Skip to content

itsmekhoathekid/CountingObject

 
 

Repository files navigation

Zero-Shot Text-Guided Object Counting with Exemplars

Overview

This repository presents a zero-shot text-guided object counting framework enhanced with exemplar-based learning. The system is designed to improve counting accuracy by explicitly modeling count-relevant visual features and suppressing background interference.

Key Contributions

  • Integrated a loss function that explicitly differentiates foreground objects from background regions, enabling the model to focus on count-relevant features.
  • Developed an exemplar extraction module to identify representative object instances from images and leverage these features during both training and evaluation.

Demo

Demo videos illustrating the counting performance and exemplar-guided inference are available at here

About

No description, website, or topics provided.

Resources

Stars

Watchers

Forks

Releases

No releases published

Packages

No packages published

Languages

  • Python 98.1%
  • Shell 1.9%