时间：2026-10-04 20:13:09 来源：网络整理编辑：百科
Facebook's search tool is about to get way more visual. Director of Applied Machine Learning Joaquin
Facebook's search tool is about to get way more visual.
Director of Applied Machine Learning Joaquin Candela published a blog post today (accompanying his presentation at the Machine Learning @Scale event in New York City) to share updates about Facebook's AI-based image-recognition tool. The improvements can home in on photos to the "pixel level" and will let users search images based on their content -- whether or not they've been manually tagged.
"Until recently, online search has always been a text-driven technology, even when searching through images," he writes. "Whether an image was discoverable was dependent on whether it was sufficiently tagged or had the right caption -- until now."
SEE ALSO:How Facebook is trying to dominate mobile without owning your smartphoneAdvancements in Facebook's computer vision tech and the introduction of new tools will let users make much more targeted image searches. For instance, when you search your old photos, you'll be able to look for images where you're wearing a black shirt or red dress, or where the people in the image are dancing.
Facebook's computer-vision tools were originally envisioned to help the visually impaired navigate the service, discerning what's in a photo just by scanning it. But today's news shows general Facebook users have a lot to benefit from the feature as well.
Crediting "a lot" of teams for the advancements, Candela wrote that Facebook's general-purpose AI platform, FBLearner Flow, is now running 1.2 million AI experiments a month -- six times more than it was just a year ago.
Built on top of that is Lumos, Facebook's specialized platform for image and video understanding. Using Lumos, the network' search tool can identify features in images and video automatically. For users, that capability will help pinpoint searches to the exact pic they're looking for -- and for Facebook, the automation will make it easier to identify inappropriate content and spam.
These systems are also being employed to improve the platform's automatic alt text (AAT) for photos, which makes the visual aspects of the platform more accessible to the visually impaired. With the new tools, a set of 12 new actions, like "people dancing," have been added to the automatic image description.
TopicsArtificial IntelligenceFacebook
Fyvush Finkel, Emmy winner for 'Picket Fences,' dies at 932026-10-04 19:15
Rolling Stone loses defamation lawsuit over 'A Rape on Campus' article2026-10-04 18:50
How you can help Indigenous activists fight the Dakota Access Pipeline2026-10-04 18:43
17 Halloween costumes that definitely won't get you laid2026-10-04 18:39
Pole vaulter claims his penis is not to blame2026-10-04 18:33
Australia's coming for the Eurovision crown again, geography be damned2026-10-04 18:33
The 'Mannequin Challenge' is letting us live our sci2026-10-04 18:14
Netflix downloads could be here soon, but not for U.S. users2026-10-04 18:07
One of the most controversial power struggles in media comes to a close2026-10-04 17:46
Why men and women can't agree on the perfect temperature2026-10-04 17:39
17 questions you can answer if you're a good communicator2026-10-04 19:51
The Cubs and Bill Murray just dropped by 'Saturday Night Live' to sing a bit2026-10-04 19:20
Thor apologizes to Native Americans in Instagram post2026-10-04 19:03
Glowing Vincent van Gogh costume will illuminate your Halloween2026-10-04 18:45
This weird squid looks like it has googly eyes, guys2026-10-04 18:42
These live2026-10-04 18:32
Teen dressed as a water bottle for Halloween is flipping amazing2026-10-04 18:02
Russian artists' book bags let you wear your favorite novel as a purse2026-10-04 17:45
One of the most controversial power struggles in media comes to a close2026-10-04 17:38
The Cubs and Bill Murray just dropped by 'Saturday Night Live' to sing a bit2026-10-04 17:30
