Check it out, some sort of facial Recognition system, but then with entire images! A sort Object Recognition FaceBook AI…. Hmmm
(Normally you do not see this, only exposed with FaceBook half down like it is today):
#FaceBook is half down, #images not displaying fully, BUT, I see, I see, some secret #metadata?? — #facialRecognition #privacy Object Recognition Software at work: pic.twitter.com/zBn12W7U75
— Pijnacker01 (@Pijnacker01) July 3, 2019
Our researchers and engineers have addressed this by training image recognition networks on large sets of public images with hashtags, the biggest of which included 3.5 billion images and 17,000 hashtags. The crux of this approach is using existing, public, user-supplied hashtags as labels instead of manually categorizing each picture. This approach has worked well in our testing. By training our computer vision system with a 1 billion-image version of this data set, we achieved a record-high score — 85.4 percent accuracy — on ImageNet, a common benchmarking tool. Along with enabling this genuine breakthrough in image recognition performance, this research offers important insight into how to shift from supervised to weakly supervised training, where we use existing labels — in this case, hashtags — rather than ones that are chosen and applied specifically for AI training. We plan to open source the embeddings of these models in the future, so the research community at large can use and build on these representations for high-level tasks.
MORE:
h/t 2012