TinySAM: Pushing the Envelope for Efficient Segment Anything Model

arXiv:2312.13789v2 Announce Type: replace
Abstract: Recently segment anything model (SAM) has shown powerful segmentation capability and has drawn great attention in computer vision fields. Massive following works have developed various applications based on the pretrained SAM and achieved impressive performance on downstream vision tasks.
However, SAM consists of heavy architectures and requires massive computational capacity, which hinders the further application of SAM on computation constrained edge devices. To this end, in this paper we propose a framework to obtain a …

abstract applications arxiv attention capability computer computer vision cs.cv fields massive performance sam segment segment anything segment anything model segmentation tasks type vision