Modeling Visual Memorability Assessment with Autoencoders Reveals Characteristics of Memorable Images
This work addresses the challenge of understanding human visual memory for applications in fields like psychology and AI, though it is incremental as it builds on existing autoencoder and CNN methods.
The paper tackled the problem of identifying what makes images memorable by using an autoencoder-based deep learning model, finding significant correlations between memorability scores and reconstruction error, and identifying key visual characteristics that contribute to memorability.
Image memorability refers to the phenomenon where certain images are more likely to be remembered than others. It is a quantifiable and intrinsic image attribute, defined as the likelihood of an image being remembered upon a single exposure. Despite advances in understanding human visual perception and memory, it is unclear what features contribute to an image's memorability. To address this question, we propose a deep learning-based computational modeling approach. We employ an autoencoder-based approach built on VGG16 convolutional neural networks (CNNs) to learn latent representations of images. The model is trained in a single-epoch setting, mirroring human memory experiments that assess recall after a single exposure. We examine the relationship between autoencoder reconstruction error and memorability, analyze the distinctiveness of latent space representations, and develop a multi-layer perceptron (MLP) model for memorability prediction. Additionally, we perform interpretability analysis using Integrated Gradients (IG) to identify the key visual characteristics that contribute to memorability. Our results demonstrate a significant correlation between the images' memorability score and the autoencoder's reconstruction error, as well as the robust predictive performance of its latent representations. Distinctiveness in these representations correlated significantly with memorability. Additionally, certain visual characteristics were identified as features contributing to image memorability in our model. These findings suggest that autoencoder-based representations capture fundamental aspects of image memorability, providing new insights into the computational modeling of human visual memory.