google-research/l2p

Learning to Prompt (L2P) for Continual Learning @ CVPR22 and DualPrompt: Complementary Prompting for Rehearsal-free Continual Learning @ ECCV22

43
/ 100
Emerging

This project offers an advanced method to train AI models that can continuously learn new image recognition tasks without forgetting previously learned information. It takes in pre-trained image recognition models and new image datasets, producing a model that excels at identifying objects across many different, sequentially learned categories. This is designed for AI researchers and practitioners who develop or apply machine learning models in dynamic environments.

471 stars. No commits in the last 6 months.

Use this if you need to continually update an image recognition model with new data or tasks over time, especially in situations where storing old data for 'rehearsal' is not feasible or efficient.

Not ideal if your image recognition tasks are static and don't require continuous adaptation or learning new categories sequentially.

continual-learning image-recognition machine-learning-research model-adaptation sequential-learning
Stale 6m No Package No Dependents
Maintenance 0 / 25
Adoption 10 / 25
Maturity 16 / 25
Community 17 / 25

How are scores calculated?

Stars

471

Forks

47

Language

Python

License

Apache-2.0

Last pushed

Jul 30, 2024

Commits (30d)

0

Get this data via API

curl "https://pt-edge.onrender.com/api/v1/quality/prompt-engineering/google-research/l2p"

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