[ad_1]
Pugs, Ferraris, mountains, brunches, beaches and babies, Instagram is full of them. In fact, it has grown into one of the largest image databases on the planet over the past decade and the owner of the company, Facebook, is using this treasure to teach machines what there is. in a photo.
Facebook announced Thursday that it has built an artificial intelligence program that can “see” what it is looking at. He did this by providing her with over a billion public Instagram images.
The “computer vision” program, dubbed SEER, outperformed existing AI models in an object recognition test, Facebook said.
The program obtained a “Classification Accuracy Score” of 84.2% when it attempted a test provided by ImageNet, which is a large visual database designed for use in finding visual recognition software. objects. Basically, it tests if an AI program can identify the content of a photo.
New approach
While many AI models are trained on carefully labeled data sets, Facebook said SEER has learned to identify objects in photos by analyzing random, unlabeled and unsaturated Instagram images.
This AI technique is known as self-supervised learning. (SEER is a play on SElf-supERvised, according to an academic article Facebook researchers published about the work.)
“The future of AI lies in creating systems that can learn directly from the information given to them, be it text, images or some other type of data without s’ relying on carefully organized and labeled sets of data to teach them how to recognize objects in a photo, interpret a block of text, or perform one of the myriad other tasks we ask, ”the Facebook researchers wrote in an article blog.
“SEER’s performance demonstrates that self-supervised learning can excel at computer vision tasks in real environments,” they added.
“This is a breakthrough that paves the way for more flexible, precise and adaptable computer vision models in the future.”
Although this is only a research project, a Facebook spokesperson said the potential uses are relatively wide.
They include improved automatically generated text to describe images to visually impaired people, better automatic categorization of items sold on Facebook Marketplace, and better systems to keep harmful images away from the Facebook platform, the company said.
Confidentiality issue?
But many Instagram users may be surprised to learn that their images are 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 in technological advancements like this,” said Priya Goyal, software engineer at Facebook AI Research, at CNBC.
Facebook said it would open up some of its software for other researchers to experiment with.
“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 unsaturated images, we do not share the images or SEER mode, ”Goyal said.
Other big tech 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.
Source link
