RepViT-SAM: Towards Real-Time Segmenting Anything

Fuente: arXiv
Salvato in:
Dettagli Bibliografici
Autori principali: Wang, Ao, Chen, Hui, Lin, Zijia, Han, Jungong, Ding, Guiguang
Natura: Preprint
Pubblicazione: 2023
Soggetti:
Accesso online:
Tags: Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
_version_ 1866913247478677504
author Wang, Ao
Chen, Hui
Lin, Zijia
Han, Jungong
Ding, Guiguang
author_facet Wang, Ao
Chen, Hui
Lin, Zijia
Han, Jungong
Ding, Guiguang
contents Segment Anything Model (SAM) has shown impressive zero-shot transfer performance for various computer vision tasks recently. However, its heavy computation costs remain daunting for practical applications. MobileSAM proposes to replace the heavyweight image encoder in SAM with TinyViT by employing distillation, which results in a significant reduction in computational requirements. However, its deployment on resource-constrained mobile devices still encounters challenges due to the substantial memory and computational overhead caused by self-attention mechanisms. Recently, RepViT achieves the state-of-the-art performance and latency trade-off on mobile devices by incorporating efficient architectural designs of ViTs into CNNs. Here, to achieve real-time segmenting anything on mobile devices, following MobileSAM, we replace the heavyweight image encoder in SAM with RepViT model, ending up with the RepViT-SAM model. Extensive experiments show that RepViT-SAM can enjoy significantly better zero-shot transfer capability than MobileSAM, along with nearly $10\times$ faster inference speed. The code and models are available at \url{https://github.com/THU-MIG/RepViT}.
format Preprint
id arxiv_https___arxiv_org_abs_2312_05760
institution arXiv
publishDate 2023
record_format arxiv
spellingShingle RepViT-SAM: Towards Real-Time Segmenting Anything
Wang, Ao
Chen, Hui
Lin, Zijia
Han, Jungong
Ding, Guiguang
Computer Vision and Pattern Recognition
Segment Anything Model (SAM) has shown impressive zero-shot transfer performance for various computer vision tasks recently. However, its heavy computation costs remain daunting for practical applications. MobileSAM proposes to replace the heavyweight image encoder in SAM with TinyViT by employing distillation, which results in a significant reduction in computational requirements. However, its deployment on resource-constrained mobile devices still encounters challenges due to the substantial memory and computational overhead caused by self-attention mechanisms. Recently, RepViT achieves the state-of-the-art performance and latency trade-off on mobile devices by incorporating efficient architectural designs of ViTs into CNNs. Here, to achieve real-time segmenting anything on mobile devices, following MobileSAM, we replace the heavyweight image encoder in SAM with RepViT model, ending up with the RepViT-SAM model. Extensive experiments show that RepViT-SAM can enjoy significantly better zero-shot transfer capability than MobileSAM, along with nearly $10\times$ faster inference speed. The code and models are available at \url{https://github.com/THU-MIG/RepViT}.
title RepViT-SAM: Towards Real-Time Segmenting Anything
topic Computer Vision and Pattern Recognition
url https://arxiv.org/abs/2312.05760