Google Brain

It’s an exciting time for AI, with fascinating advances in generated media and many other applications, some even in science and medicine. Some folks may dream about what more AI can create and how much bigger models we may engineer.

Large models pretrained in an unsupervised fashion and then fine-tuned on a smaller corpus of labeled data have achieved spectacular results in natural language processing. New research pushes forward with a similar approach to computer vision.

If the world changes every second and you take a picture every 10 seconds, you won’t have enough pictures to observe the changes clearly, and storing a series of pictures won’t help. On the other hand, if you take a picture every tenth of a second, then storing a history will help model the world.

The previous state-of-the-art image classifier was trained on the ImageNet dataset plus 3.5 billion supplemental images from a different database. A new method achieved higher accuracy with one-tenth as many supplemental examples — and they were unlabeled, to boot.