acmi-lab/CHILS

Code and results accompanying our paper titled CHiLS: Zero-Shot Image Classification with Hierarchical Label Sets

33
/ 100
Emerging

This project helps machine learning researchers or practitioners classify images into categories even when they haven't seen any examples for those specific categories during training. It takes existing images and a list of categories, then produces predictions for what each image depicts, especially useful when categories are organized hierarchically. This is for users working with large or novel image datasets where traditional training for every single category is impractical.

No commits in the last 6 months.

Use this if you need to classify images into a wide range of categories, including many for which you have no prior training data, and especially if those categories have a natural hierarchical structure (e.g., 'animal' -> 'dog' -> 'golden retriever').

Not ideal if you already have ample labeled training data for all your target image categories and are looking for a standard supervised image classification solution.

Image Classification Machine Learning Research Computer Vision Zero-Shot Learning Dataset Analysis
Stale 6m No Package No Dependents
Maintenance 0 / 25
Adoption 8 / 25
Maturity 16 / 25
Community 9 / 25

How are scores calculated?

Stars

60

Forks

5

Language

Python

License

MIT

Last pushed

Jun 04, 2023

Commits (30d)

0

Get this data via API

curl "https://pt-edge.onrender.com/api/v1/quality/ml-frameworks/acmi-lab/CHILS"

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