Enregistré dans:
Détails bibliographiques
Auteurs principaux: Fu, Jianhai, Yu, Yuanjie, Li, Ningchuan, Zhang, Yi, Chen, Qichao, Xiong, Jianping, Yin, Jun, Xiang, Zhiyu
Format: Preprint
Publié: 2024
Sujets:
Accès en ligne:https://arxiv.org/abs/2407.08965
Tags: Ajouter un tag
Pas de tags, Soyez le premier à ajouter un tag!
_version_ 1866917720276074496
author Fu, Jianhai
Yu, Yuanjie
Li, Ningchuan
Zhang, Yi
Chen, Qichao
Xiong, Jianping
Yin, Jun
Xiang, Zhiyu
author_facet Fu, Jianhai
Yu, Yuanjie
Li, Ningchuan
Zhang, Yi
Chen, Qichao
Xiong, Jianping
Yin, Jun
Xiang, Zhiyu
contents This paper introduces Lite-SAM, an efficient end-to-end solution for the SegEvery task designed to reduce computational costs and redundancy. Lite-SAM is composed of four main components: a streamlined CNN-Transformer hybrid encoder (LiteViT), an automated prompt proposal network (AutoPPN), a traditional prompt encoder, and a mask decoder. All these components are integrated within the SAM framework. Our LiteViT, a high-performance lightweight backbone network, has only 1.16M parameters, which is a 23% reduction compared to the lightest existing backbone network Shufflenet. We also introduce AutoPPN, an innovative end-to-end method for prompt boxes and points generation. This is an improvement over traditional grid search sampling methods, and its unique design allows for easy integration into any SAM series algorithm, extending its usability. we have thoroughly benchmarked Lite-SAM across a plethora of both public and private datasets. The evaluation encompassed a broad spectrum of universal metrics, including the number of parameters, SegEvery execution time, and accuracy. The findings reveal that Lite-SAM, operating with a lean 4.2M parameters, significantly outpaces its counterparts, demonstrating performance improvements of 43x, 31x, 20x, 21x, and 1.6x over SAM, MobileSAM, Edge-SAM, EfficientViT-SAM, and MobileSAM-v2 respectively, all the while maintaining competitive accuracy. This underscores Lite-SAM's prowess in achieving an optimal equilibrium between performance and precision, thereby setting a new state-of-the-art(SOTA) benchmark in the domain.
format Preprint
id arxiv_https___arxiv_org_abs_2407_08965
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle Lite-SAM Is Actually What You Need for Segment Everything
Fu, Jianhai
Yu, Yuanjie
Li, Ningchuan
Zhang, Yi
Chen, Qichao
Xiong, Jianping
Yin, Jun
Xiang, Zhiyu
Computer Vision and Pattern Recognition
Machine Learning
This paper introduces Lite-SAM, an efficient end-to-end solution for the SegEvery task designed to reduce computational costs and redundancy. Lite-SAM is composed of four main components: a streamlined CNN-Transformer hybrid encoder (LiteViT), an automated prompt proposal network (AutoPPN), a traditional prompt encoder, and a mask decoder. All these components are integrated within the SAM framework. Our LiteViT, a high-performance lightweight backbone network, has only 1.16M parameters, which is a 23% reduction compared to the lightest existing backbone network Shufflenet. We also introduce AutoPPN, an innovative end-to-end method for prompt boxes and points generation. This is an improvement over traditional grid search sampling methods, and its unique design allows for easy integration into any SAM series algorithm, extending its usability. we have thoroughly benchmarked Lite-SAM across a plethora of both public and private datasets. The evaluation encompassed a broad spectrum of universal metrics, including the number of parameters, SegEvery execution time, and accuracy. The findings reveal that Lite-SAM, operating with a lean 4.2M parameters, significantly outpaces its counterparts, demonstrating performance improvements of 43x, 31x, 20x, 21x, and 1.6x over SAM, MobileSAM, Edge-SAM, EfficientViT-SAM, and MobileSAM-v2 respectively, all the while maintaining competitive accuracy. This underscores Lite-SAM's prowess in achieving an optimal equilibrium between performance and precision, thereby setting a new state-of-the-art(SOTA) benchmark in the domain.
title Lite-SAM Is Actually What You Need for Segment Everything
topic Computer Vision and Pattern Recognition
Machine Learning
url https://arxiv.org/abs/2407.08965