Training-free Object Counting with Prompts

TL;DR

This paper introduces a training-free object counting method using the Segment Anything Model with prior-guided mask generation, enabling accurate counting without extensive data or training.

Contribution

It proposes a novel training-free counting approach leveraging SAM and priors, improving efficiency and accuracy over existing methods.

Findings

Competitive performance on standard datasets

Effective class-specific object counting without training

Enhanced accuracy with prior-guided segmentation

Abstract

This paper tackles the problem of object counting in images. Existing approaches rely on extensive training data with point annotations for each object, making data collection labor-intensive and time-consuming. To overcome this, we propose a training-free object counter that treats the counting task as a segmentation problem. Our approach leverages the Segment Anything Model (SAM), known for its high-quality masks and zero-shot segmentation capability. However, the vanilla mask generation method of SAM lacks class-specific information in the masks, resulting in inferior counting accuracy. To overcome this limitation, we introduce a prior-guided mask generation method that incorporates three types of priors into the segmentation process, enhancing efficiency and accuracy. Additionally, we tackle the issue of counting objects specified through text by proposing a two-stage approach that combines reference object selection and prior-guided mask generation. Extensive experiments on standard datasets demonstrate the competitive performance of our training-free counter compared to learning-based approaches. This paper presents a promising solution for counting objects in various scenarios without the need for extensive data collection and counting-specific training. Code is available at \url{https://github.com/shizenglin/training-free-object-counter}