Google AI Team Open Sources BiT – Big Transfer: General Visual Representation Learning (Computer Vision)

0
1817
Source: https://ai.googleblog.com/2020/05/open-sourcing-bit-exploring-large-scale.html
-Advertisement-

Google AI team recently open-source BiT (Big Transfer) for general visual representation learning. Current computer vision training generally involves a pre-trained model due to lack of labeled data for computer vision tasks. This has been a common problem for computer vision scientists to collect and train models with a large set of generic data available via tools like OpenImages or Places, but many times this collection of a large set of data (over 1M labeled images) could be prohibitive for an average practitioner.

The available solutions include using pre-trained models that are trained on generic data (example: ImageNet). Despite these pre-trained models working well in practice, this still doesn’t solve the problem for conditions like grasping news concepts and then to understand them in a different context. Just like how BERT and T5 have shown advances in the language domain, it is believed BiT based large-scale pre-training can advance the performance of computer vision models.

Advertisement

Paper: https://arxiv.org/abs/1912.11370

Github: https://github.com/google-research/big_transfer

BiT Models – Components of all TL blocks: https://tfhub.dev/google/collections/bit/1

https://ai.googleblog.com/2020/05/open-sourcing-bit-exploring-large-scale.html

LEAVE A REPLY

Please enter your comment!
Please enter your name here

This site uses Akismet to reduce spam. Learn how your comment data is processed.