrap result for the correlation i.e., p ≤ 0.0001. Results show that our Neuroscore is more consistent with human judgment compared with the conventional metrics we evaluated. We conclude that neural signals have potential applications for high-quality, rapid evaluation of GANs in the context of visual image synthesis.
Keyword(s): Neuroscience; Artificial intelligence; Machine learning; Generative adversarial networks; Rapid serial visual presentation; Neuroscore; Brain-computer interface; Neuro-AI interface
Publication Date:
2019
Type: Other
Peer-Reviewed: Unknown
Language(s): English
Institution: Dublin City University
Citation(s): Wang, Zhengwei ORCID: 0000-0001-7706-553X <https://orcid.org/0000-0001-7706-553X>, Healy, Graham ORCID: 0000-0001-6429-6339 <https://orcid.org/0000-0001-6429-6339>, Smeaton, Alan F. ORCID: 0000-0003-1028-8389 <https://orcid.org/0000-0003-1028-8389> and Ward, Tomás E. ORCID: 0000-0002-6173-6607 <https://orcid.org/0000-0002-6173-6607> (2019) Use of neural signals to evaluate the quality of generative adversarial network performance in facial image generation. Cognitive Computation, 12 (1). pp. 13-24. ISSN 1866-9964
Publisher(s): Springer Nature
File Format(s): application/pdf
Related Link(s): http://doras.dcu.ie/24648/1/Cognitive_Computation_revision_1.pdf,
http://dx.doi.org/10.1007/s12559-019-09670-y
First Indexed: 2020-06-19 06:55:03 Last Updated: 2020-06-19 06:55:03