bwnzheng/MRFA_ICML2024
The code repository for "Multi-layer Rehearsal Feature Augmentation for Class-Incremental Learning" (ICML24)
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.
Stars
11
Forks
2
Language
Python
License
—
Category
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.
Higher-rated alternatives
aimagelab/mammoth
An Extendible (General) Continual Learning Framework based on Pytorch - official codebase of...
LAMDA-CL/PyCIL
PyCIL: A Python Toolbox for Class-Incremental Learning
GMvandeVen/continual-learning
PyTorch implementation of various methods for continual learning (XdG, EWC, SI, LwF, FROMP, DGR,...
LAMDA-CL/LAMDA-PILOT
🎉 PILOT: A Pre-trained Model-Based Continual Learning Toolbox
mmasana/FACIL
Framework for Analysis of Class-Incremental Learning with 12 state-of-the-art methods and 3 baselines.