sun-hailong/CVPR24-Ease

[CVPR 2024] The code repository for "Expandable Subspace Ensemble for Pre-Trained Model-Based Class-Incremental Learning" in PyTorch.

23
/ 100
Experimental

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.

continual-learning image-classification machine-vision model-adaptation deep-learning-research
No License Stale 6m No Package No Dependents
Maintenance 0 / 25
Adoption 9 / 25
Maturity 8 / 25
Community 6 / 25

How are scores calculated?

Stars

82

Forks

3

Language

Python

License

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.