Synthetic-Neuroscore: Using A Neuro-AI Interface for Evaluating Generative Adversarial Networks
This addresses the challenge of evaluating GANs for researchers and practitioners in computer vision and related fields, offering a more human-aligned metric, though it is incremental as it builds on existing evaluation methods.
The paper tackles the problem of evaluating Generative Adversarial Networks (GANs) by proposing Neuroscore, a metric that uses brain signals to reflect human perception of image quality, showing it outperforms existing metrics in consistency with human judgment, requiring fewer samples, and enabling per-GAN ranking.
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 https://github.com/villawang/Neuro-AI-Interface.