BiT: Exploring Large-Scale Pre-training for Compute
We are excited to share the best BiT models pre-trained on public datasets, along with code in TF2, Jax, and PyTorch.
object-detection computer-vision pretraining models tf-hub bit tensorflow pytorch tutorial
Resource links
Top collections
Details
Objectives & Highlights

Even though this pre-training works reasonably well in practice, it still falls short of the ability to both quickly grasp new concepts and understand them in different contexts. In a similar spirit to how BERT and T5 have shown advances in the language domain, we believe that large-scale pre-training can advance the performance of computer vision models.

Takeaways & Next Steps

We are excited to share the best BiT models pre-trained on public datasets, along with code in TF2, Jax, and PyTorch. This will allow anyone to reach state-of-the-art performance on their task of interest, even with just a handful of labeled images per class.

Don't forget to tag @lucasb-eyer in your comment.

Authors community post
Just some dude.
Share this project
Similar projects
An Intuitive Guide to Deep Network Architectures
Intuition behind base network architectures like MobileNets, Inception, and ResNet.
Object-detection with multi-template matching
This python package allows to perform object detection using one or a few template images, it provides a simpler alternative to deep-learning methods
Deep Tutorials for PyTorch
This is a series of in-depth tutorials I'm writing for implementing cool deep learning models on your own with the amazing PyTorch library.
Deep Learning for Object Detection: A Comprehensive Review
A closer look at Tensorflow’s object detection models: Faster R-CNN, R-FCN, and SSD.