/* ---- Google Analytics Code Below */

Friday, November 01, 2019

What Makes an Image Usefully Memorable?

Asked this question as early as the 80s, hoping to capture the value for advertisers.  With very large Ad databases.   But with very different methods.    Not overly successful, but did provide some deeper thinking about measures.  It led to measurable results, but not useful ones.   Using Generative  Adversarial Networks is interesting here.   Paper referenced: https://arxiv.org/pdf/1906.10112.pdf

What makes an image memorable? Ask a computer scientist
An artificial intelligence model co-developed at MIT shows in striking detail what makes some images stick in our minds.

Kim Martineau | MIT Quest for Intelligence

From the "Mona Lisa" to the "Girl with a Pearl Earring," some images linger in the mind long after others have faded. Ask an artist why, and you might hear some generally-accepted principles for making memorable art. Now there’s an easier way to learn: ask an artificial intelligence model to draw an example. 

A new study using machine learning to generate images ranging from a memorable cheeseburger to a forgettable cup of coffee shows in close detail what makes a portrait or scene stand out. The images that human subjects in the study remembered best featured bright colors, simple backgrounds, and subjects that were centered prominently in the frame. Results were presented this week at the International Conference on Computer Vision. 

“A picture is worth a thousand words,” says the study’s co-senior author Phillip Isola, the Bonnie and Marty (1964) Tenenbaum CD Assistant Professor of Electrical Engineering and Computer Science at MIT. “A lot has been written about memorability, but this method lets us actually visualize what memorability looks like. It gives us a visual definition for something that’s hard to put into words."

The work builds on an earlier model, MemNet, which rates the memorability of an image and highlights the features in the picture influencing its decision. MemNet’s predictions are based on the results of an online study in which 60,000 images were shown to human subjects and ranked by how easily they were remembered.

The model in the current study, GANalyze, uses a machine learning technique called generative adversarial networks, or GANs, to visualize a single image as it inches its way from "meh" to memorable. GANalyze lets viewers visualize the incremental transformation of, say, a blurry panda lost in the bamboo into a panda that dominates the frame, its black eyes, ears, and paws contrasting sharply and adorably with its white mug.  ... " 

No comments: