On the Notion of Image Memorability of Pattern Recognition Machines
Abstract: We study 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 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.
Submission Length: Regular submission (no more than 12 pages of main content)
Changes Since Last Submission: Fix font and format issues. Url is not available.
Assigned Action Editor: ~Stanislaw_Kamil_Jastrzebski1
Submission Number: 2426
Loading