winci-ai/resa

An official implementation of ReSA (ICML 2025)

39
/ 100
Emerging

ReSA helps machine learning practitioners efficiently train image recognition models without needing large amounts of labeled data. It takes raw, unlabeled image datasets and produces highly effective image encoders. These encoders can then be used for various downstream tasks like classifying images into categories or identifying specific objects within them.

Use this if you need to build robust image classification or recognition systems, especially when acquiring vast amounts of labeled image data is impractical or too expensive.

Not ideal if your primary goal is natural language processing or tabular data analysis, as this project is specifically designed for computer vision tasks.

image-classification computer-vision unsupervised-learning deep-learning data-efficient-ai
No Package No Dependents
Maintenance 6 / 25
Adoption 7 / 25
Maturity 16 / 25
Community 10 / 25

How are scores calculated?

Stars

25

Forks

3

Language

Python

License

Apache-2.0

Last pushed

Nov 23, 2025

Commits (30d)

0

Get this data via API

curl "https://pt-edge.onrender.com/api/v1/quality/ml-frameworks/winci-ai/resa"

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