A person using Instagram.
Lorenzo Di Cola | NurPhoto via Getty Images
Pugs, Ferraris, mountains, brunches, beaches and babies – Instagram is full of them. In fact, it has become one of the largest image databases on the planet in the past decade and the company’s owner, Facebook, is using this treasure to teach machines what’s in a photo.
Facebook announced on Thursday that it has built an artificial intelligence program that can “see” what it is looking at. He did this by feeding him more than 1 billion public Instagram images.
The “computer vision” program, dubbed SEER, outperformed existing AI models in an object recognition test, Facebook said.
He reached an “accuracy rating score” of 84.2% when he tried a test provided by ImageNet, which is a large visual database designed for use in researching visual object recognition software. Basically, it tests whether an AI program can identify what is in a photo.
New approach
Considering that many AI models are trained on carefully labeled data sets, Facebook said SEER learned how to identify objects in photos by analyzing random, unlabeled and uncured Instagram images. This AI technique is known as self-supervised learning (SEER is a game with SELF-SUPERVISED).
“The future of AI is in creating systems that can learn directly from any information provided – be it text, images or other data – without relying on carefully selected and labeled data sets to teach them how to recognize objects in a photo, interpret a block of text or perform any of the countless other tasks we ask for, ”wrote the Facebook researchers in a blog post.
“SEER’s performance demonstrates that self-supervised learning can excel in computer vision tasks in real-world settings,” they added. “This is a breakthrough that paves the way for more flexible, accurate and adaptable computer vision models in the future.”
Although this is just a research project, a Facebook spokesman said the potential uses are relatively broad. They include automatically generated text that is enhanced to describe images for people with visual impairments, better automatic categorization of items sold on the Facebook Marketplace, and better systems for keeping harmful images away from the Facebook platform, the company said.
Privacy issue?
But many Instagram users may be surprised to learn that their images are being used to train Facebook’s AI systems.
“We inform Instagram account holders in our data policy that we use the information we have to support research and innovation, including technological advances like this,” Priya Goyal, software engineer at Facebook AI Research, told CNBC.
Facebook said it will open the code for some of its software so that other researchers can experiment with it.
“While we are sharing the details of our research and creating an open source library that will allow other researchers to use self-supervised learning to train models in uncured images, we are not sharing the images or the SEER mode,” said Goyal.
Other major technology companies, including Google and Microsoft, are also trying to push the limits of computer vision. Last summer, Google published the computer vision model SimCLRv2, while OpenAI published iGPT 2.