Meta AI recently released the Segment Anything model (SAM), which has garnered attention due to its impressive performance in class-agnostic segmenting. In this study, we explore the use of SAM for the challenging task of few-shot object counting, which involves counting objects of an unseen category by providing a few bounding boxes of examples. We compare SAM's performance with other few-shot counting methods and find that it is currently unsatisfactory without further fine-tuning, particularly for small and crowded objects. Code can be found at \url{https://github.com/Vision-Intelligence-and-Robots-Group/count-anything}.
@article{arxiv.2304.10817,
title = {Can SAM Count Anything? An Empirical Study on SAM Counting},
author = {Zhiheng Ma and Xiaopeng Hong and Qinnan Shangguan},
journal= {arXiv preprint arXiv:2304.10817},
year = {2023}
}
Comments
An empirical study on few-shot counting using Meta AI's segment anything model