sun-hailong/CVPR24-Ease
[CVPR 2024] The code repository for "Expandable Subspace Ensemble for Pre-Trained Model-Based Class-Incremental Learning" in PyTorch.
This project helps machine learning researchers and practitioners who are building image classification systems that need to learn new categories over time without forgetting previously learned ones. It takes a pre-trained image classification model and new image datasets for additional classes, producing an updated model capable of classifying both old and new categories more accurately. It's designed for those working on incremental learning problems in computer vision.
No commits in the last 6 months.
Use this if you need to continuously update an existing image classification model with new visual categories without degrading its performance on the categories it already knows.
Not ideal if your task involves learning entirely new domains or if you are not working with pre-trained vision models for classification.
Stars
82
Forks
3
Language
Python
License
—
Category
Last pushed
Apr 01, 2025
Commits (30d)
0
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/ml-frameworks/sun-hailong/CVPR24-Ease"
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.