zzf495/ICSC

The implementation of ICSC: Domain Adaptation via Incremental Confidence Samples into Classification

21
/ 100
Experimental

This tool helps scientists and researchers adapt existing image classification models to new, but related, image datasets without needing to retrain the model from scratch. You input an image classification model trained on a 'source' dataset and a 'target' dataset you want to classify, and it provides an improved classifier for the target dataset. It's designed for machine learning practitioners and researchers working with computer vision tasks.

No commits in the last 6 months.

Use this if you have an image classification model that performs well on one dataset, but struggles with a new, similar dataset, and you want to improve its accuracy on the new data without extensive re-labeling or full retraining.

Not ideal if you are looking for a general-purpose, out-of-the-box image classification solution for completely unrelated datasets, or if you don't have existing labeled source data.

image-classification computer-vision model-adaptation machine-learning-research dataset-transfer
Stale 6m No Package No Dependents
Maintenance 0 / 25
Adoption 5 / 25
Maturity 16 / 25
Community 0 / 25

How are scores calculated?

Stars

10

Forks

Language

MATLAB

License

MIT

Last pushed

Dec 06, 2022

Commits (30d)

0

Get this data via API

curl "https://pt-edge.onrender.com/api/v1/quality/ml-frameworks/zzf495/ICSC"

Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.