altndrr/vic

Code implementation of our NeurIPS 2023 paper: Vocabulary-free Image Classification

30
/ 100
Emerging

This project helps anyone working with images by providing a way to classify them using descriptions, without needing a pre-set list of categories. You input an image, and it outputs a highly relevant descriptive label, even for nuanced or new concepts. It's designed for professionals who need flexible, descriptive image tagging.

107 stars. No commits in the last 6 months.

Use this if you need to classify images into categories that are unknown or evolve rapidly, or if you require highly specific and descriptive labels beyond a fixed vocabulary.

Not ideal if you already have a well-defined and unchanging list of image categories for classification, as it adds unnecessary complexity for that scenario.

image-tagging visual-content-analysis semantic-search digital-asset-management unsupervised-classification
Stale 6m No Package No Dependents
Maintenance 0 / 25
Adoption 9 / 25
Maturity 16 / 25
Community 5 / 25

How are scores calculated?

Stars

107

Forks

3

Language

Python

License

MIT

Last pushed

Feb 02, 2024

Commits (30d)

0

Get this data via API

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

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