GECO2-demo / README.md
jerpelhan's picture
Update README.md
f7ef64f verified
|
raw
history blame
1.06 kB
metadata
title: GeCo2 Gradio Demo
sdk: gradio
sdk_version: 4.44.1
python_version: 3.10.13
app_file: demo_gradio.py

GeCo2: Count Anything with Few Examples

GeCo2 is a few-shot, category-agnostic detection counter. With only a small number of exemplars, GeCo2 can identify and count all instances of the target object in an image—without predefined classes or retraining.

Key Features

  • Count anything: works for arbitrary object categories
  • Few-shot: requires only a handful of exemplars
  • Robust: handles scale variation and diverse visual domains

Demo Description

Provide a few exemplar annotations for the object of interest, and GeCo2 will propagate this visual concept across the image to detect and count all matching instances. This makes the demo suitable for rapid exploration of novel object categories and domains where labeled data is scarce.


This demo was build using the GeCo2 model and the demo bases on the CountGD demo.