yinboc/DGP

Rethinking Knowledge Graph Propagation for Zero-Shot Learning, in CVPR 2019

47
/ 100
Emerging

This project helps computer vision researchers expand the capabilities of image recognition systems to identify entirely new categories of objects they haven't been specifically trained on. It takes existing image classification models and knowledge graphs (like WordNet) as input and outputs an enhanced model capable of 'zero-shot learning' — recognizing objects from unseen classes. This is for researchers and practitioners in machine learning and computer vision who need to build more adaptable and generalized image recognition systems.

321 stars. No commits in the last 6 months.

Use this if you are developing computer vision models and need to enable them to recognize object categories they have never encountered during training, leveraging semantic relationships between concepts.

Not ideal if you are looking for an out-of-the-box solution for standard image classification where all target classes are known and available for training.

computer-vision image-recognition zero-shot-learning knowledge-graphs machine-learning-research
Stale 6m No Package No Dependents
Maintenance 0 / 25
Adoption 10 / 25
Maturity 16 / 25
Community 21 / 25

How are scores calculated?

Stars

321

Forks

57

Language

Python

License

MIT

Last pushed

Jun 22, 2019

Commits (30d)

0

Get this data via API

curl "https://pt-edge.onrender.com/api/v1/quality/ml-frameworks/yinboc/DGP"

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