Generating Memorable Images Based on Human Visual Memory Schemas
This addresses the problem of creating tailored visual content for applications like advertising or education, though it is incremental as it builds on existing GAN and memorability research.
The study tackled generating images with controlled memorability by using GANs with a human visual memory schema constraint, resulting in images that could be made more or less memorable as validated by computational measures.
This research study proposes using Generative Adversarial Networks (GAN) that incorporate a two-dimensional measure of human memorability to generate memorable or non-memorable images of scenes. The memorability of the generated images is evaluated by modelling Visual Memory Schemas (VMS), which correspond to mental representations that human observers use to encode an image into memory. The VMS model is based upon the results of memory experiments conducted on human observers, and provides a 2D map of memorability. We impose a memorability constraint upon the latent space of a GAN by employing a VMS map prediction model as an auxiliary loss. We assess the difference in memorability between images generated to be memorable or non-memorable through an independent computational measure of memorability, and additionally assess the effect of memorability on the realness of the generated images.