SinicaGroup/Class-agnostic-Few-shot-Object-Counting

pytorch implementation of a WACV 2021 Paper "Class-agnostic Few-shot-Object-Counting"

39
/ 100
Emerging

This project helps researchers and computer vision practitioners accurately count specific objects within images, even if those objects are rare or new. You provide a few example images of the objects you want to count, and it outputs the total count of those objects in a new, larger image. It's ideal for those working with visual data who need precise object enumeration without extensive training data.

118 stars. No commits in the last 6 months.

Use this if you need to count specific objects in images, especially if you only have a handful of example images for the objects of interest and don't want to collect a large dataset.

Not ideal if you need to detect and localize objects rather than just count them, or if you already have a large, labeled dataset for your specific object counting task.

image-analysis object-counting computer-vision few-shot-learning research
Stale 6m No Package No Dependents
Maintenance 0 / 25
Adoption 10 / 25
Maturity 16 / 25
Community 13 / 25

How are scores calculated?

Stars

118

Forks

12

Language

Python

License

MIT

Last pushed

Sep 22, 2022

Commits (30d)

0

Get this data via API

curl "https://pt-edge.onrender.com/api/v1/quality/ml-frameworks/SinicaGroup/Class-agnostic-Few-shot-Object-Counting"

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