bwnzheng/MRFA_ICML2024

The code repository for "Multi-layer Rehearsal Feature Augmentation for Class-Incremental Learning" (ICML24)

25
/ 100
Experimental

This project helps machine learning practitioners who are continually training models on new data without forgetting old classes. It takes your existing class-incremental learning setup and enhances it, resulting in models that maintain better performance on previously learned categories while adapting to new ones. Data scientists and AI researchers working with evolving datasets will find this useful.

No commits in the last 6 months.

Use this if you are encountering 'catastrophic forgetting' in your class-incremental learning models, where training on new classes degrades performance on previously learned ones.

Not ideal if you are working with a static dataset or do not need your machine learning models to adapt incrementally to new data classes over time.

Machine Learning Continual Learning Incremental Learning Data Science AI Research
No License Stale 6m No Package No Dependents
Maintenance 0 / 25
Adoption 5 / 25
Maturity 8 / 25
Community 12 / 25

How are scores calculated?

Stars

11

Forks

2

Language

Python

License

Last pushed

Jun 07, 2024

Commits (30d)

0

Get this data via API

curl "https://pt-edge.onrender.com/api/v1/quality/ml-frameworks/bwnzheng/MRFA_ICML2024"

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