OatmealLiu/FineR

[ICLR'24] Democratizing Fine-grained Visual Recognition with Large Language Models

35
/ 100
Emerging

This project helps scientists and researchers in fields like biology or zoology identify specific species or variants of objects from images. It takes a small set of example images and uses language models to discover and describe the subtle visual differences. The output is a highly accurate categorization of fine-grained images, even for categories that were not explicitly labeled beforehand.

190 stars. No commits in the last 6 months.

Use this if you need to classify images into very specific, nuanced categories (like different bird species or car models) without extensive manual annotation or predefined category names.

Not ideal if you are looking for broad object detection or classification into general categories, or if you don't have a few example images per fine-grained category for discovery.

biological-classification species-identification product-variant-recognition visual-taxonomy image-categorization
Stale 6m No Package No Dependents
Maintenance 0 / 25
Adoption 10 / 25
Maturity 16 / 25
Community 9 / 25

How are scores calculated?

Stars

190

Forks

8

Language

Python

License

Apache-2.0

Last pushed

Jul 15, 2024

Commits (30d)

0

Get this data via API

curl "https://pt-edge.onrender.com/api/v1/quality/transformers/OatmealLiu/FineR"

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