Menu
Wondering which photo is best? Ask this deep-learning algorithm online

Wondering which photo is best? Ask this deep-learning algorithm online

Now available as a demo, new technology from MIT can tell you which ones are most memorable

Choosing the best photos has always been more a matter of art than of science, whether it's for a Facebook page or a marketing campaign. That may soon change, however, thanks to some new technology out of MIT.

Researchers from MIT’s Computer Science and Artificial Intelligence Laboratory (CSAIL) have created an algorithm called MemNet that can predict how memorable or forgettable an image is almost as accurately as humans can, the university announced on Wednesday.

For each image, the algorithm produces a heat map showing which parts of the image are most memorable. The idea, ultimately, is to help increase images' memorability by emphasizing different regions.

The technology is now available through an online demo that anyone can try, and the researchers plan to turn it into an app as well, with a focus on helping users tweak their photos to make them more memorable.

Potential applications might include improving the content of ads and social media posts or developing more effective teaching resources, the researchers suggested.

“Understanding memorability can help us make systems to capture the most important information, or, conversely, to store information that humans will most likely forget,” said CSAIL graduate student Aditya Khosla, who was lead author on a related paper. “It’s like having an instant focus group that tells you how likely it is that someone will remember a visual message.”

Khosla is scheduled to present the paper in Chile this week at the International Conference on Computer Vision.

The research team behind MemNet had already developed a similar algorithm for facial memorability, but this new work uses techniques from deep learning, including neural networks to teach computers to sift through massive amounts of data to find patterns.

The team tested the algorithm on tens of thousands of images from several different data sets. Those images had already each received a “memorability score” based on the ability of human subjects to remember them in online experiments.

The algorithm then went head-to-head with humans by predicting how memorable a group of people would find a new, never-before-seen image. As it turned out, it performed 30 percent better than existing algorithms and was within a few percentage points of the performance of the average human.

Looking ahead, the research team next plans to try to update the system to be able to predict the memory of a specific person, and to better tailor it for individual industries such as retail clothing and logo design.

Google, Xerox and Nvidia are among the organizations that supported the research along with the National Science Foundation, the McGovern Institute Neurotechnology Program and the MIT Big Data Initiative at CSAIL.


Follow Us

Join the newsletter!

Or

Sign up to gain exclusive access to email subscriptions, event invitations, competitions, giveaways, and much more.

Membership is free, and your security and privacy remain protected. View our privacy policy before signing up.

Error: Please check your email address.

Brand Post

What to expect from your IT Distributor

Whether you’re just starting out or you’ve been around since before the dot com rollercoaster, choosing the right distribution partner can be a pivotal factor in your success. This definitive guide outlines the traits that every IT partner needs to look for in their IT Distributor.

Featured

Slideshows

Meet the winners of the 2020 Reseller News Innovation Awards

Meet the winners of the 2020 Reseller News Innovation Awards

Reseller News honoured the standout players of the New Zealand channel in front of more than 500 technology leaders in Auckland on 21 October, recognising the achievements of top partners, start-ups, vendors, distributors and individuals.

Meet the winners of the 2020 Reseller News Innovation Awards
Meet the Reseller News 30 Under 30 Tech Awards 2020 winners

Meet the Reseller News 30 Under 30 Tech Awards 2020 winners

This year’s Reseller News 30 Under 30 Tech Awards were held as an integral part of the first entirely virtual Emerging Leaders​ forum, an annual event dedicated to identifying, educating and showcasing the New Zealand technology market’s rising stars. The 30 Under 30 Tech Awards 2020 recognised the outstanding achievements and business excellence of 30 talented individuals​, across both young leaders and those just starting out. In this slideshow, Reseller News honours this year's winners and captures their thoughts about how their ideas of leadership have changed over time.​

Meet the Reseller News 30 Under 30 Tech Awards 2020 winners
Reseller News Exchange Auckland: Beyond the myths — how partners can master cloud security

Reseller News Exchange Auckland: Beyond the myths — how partners can master cloud security

This exclusive Reseller News Exchange event in Auckland explored the challenges facing the partner community on the cloud security frontier, as well as market trends, customer priorities and how the channel can capitalise on the opportunities available. In association with Arrow, Bitdefender, Exclusive Networks, Fortinet and Palo Alto Networks. Photos by Gino Demeer.

Reseller News Exchange Auckland: Beyond the myths — how partners can master cloud security
Show Comments