amirbar/DETReg

Official implementation of the CVPR 2022 paper "DETReg: Unsupervised Pretraining with Region Priors for Object Detection".

45
/ 100
Emerging

This project helps computer vision practitioners train object detection models more effectively, especially when they have limited labeled data. It takes in collections of images (like ImageNet or COCO) and produces a highly capable object detection model that can accurately locate and identify objects within new images. It is ideal for researchers and engineers working on advanced computer vision applications.

338 stars. No commits in the last 6 months.

Use this if you need to develop robust object detection models but struggle with obtaining vast amounts of manually labeled training data.

Not ideal if you are looking for a plug-and-play solution for general image classification or a tool for basic image editing.

object-detection computer-vision machine-learning-research model-pretraining low-data-learning
Stale 6m No Package No Dependents
Maintenance 0 / 25
Adoption 10 / 25
Maturity 16 / 25
Community 19 / 25

How are scores calculated?

Stars

338

Forks

48

Language

Python

License

Apache-2.0

Last pushed

Jul 18, 2023

Commits (30d)

0

Get this data via API

curl "https://pt-edge.onrender.com/api/v1/quality/computer-vision/amirbar/DETReg"

Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.