Synthetic-Neuroscore: Using a neuro-AI interface for evaluating generative adversarial networks
By Zhengwei Wang, Qi She, Alan F. Smeaton, Tomás Ward, Graham F. Healy. 2019
13 citations recorded by the source corpus.
Generative adversarial networks (GANs) are increasingly attracting attention in the computer vision, natural language processing, speech synthesis and similar domains. Arguably the most striking results have been in the area of image synthesis. However, evaluating the performance of GANs is still an open and challenging problem. Existing evaluation metrics primarily measure the dissimilarity between real and generated images using automated statistical methods. They often require large sample sizes for evaluation and do not directly reflect human perception of image quality. In this work, we describe an evaluation metric we call Neuroscore, for evaluating the performance of GANs, that more directly reflects psychoperceptual image quality through the utilization of brain signals. Our results show that Neuroscore has superior performance to the current evaluation metrics in that: (1) It is more consistent with human judgment; (2) The evaluation process needs much smaller numbers of samples; and (3) It is able to rank the quality of images on a per GAN basis. A convolutional neural network (CNN) based neuro-AI interface is proposed to predict Neuroscore from GAN-generated images directly without the need for neural responses. Importantly, we show that including neural responses during the training phase of the network can significantly improve the prediction capability of the proposed model. Materials related to this work are provided at this https URL.
Subfields: Cognitive Neuroscience, Computer Vision and Pattern Recognition
How researchers see this paper
The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.
In Cognitive Neuroscience
In Computer Vision and Pattern Recognition
Citations in the corpus
- Generative Adversarial Networks (2021, neutral): “Formal methods can be used to improve the reliability and safety of GANs by verifying the properties of GANs or generating adversarial examples to evaluate their robustness [23], [24].”
- Generative Adversarial Networks in Time Series: A Systematic Literature Review (2022, background): “A wide range of evaluation metrics has been proposed to evaluate the performance of GANs [9, 10, 98, 99].”