Connect with us

FACEBOOK

Computer vision inches toward ‘common sense’ with Facebook’s latest research

Published

on

Machine learning is capable of doing all sorts of things as long as you have the data to teach it how. That’s not always easy, and researchers are always looking for a way to add a bit of “common sense” to AI so you don’t have to show it 500 pictures of a cat before it gets it. Facebook’s newest research takes a big step toward reducing the data bottleneck.

The company’s formidable AI research division has been working for years now on how to advance and scale things like advanced computer vision algorithms, and has made steady progress, generally shared with the rest of the research community. One interesting development Facebook has pursued in particular is what’s called “semi-supervised learning.”

Generally when you think of training an AI, you think of something like the aforementioned 500 pictures of cats — images that have been selected and labeled (which can mean outlining the cat, putting a box around the cat or just saying there’s a cat in there somewhere) so that the machine learning system can put together an algorithm to automate the process of cat recognition. Naturally if you want to do dogs or horses, you need 500 dog pictures, 500 horse pictures, etc. — it scales linearly, which is a word you never want to see in tech.

Semi-supervised learning, related to “unsupervised” learning, involves figuring out important parts of a data set without any labeled data at all. It doesn’t just go wild, there’s still structure; for instance, imagine you give the system a thousand sentences to study, then showed it 10 more that have several of the words missing. The system could probably do a decent job filling in the blanks just based on what it’s seen in the previous thousand. But that’s not so easy to do with images and video — they aren’t as straightforward or predictable.

See also  Facebook and Instagram block #StormTheCapitol, lock Trump out of posting for 24 hours

But Facebook researchers have shown that while it may not be easy, it’s possible and in fact very effective. The DINO system (which stands rather unconvincingly for “DIstillation of knowledge with NO labels”) is capable of learning to find objects of interest in videos of people, animals and objects quite well without any labeled data whatsoever.

Animation showing four videos and the AI interpretation of the objects in them.

Image Credits: Facebook

It does this by considering the video not as a sequence of images to be analyzed one by one in order, but as a complex, interrelated set, like the difference between “a series of words” and “a sentence.” By attending to the middle and the end of the video as well as the beginning, the agent can get a sense of things like “an object with this general shape goes from left to right.” That information feeds into other knowledge, like when an object on the right overlaps with the first one, the system knows they’re not the same thing, just touching in those frames. And that knowledge in turn can be applied to other situations. In other words, it develops a basic sense of visual meaning, and does so with remarkably little training on new objects.

This results in a computer vision system that’s not only effective — it performs well compared with traditionally trained systems — but more relatable and explainable. For instance, while an AI that has been trained with 500 dog pictures and 500 cat pictures will recognize both, it won’t really have any idea that they’re similar in any way. But DINO — although it couldn’t be specific — gets that they’re similar visually to one another, more so anyway than they are to cars, and that metadata and context is visible in its memory. Dogs and cats are “closer” in its sort of digital cognitive space than dogs and mountains. You can see those concepts as little blobs here — see how those of a type stick together:

Advertisement
Animated diagram showing how concepts in the machine learning model stay close together.

Image Credits: Facebook

This has its own benefits, of a technical sort we won’t get into here. If you’re curious, there’s more detail in the papers linked in Facebook’s blog post.

There’s also an adjacent research project, a training method called PAWS, which further reduces the need for labeled data. PAWS combines some of the ideas of semi-supervised learning with the more traditional supervised method, essentially giving the training a boost by letting it learn from both the labeled and unlabeled data.

Facebook of course needs good and fast image analysis for its many user-facing (and secret) image-related products, but these general advances to the computer vision world will no doubt be welcomed by the developer community for other purposes.

TechCrunch

FACEBOOK

Facebook fighting against disinformation: Launch new options

Published

on

Meta, the parent company of Facebook, has dismantled new malicious networks that used vaccine debates to harass professionals or sow division in some countries, a sign that disinformation about the pandemic, spread for political ends, is on the wane not.

“They insulted doctors, journalists and elected officials, calling them supporters of the Nazis because they were promoting vaccines against the Covid, ensuring that compulsory vaccination would lead to a dictatorship of health,” explained Mike Dvilyanski, director investigations into emerging threats, at a press conference on Wednesday.

He was referring to a network linked to an anti-vaccination movement called “V_V”, which the Californian group accuses of having carried out a campaign of intimidation and mass harassment in Italy and France, against health figures, media and politics.

The authors of this operation coordinated in particular via the Telegram messaging system, where the volunteers had access to lists of people to target and to “training” to avoid automatic detection by Facebook.

Their tactics included leaving comments under victims’ messages rather than posting content, and using slightly changed spellings like “vaxcinati” instead of “vaccinati”, meaning “people vaccinated” in Italian.

The social media giant said it was difficult to assess the reach and impact of the campaign, which took place across different platforms.

This is a “psychological war” against people in favor of vaccines, according to Graphika, a company specializing in the analysis of social networks, which published Wednesday a report on the movement “V_V”, whose name comes from the Italian verb “vivere” (“to live”).

“We have observed what appears to be a sprawling populist movement that combines existing conspiratorial theories with anti-authoritarian narratives, and a torrent of health disinformation,” experts detail.

Advertisement

They estimate that “V_V” brings together some 20,000 supporters, some of whom have taken part in acts of vandalism against hospitals and operations to interfere with vaccinations, by making medical appointments without honoring them, for example.

See also  Social media marketers need fresh tactics for posting on CTV apps

Change on Facebook

Facebook announces news that will facilitate your sales and purchases on the social network.

Mark Zuckerberg, the boss of Facebook, announced that the parent company would now be called Meta, to better represent all of its activities, from social networks to virtual reality, but the names of the different services will remain unchanged. A month later, Meta is already announcing news for the social network.

The first is the launch of online stores in Facebook groups. A “Shop” tab will appear and will allow members to buy products directly through the group in question.

Other features have been communicated with the aim of facilitating e-commerce within the social network, such as the display of recommendations and a better mention of products or even Live Shopping. At this time, no date has been announced regarding the launch of these new options.

In the light of recent features, the company wants to know the feedback from its users through the survey same like what Tesco doing to get its customers feedback via Tesco Views Survey. However, the company is still about this feedback will announce sooner than later in this regard.

Continue Reading

DON'T MISS ANY IMPORTANT NEWS!
Subscribe To our Newsletter
We promise not to spam you. Unsubscribe at any time.
Invalid email address

Trending