all AI news
Can SAM Count Anything? An Empirical Study on SAM Counting. (arXiv:2304.10817v1 [cs.CV])
cs.CV updates on arXiv.org arxiv.org
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 …
arxiv attention code count examples fine-tuning meta meta ai objects performance sam segment anything model small study