TensorX
返回文献探索

Paper · arXiv 2402.05008

EfficientViT-SAM: Accelerated Segment Anything Model Without Performance Loss

Zhuoyang Zhang, Han Cai, Song Han

24 upvotesFebruary 7, 2024arXiv 预印本
AI 摘要

EfficientViT-SAM combines SAM's prompt encoder and mask decoder with EfficientViT as the image encoder, achieving significant speedup without losing performance.

EfficientViT-SAMSAM-ViT-Hknowledge distillationend-to-end trainingSA-1B datasetTensorRTA100 GPU

Abstract

We present EfficientViT-SAM, a new family of accelerated segment anything models. We retain SAM's lightweight prompt encoder and mask decoder while replacing the heavy image encoder with EfficientViT. For the training, we begin with the knowledge distillation from the SAM-ViT-H image encoder to EfficientViT. Subsequently, we conduct end-to-end training on the SA-1B dataset. Benefiting from EfficientViT's efficiency and capacity, EfficientViT-SAM delivers 48.9x measured TensorRT speedup on A100 GPU over SAM-ViT-H without sacrificing performance. Our code and pre-trained models are released at https://github.com/mit-han-lab/efficientvit.

北京市昌平区探索星信息技术及软件开发工作室

京ICP备2026059466号
EfficientViT-SAM: Accelerated Segment Anything Model Without Performance Loss | TensorX