mlsanityData to 13 Oct 2026

EfficientViT-SAM: Accelerated Segment Anything Model Without Accuracy Loss

arXiv 2402.05008 ↗First posted 7 Feb 2024cs.CV cs.AI cs.LGcited by 3

Not on the map. Why?

Abstract (arXiv)

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.

Key facts. Cited by 3 papers in the map (data through 13 Oct 2026). Builds on 23 of its 24 references that are in the map. First posted on arXiv 7 Feb 2024.

Builds on

23 of 24 references.

References · 23

  1. 2015Deep Residual Learning for Image Recognitioncited by 51,950
  2. 2014Microsoft COCO: Common Objects in Contextcited by 17,550
  3. 2015Distilling the Knowledge in a Neural Networkcited by 10,180
  4. 2023Segment Anythingcited by 8,195
  5. 2017MobileNets: Efficient Convolutional Neural Networks for Mobile Vision Applicationscited by 3,836
  6. 2023Grounding DINO: Marrying DINO with Grounded Pre-Training for Open-Set Object Detectioncited by 3,299
  7. 2015Deep Compression: Compressing Deep Neural Networks with Pruning, Trained Quantization and Huffman Codingcited by 2,315
  8. 2015Learning both Weights and Connections for Efficient Neural Networkscited by 2,017
  9. 2019LVIS: A Dataset for Large Vocabulary Instance Segmentationcited by 1,215
  10. 2021EfficientNetV2: Smaller Models and Faster Trainingcited by 1,130
  11. 2019Once-for-All: Train One Network and Specialize it for Efficient Deploymentcited by 783
  12. 2022Exploring Plain Vision Transformer Backbones for Object Detectioncited by 724
11 more
  1. 2018ProxylessNAS: Direct Neural Architecture Search on Target Task and Hardwarecited by 670
  2. 2023Zero123++: a Single Image to Consistent Multi-view Diffusion Base Modelcited by 518
  3. 2023Faster Segment Anything: Towards Lightweight SAM for Mobile Applicationscited by 347
  4. 2022Generalized Decoding for Pixel, Image, and Languagecited by 293
  5. 2023One-2-3-45++: Fast Single Image to 3D Objects with Consistent Multi-View Generation and 3D Diffusioncited by 283
  6. 2023Inpaint Anything: Segment Anything Meets Image Inpaintingcited by 233
  7. 2023Track Anything: Segment Anything Meets Videoscited by 230
  8. 2023Segment and Track Anythingcited by 193
  9. 2023EfficientSAM: Leveraged Masked Image Pretraining for Efficient Segment Anythingcited by 187
  10. 2023EdgeSAM: Prompt-In-the-Loop Distillation for SAMcited by 40
  11. 2023TinySAM: Pushing the Envelope for Efficient Segment Anything Modelcited by 33

Built on by

Cited by year

Citing papers per year: 2024: 1; 2025: 2.

3 papers.

  1. 2024De-LightSAM: Modality-Decoupled Lightweight SAM for Generalizable Medical Segmentationcited by 11
  2. 2025SegDAC: Visual Generalization in Reinforcement Learning via Dynamic Object Tokenscited by 0
  3. 2025Tiny-YOLOSAM: Fast Hybrid Image Segmentationcited by 0