Facebook trains artificial intelligence to ‘see’ using 1 billion public Instagram photos – tech2.org

Facebook trains artificial intelligence to ‘see’ using 1 billion public Instagram photos


A person who uses Instagram.

Lorenzo Di Cola | NurPhoto via Getty Images

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 company owner Facebook is using this treasure to teach machines what is in a photo.

Facebook announced Thursday that it had built an artificial intelligence program that can “see” what it is looking at. It did so by feeding it over a billion public Instagram images.

The “computer vision” program, dubbed SEER, outperformed existing artificial intelligence 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 for use in visual object recognition software research. Basically, it tests whether an artificial intelligence program can identify what is in a photo.

New focus

While many AI models are trained on carefully labeled data sets, Facebook said SEER learned to identify objects in photos by analyzing random, untagged, and uncured Instagram images. This AI technique is known as self-supervised learning (SEER is a SElf-supERvised game).

“The future of AI is in creating systems that can learn directly from whatever information is given to them, be it text, images or other types of data, without relying on carefully selected and labeled data sets to teach them how to recognize objects. on a photo, interpret a block of text, or perform any of the myriad other tasks we ask of you, “wrote the Facebook researchers in a blog post.

“SEER’s performance demonstrates that self-supervised learning can excel at computer vision tasks in real-world settings,” they added. “This is a breakthrough that ultimately clears the way for more flexible, accurate and adaptable computer vision models in the future.”

While this is just a research project, a Facebook spokesperson said the potential uses were relatively wide. They include improved auto-generated text to describe images to the visually impaired, better automatic categorization of items sold on Facebook Marketplace, and better systems for keeping harmful images away from the Facebook platform, the company said.

Privacy issues?

But many Instagram users may be surprised to learn that their images are used to train Facebook’s artificial intelligence systems.

“We inform Instagram account holders in our data policy that we use the information we have to support research and innovation, including technological advancements like this,” Priya Goyal, software engineer at Facebook AI Research, told CNBC.

Facebook said it will make some of its open source software open 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 raw images, we are not sharing the images or the SEER mode,” Goyal said.

Other big tech companies, like Google and Microsoft, are also trying to push the boundaries of computer vision. Last summer, Google published the SimCLRv2 computer vision model, while OpenAI published iGPT 2.

.

Source link