Recommendable! The latest and greatest from Facebook's AI research into computer vision! Impressive! The performance of ever larger models in computer vision is catching up with the large pretrained models in natural language processing.
"... Facebook AI has now brought this self-supervised learning paradigm shift to computer vision. We’ve developed
SEER (SElf-supERvised), a new billion-parameter self-supervised computer vision model that can learn from any random group of images on the internet — without the need for careful curation and labeling that goes into most computer vision training today. ...
After pretraining on a billion random, unlabeled and uncurated public Instagram images, SEER outperformed the most advanced, state-of-the-art self-supervised systems, reaching 84.2 percent top-1 accuracy on ImageNet. SEER also outperformed state-of-the-art supervised models on downstream tasks, including low-shot, object detection, segmentation, and image classification. When trained with just 10 percent of the examples in the ImageNet data set, SEER still achieved 77.9 percent top-1 accuracy on the full data set. When trained with just 1 percent of the annotated ImageNet examples, SEER achieved 60.5 percent top-1 accuracy."
After pretraining on a billion random, unlabeled and uncurated public Instagram images, SEER outperformed the most advanced, state-of-the-art self-supervised systems, reaching 84.2 percent top-1 accuracy on ImageNet. SEER also outperformed state-of-the-art supervised models on downstream tasks, including low-shot, object detection, segmentation, and image classification. When trained with just 10 percent of the examples in the ImageNet data set, SEER still achieved 77.9 percent top-1 accuracy on the full data set. When trained with just 1 percent of the annotated ImageNet examples, SEER achieved 60.5 percent top-1 accuracy."
Here is the link to the referenced preprint paper:
Credits to VentureBeat:
No comments:
Post a Comment