Can SAM Count Anything? An Empirical Study on SAM Counting
This addresses the problem of few-shot counting for unseen categories in computer vision, but it is incremental as it evaluates an existing model on a new task.
The study investigated whether the Segment Anything Model (SAM) could be effectively used for few-shot object counting, finding that its performance was unsatisfactory without fine-tuning, especially for small and crowded objects.
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}.