What Images are More Memorable to Machines?
This work introduces the concept of machine memorability, opening a new research direction at the interface between machine memory and visual data, which is foundational for understanding machine intelligence.
The paper tackles the problem of measuring and predicting image memorability for machines, revealing that complex images are generally more memorable to machines, with differences observed compared to human memorability.
This paper studies the problem of measuring and predicting how memorable an image is to pattern recognition machines, as a path to explore machine intelligence. Firstly, we propose a self-supervised machine memory quantification pipeline, dubbed ``MachineMem measurer'', to collect machine memorability scores of images. Similar to humans, machines also tend to memorize certain kinds of images, whereas the types of images that machines and humans memorize are different. Through in-depth analysis and comprehensive visualizations, we gradually unveil that``complex" images are usually more memorable to machines. We further conduct extensive experiments across 11 different machines (from linear classifiers to modern ViTs) and 9 pre-training methods to analyze and understand machine memory. This work proposes the concept of machine memorability and opens a new research direction at the interface between machine memory and visual data.