RaptorMai/online-continual-learning
A collection of online continual learning paper implementations and tricks for computer vision in PyTorch, including our ASER(AAAI-21), SCR(CVPR21-W) and survey (Neurocomputing).
When you need to keep your image classification models accurate as new classes or variations of images are introduced over time, this project offers solutions. It takes existing image datasets that are updated sequentially and provides methods to continuously train your models. The output is a robust image classification model that adapts to new data without forgetting what it learned before. This is for machine learning practitioners and researchers focused on computer vision.
417 stars. No commits in the last 6 months.
Use this if you are developing or evaluating image classification systems that need to learn new categories or adapt to changing image conditions dynamically without re-training from scratch on all historical data.
Not ideal if you are working with static datasets where all categories are known upfront, or if your primary task is not image classification.
Stars
417
Forks
61
Language
Python
License
—
Category
Last pushed
May 30, 2023
Commits (30d)
0
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/ml-frameworks/RaptorMai/online-continual-learning"
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.