paper-with-me

Papers

EfficientViT-SAM: Accelerated Segment Anything Model Without Accuracy Loss

2024-02-07 · Zhuoyang Zhang, Han Cai, Song Han

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.

📄 PDF Abstract BibTeX arXiv:2402.05008

Code (1)

mit-han-lab/efficientvit 공식 구현 pytorch

Tasks

DecoderGPUKnowledge DistillationZero-Shot Instance Segmentation

Methods 이 논문이 사용한 방법론

Knowledge Distillation A very simple way to improve the performance of almost any machine learning algorithm is to train many different models on the same data and then to average their predictions.…

Similar Papers 제목 키워드 기반

Efficient Segment Anything with Depth-Aware Fusion and Limited Training Data

2026-02-12 · Yiming Zhou, Xuenjie Xie, Panfeng Li, Albrecht Kunz 외 arxiv

Segment Anything Models (SAM) achieve impressive universal segmentation performance but require massive datasets (e.g., 11M images) and rely solely on RGB inputs. Recent efficient variants reduce computation but still de…

EfficientViT: Multi-Scale Linear Attention for High-Resolution Dense Prediction

2022-05-29 · Han Cai, Junyan Li, Muyan Hu, Chuang Gan 외

High-resolution dense prediction enables many appealing real-world applications, such as computational photography, autonomous driving, etc. However, the vast computational cost makes deploying state-of-the-art high-reso…

Autonomous DrivingCPUGPUImage Classification+8

EfficientSAM3: Progressive Hierarchical Distillation for Video Concept Segmentation from SAM1, 2, and 3

2025-11-19 · Chengxi Zeng, Yuxuan Jiang, Aaron Zhang arxiv

The Segment Anything Model 3 (SAM3) advances visual understanding with Promptable Concept Segmentation (PCS) across images and videos, but its unified architecture (shared vision backbone, DETR-style detector, dense-memo…

EfficientViT: Memory Efficient Vision Transformer with Cascaded Group Attention

2023-05-11 · CVPR 2023 1 · Xinyu Liu, Houwen Peng, Ningxin Zheng, Yuqing Yang 외

Vision transformers have shown great success due to their high model capabilities. However, their remarkable performance is accompanied by heavy computation costs, which makes them unsuitable for real-time applications. …

CPUGPU

Onboard Satellite Image Classification for Earth Observation: A Comparative Study of ViT Models

2024-09-05 · Thanh-Dung Le, Vu Nguyen Ha, Ti Ti Nguyen, Geoffrey Eappen 외

This study focuses on identifying the most effective pre-trained model for land use classification in onboard satellite processing, emphasizing achieving high accuracy, computational efficiency, and robustness against no…

Computational EfficiencyEarth Observationimage-classificationImage Classification+2