grypesc/SEED
ICLR2024 paper on Continual Learning
This project helps machine learning researchers evaluate methods for 'continual learning,' where a model learns new information over time without forgetting previously learned concepts. It takes standard image datasets, like CIFAR100 or ImageNet, and outputs performance metrics showing how well models adapt to new tasks while retaining old knowledge. Researchers focused on developing robust and adaptive AI systems would find this useful.
No commits in the last 6 months.
Use this if you are a machine learning researcher evaluating continual learning algorithms, especially in image classification tasks.
Not ideal if you are looking for a pre-trained model to deploy in an application or if your primary interest is in domains other than image classification.
Stars
36
Forks
7
Language
Python
License
MIT
Category
Last pushed
Apr 21, 2024
Commits (30d)
0
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/ml-frameworks/grypesc/SEED"
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.