Facebook opens up its image-recognition AI software to everyone

facebook messenger virus malware windows chrome facebookcomp head
The AI research division at Facebook is open sourcing its image recognition software with the aim of advancing the tech so it can one day be applied to live video. Facebook’s DeepMask, SharpMask, and MultiPathNet software is now available to everyone on GitHub.

Facebook previously laid out its image-recognition systems in a number of research papers, which are also being made available to the public along with its demos. At present, the company’s algorithms work in conjunction with its MultiPathNet convolutional neural networks — an AI that is fed huge amounts of data until it can autonomously recognize other data — allowing Facebook to understand an image based on each pixel it contains.

In order to classify and label the objects in an image, Facebook couples its DeepMask segmentation framework with its SharpMask segment refinement module. The final stage in Facebook’s machine vision system utilizes its MultiPathNet deep learning AI to label each object in the photo.

According to Facebook, AI machine vision software has progressed in leaps and bounds over the past few years, allowing the type of image classification that didn’t even exist a short while ago. Facebook claims that open sourcing the software is critical to its advancement.

Example images scanned by Facebook's complete image-recognition system
Example images scanned by Facebook’s complete image-recognition system

Deep learning techniques are springing up all over the big blue behemoth. The AI powers Facebook’s (controversial) facial-recognition feature, manages curation on its News Feed, and is even utilized within its digital assistant for Messenger.

This isn’t the first time Facebook has open sourced its AI. In fact, the company is somewhat of a trailblazer when it comes to sharing its tech. In December, Facebook submitted its state-of-the-art computer server dedicated to AI to the Open Compute Project — a group consisting of tech giants, such as Apple and Microsoft, that share the designs of their respective computer infrastructures.

Facebook is already predicting the future use cases for the image-recognition tech. The company reveals that it could potentially help it to build upon its existing AI generated image descriptions for the visually impaired.

“Currently, visually impaired users browsing photos on Facebook only hear the name of the person who shared the photo, followed by the term “photo,” when they come upon an image in their News Feed,” writes Piotr Dollar, research scientist at Facebook AI Research (FAIR), in a blog post. “Instead we aim to offer richer descriptions, such as ‘Photo contains beach, trees, and three smiling people.’”

Additionally, Facebook claims that its next challenge is to apply its image-recognition techniques to video, “where objects are moving, interacting, and changing over time,” and even Facebook Live broadcasts. “Real-time classification could help surface relevant and important Live videos on Facebook, while applying more refined techniques to detect scenes, objects, and actions over space and time could one day allow for real-time narration,” Dollar adds.


Peloton’s tech lets truckers play follow the leader to boost fuel economy

Peloton Technology can help semi trucks save fuel by running close together on the highway. Using short-range wireless communications, the trucks get a kind of super cruise control.

Need a free alternative to Adobe Illustrator? Here are our favorites

Photoshop and other commercial tools can be expensive, but drawing software doesn't need to be. This list of the best free drawing software is just as powerful as some of the more expensive offerings.

From DIY to AAA, here's how to take a passport photo in 6 different ways

If you're applying for a passport or renewing one, you need to submit a photo in your official application. There are strict guidelines, but fortunately, it's something you can do at home. Here's how to take a passport photo.
Emerging Tech

Face-scanning A.I. can help doctors spot unusual genetic disorders

Facial recognition can unlock your phone. Could it also be used to identify whether a person has a rare genetic disorder, based on their facial features? New research suggests it can.

Protect your expensive new laptop with the best Macbook cases

If you recently picked up a new MacBook, you’ll want something to protect its gorgeous exterior. Here, we've gathered the best MacBook cases and covers, whether you're looking for style or protection.

Watch out for these top-10 mistakes people make when buying a laptop

Buying a new laptop is exciting, but you need to watch your footing. There are a number of pitfalls you need to avoid and we're here to help. Check out these top-10 laptop buying mistakes and how to avoid them.
Product Review

LG Gram 14 proves 2-in-1 laptops don’t need to sacrifice battery for light weight

The LG Gram 14 2-in-1 aims to be very light for a laptop that converts to a tablet. And it is. But it doesn’t skimp on the battery, and so it lasts a very long time on a charge.

Don't spend a fortune on a PC. These are the best laptops under $300

Buying a laptop needn't mean spending a fortune. If you're just looking to browse the internet, answer emails, and watch Netflix, you can pick up a great laptop at a great price. These are the best laptops under $300.

Dell XPS 13 vs. Asus Zenbook 13: In battle of champions, who will be the victor?

The ZenBook 13 UX333 continues Asus's tradition of offering great budget-oriented 13-inch laptop offerings. Does this affordable machine offer enough value to compete with the excellent Dell XPS 13?

Take a trip to a new virtual world with one of these awesome HTC Vive games

So you’re considering an HTC Vive, but don't know which games to get? Our list of 25 of the best HTC Vive games will help you out, whether you're into rhythm-based gaming, interstellar dogfights, or something else entirely.

The Asus ZenBook 13 offers more value and performance than Apple's MacBook Air

The Asus ZenBook 13 UX333 is the latest in that company's excellent "budget" laptop line, and it looks and feels better than ever. How does it compare to Apple's latest MacBook Air?

AMD Radeon VII will support DLSS-like upscaling developed by Microsoft

AMD's Radeon VII has shown promise with early tests of an open DLSS-like technology developed by Microsoft called DirectML. It would provide similar upscale features, but none of the locks on hardware choice.

You could be gaming on AMD’s Navi graphics card before the end of the summer

If you're waiting for a new graphics card from AMD that doesn't cost $700, you may have to wait for Navi. But that card may not be far away, with new rumors suggesting we could see a July launch.

Is AMD's Navi back on track for 2019? Here's everything you need to know

With a reported launch in 2019, AMD is focusing on the mid-range market with its next-generation Navi GPU. Billed as a successor to Polaris, Navi promises to deliver better performance to consoles, like Sony's PlayStation 5.