Facebook open-sources object detection work: Watch out, Google CAPTCHA

The bicycle's top left. I'm not an AI... you are. Stop hitting yourself

By Jude Karabus

Posted in Artificial Intelligence, 23rd January 2018 14:29 GMT

RoTM Facebook has brought us one step closer to a Skynet future made a commitment to computer vision boffinry by open-sourcing its codebase for object detection, Detectron.

Written in Python and powered by the Caffe2 deep learning framework, the codebase – which implements object-sniffing algos such as Mask R-CNN and RetinaNet – is available under the Apache 2.0 licence.

Want to learn machine learning in 15 minutes? Start here...

READ MORE

CAPTCHA jokes aside – it's about more than just identifying what's in an image. Normally, when we look at a still pic or video, we see multiple overlapping things and calculate their relative distances; relationship to each other; the fact that foreground and background objects are affected by the focal length of the camera (or the human eye); as well as where one object ends and the other begins. If your training data includes moving pics, you'll might need to look at relative size, positioning, or partial obstruction from frame to frame. These are some of the problems that ML researchers in the computer vision game – and specifically in object detection – are attempting to solve.

Fbook's framework includes implementations of algos that can not only detect and classify objects but can also simultaneously generate segmentation masks. Identifying selected regions of images as members of a group helps train a model to identify other objects of said group. Judging by Facebook's illustration in the blog (depicting a Mask R-CNN output), some researchers are achieving a decent hit rate.

Detectron is the basis for many research projects at Facebook AI research – aka FAIR. The Zuckerborgs said researchers will be able to train models to be deployed in the cloud and on smartmobes and other mobile devices.

We can't help but picture a future where Zuckerbots and Googleborgs attempt to trick each other's computer vision while human users arm ourselves with blurry spatulas/chairs/lasers in hopes of fighting off the Machines. ®

Sign up to our NewsletterGet IT in your inbox daily

19 Comments

More from The Register

Intel adds vision to its AI vision with computer vision firm buyout

Eyes up Movidius, reaches for its wallet

We see what you're up to, Intel, with your eye-o-tee vision

Chipzilla slurps computer vision company Itseez to target autonomous cars

Oculus adds Surreal Vision to its virty portfolio

British devs are quids in with purchase

Blade Runner 2049 review: Scott's vision versus Villeneuve's skill

No spoilers Let me tell you about my mother

Amount of pixels needed to make VR less crap may set your PC on fire

Wow, this is incredib- BLEEUUURGHGHGH

Well, now Nuro: Former Waymo devs reveal cute self-driving van tech

Bijou robo-courier powered by electricity and $92m in VC cash

Your shoe, chewing gum, or ciggies are now your extra password

Boffins explore personal items as 2FA tokens using computer vision code

Has science gone too far, part 97: Boffins craft code to find protesters on social networks, rate them on their violence

Image-recognition system posited as reporting tool

Baidu puts open source deep learning into smartphones

Computer vision, deep learning, and the camera in your phone

Tesla's driverless car software chief steps down

Chris Lattner 'wasn't the right fit', says Elon Musk-led biz