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 New Zealand Reseller News newsletter!

Error: Please check your email address.

Slideshows

Top 50 defining moments of the New Zealand channel in 2016

Top 50 defining moments of the New Zealand channel in 2016

Reseller News looks back on a tumultuous 12 months for the New Zealand channel, assessing the fallout from a year of sizeable industry change. Whether it be local or global mergers and acquisitions, distribution deals or job changes, the channel that started the year differs somewhat to the one set to finish it - Reseller News assesses the key moments that made 2016.​

Top 50 defining moments of the New Zealand channel in 2016
​Hewlett Packard Enterprise honours high achieving NZ channel

​Hewlett Packard Enterprise honours high achieving NZ channel

Hewlett Packard Enterprise honoured its top performing Kiwi partners at the second running of its HPE Partner Awards in New Zealand, held at a glitzy ceremony in Auckland. Recognising excellence across eight categories - from distributors to resellers - the tech giant celebrated its first year as a standalone company, following its official split from HP in 2015.

​Hewlett Packard Enterprise honours high achieving NZ channel
Nutanix treats channel partners to Christmas cruise

Nutanix treats channel partners to Christmas cruise

Nutanix recently took to the seas for a Christmas Cruise around Sydney Harbour with its Australia and New Zealand staff, customers and partners to celebrate a stellar year for the vendor. With the sun out, they were all smiles and mingled over drinks and food.

Nutanix treats channel partners to Christmas cruise
Show Comments