A person who uses Instagram.
Lorenzo Di Cola | NurPhoto by Getty Images
Pugs, Ferraris, mountains, brunch, beaches and babies – Instagram is full of them. In fact, it has become one of the largest image databases on the planet in the last decade, and the company’s owner, Facebook, uses this treasure to teach cars what is 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 over 1 billion public images on Instagram.
The computer vision program, dubbed SEER, outperformed existing AI models in an object recognition test, Facebook said.
It achieved a “classification accuracy score” of 84.2% when it attempted a test provided by ImageNet, which is a large visual database designed to be used in research on visual object recognition software. Basically, it tests whether an AI program can identify what is in a photo.
A new approach
While many AI models are trained on carefully labeled datasets, Facebook said SEER has learned how to identify objects in photos by analyzing random, unmarked and unclean Instagram images. This AI technique is known as self-supervised learning (SEER is a piece on SElf-supERvised).
“The future of AI is to create systems that can learn directly from any information provided to them – whether it’s text, images or other data – without relying on carefully clean and labeled data sets to learn how to recognize objects in a photo, interpret a block of text or perform any of the countless other tasks we ask of it, ”the Facebook researchers wrote in a blog post.
“SEER performance demonstrates that self-supervised learning can excel at computer vision tasks in real-world settings,” they added. “This is a breakthrough that ultimately 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 wide. These include automatically generated enhanced text to describe images to the visually impaired, better automatic classification of items sold on the Facebook Marketplace, and better systems to keep harmful images away from the Facebook platform, the company said.
Privacy issue?
But many Instagram users may be surprised to hear that their images are used to train Facebook AI systems.
“We inform Instagram account holders in our data policy that we use the information we have to support research and innovation, including in technological progress of this kind,” Priya Goyal, a software engineer at Facebook AI Research, told CNBC.
Facebook has said it will open some of its software so that other researchers can experiment with it.
“While we share the details of our research and create an open-source library that will allow other researchers to use self-supervised learning to train models on impure images, we do not share images or SEER mode,” said Goyal.
Other large technology companies, including Google and Microsoft, are also trying to push the boundaries of computer vision. Last summer, Google released the SimCLRv2 computer vision model, while OpenAI released iGPT 2.