CUHK-AIM-Group/CLIFF

[ECCV' 24 Oral] CLIFF: Continual Latent Diffusion for Open-Vocabulary Object Detection

29
/ 100
Experimental

This project helps computer vision researchers and AI practitioners develop and evaluate models that can detect a wide range of objects in images, even those not seen during training. You input an image and get back identified objects along with their bounding boxes and labels. It's designed for those pushing the boundaries of object detection beyond predefined categories.

No commits in the last 6 months.

Use this if you need an object detection model capable of identifying novel or open-vocabulary objects in images without retraining for each new category.

Not ideal if you primarily work with a fixed set of object categories and only need standard, closed-vocabulary object detection.

computer-vision object-detection image-analysis AI-research model-development
Stale 6m No Package No Dependents
Maintenance 0 / 25
Adoption 7 / 25
Maturity 16 / 25
Community 6 / 25

How are scores calculated?

Stars

29

Forks

2

Language

Python

License

MIT

Last pushed

Sep 26, 2024

Commits (30d)

0

Get this data via API

curl "https://pt-edge.onrender.com/api/v1/quality/diffusion/CUHK-AIM-Group/CLIFF"

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