dddzg/up-detr

[TPAMI 2022 & CVPR2021 Oral] UP-DETR: Unsupervised Pre-training for Object Detection with Transformers

46
/ 100
Emerging

This project helps computer vision practitioners train models to automatically identify and locate objects within images, even when they have limited labeled data. You provide raw image datasets, and the system learns general object recognition capabilities without needing extensive manual annotations. The output is a highly effective object detection model that can then be fine-tuned for specific tasks.

489 stars. No commits in the last 6 months.

Use this if you need to build object detection models but want to reduce the dependency on large, costly, human-annotated datasets for initial training.

Not ideal if you require object detection for highly specialized or obscure objects that are significantly different from general real-world objects, or if you don't have access to substantial unlabeled image data.

computer-vision object-detection image-analysis machine-learning-training data-efficiency
Stale 6m No Package No Dependents
Maintenance 0 / 25
Adoption 10 / 25
Maturity 16 / 25
Community 20 / 25

How are scores calculated?

Stars

489

Forks

72

Language

Python

License

Apache-2.0

Last pushed

Jul 19, 2023

Commits (30d)

0

Get this data via API

curl "https://pt-edge.onrender.com/api/v1/quality/transformers/dddzg/up-detr"

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