mlsanityData to 14 Oct 2026

On Efficient Variants of Segment Anything Model: A Survey

arXiv 2410.04960 ↗First posted 7 Oct 2024cs.CVcited by 16

Not on the map. Why?

Abstract (arXiv)

The Segment Anything Model (SAM) is a foundational model for image segmentation tasks, known for its strong generalization across diverse applications. However, its impressive performance comes with significant computational and resource demands, making it challenging to deploy in resource-limited environments such as edge devices. To address this, a variety of SAM variants have been proposed to enhance efficiency while keeping accuracy. This survey provides the first comprehensive review of these efficient SAM variants. We begin by exploring the motivations driving this research. We then present core techniques used in SAM and model acceleration. This is followed by a detailed exploration of SAM acceleration strategies, categorized by approach, and a discussion of several future research directions. Finally, we offer a unified and extensive evaluation of these methods across various hardware, assessing their efficiency and accuracy on representative benchmarks, and providing a clear comparison of their overall performance.

Key facts. Cited by 16 papers in the map (data through 14 Oct 2026). Builds on 172 of its 275 references that are in the map. First posted on arXiv 7 Oct 2024.

Builds on

172 of 275 references.

References · 172

  1. 2017Attention Is All You Needcited by 60,361
  2. 2015Deep Residual Learning for Image Recognitioncited by 52,096
  3. 2021Learning Transferable Visual Models From Natural Language Supervisioncited by 33,744
  4. 2020Language Models are Few-Shot Learnerscited by 32,419
  5. 2020An Image is Worth 16x16 Words: Transformers for Image Recognition at Scalecited by 30,186
  6. 2015U-Net: Convolutional Networks for Biomedical Image Segmentationcited by 19,713
  7. 2023GPT-4 Technical Reportcited by 18,396
  8. 2014Microsoft COCO: Common Objects in Contextcited by 17,608
  9. 2023LLaMA: Open and Efficient Foundation Language Modelscited by 14,132
  10. 2023Llama 2: Open Foundation and Fine-Tuned Chat Modelscited by 13,028
  11. 2021Swin Transformer: Hierarchical Vision Transformer using Shifted Windowscited by 12,139
  12. 2015Distilling the Knowledge in a Neural Networkcited by 10,324
38 more
  1. 2023Segment Anythingcited by 8,234
  2. 2023Visual Instruction Tuningcited by 7,869
  3. 2021Masked Autoencoders Are Scalable Vision Learnerscited by 7,403
  4. 2015Batch Normalization: Accelerating Deep Network Training by Reducing Internal Covariate Shiftcited by 7,005
  5. 2016Layer Normalizationcited by 5,669
  6. 2022PaLM: Scaling Language Modeling with Pathwayscited by 5,326
  7. 2016Feature Pyramid Networks for Object Detectioncited by 5,036
  8. 2018MobileNetV2: Inverted Residuals and Linear Bottleneckscited by 4,795
  9. 2017Squeeze-and-Excitation Networkscited by 4,789
  10. 2023Mamba: Linear-Time Sequence Modeling with Selective State Spacescited by 4,718
  11. 2021On the Opportunities and Risks of Foundation Modelscited by 4,033
  12. 2022FlashAttention: Fast and Memory-Efficient Exact Attention with IO-Awarenesscited by 3,673
  13. 2022A ConvNet for the 2020scited by 3,579
  14. 2023Grounding DINO: Marrying DINO with Grounded Pre-Training for Open-Set Object Detectioncited by 3,332
  15. 2024SAM 2: Segment Anything in Images and Videoscited by 2,863
  16. 2023A Survey of Large Language Modelscited by 2,576
  17. 2021Efficiently Modeling Long Sequences with Structured State Spacescited by 2,465
  18. 2021Pre-train, Prompt, and Predict: A Systematic Survey of Prompting Methods in Natural Language Processingcited by 2,234
  19. 2022GPTQ: Accurate Post-Training Quantization for Generative Pre-trained Transformerscited by 1,919
  20. 2017Deformable Convolutional Networkscited by 1,488
  21. 2019LVIS: A Dataset for Large Vocabulary Instance Segmentationcited by 1,217
  22. 2023PaLM 2 Technical Reportcited by 1,162
  23. 2021Perceiver: General Perception with Iterative Attentioncited by 1,104
  24. 2023Video-ChatGPT: Towards Detailed Video Understanding via Large Vision and Language Modelscited by 1,062
  25. 2024Vision Mamba: Efficient Visual Representation Learning with Bidirectional State Space Modelcited by 1,056
  26. 2020Designing Network Design Spacescited by 960
  27. 2021DynamicViT: Efficient Vision Transformers with Dynamic Token Sparsificationcited by 864
  28. 2023RWKV: Reinventing RNNs for the Transformer Eracited by 827
  29. 2022Exploring Plain Vision Transformer Backbones for Object Detectioncited by 724
  30. 2024KAN: Kolmogorov-Arnold Networkscited by 649
  31. 2021MobileViT: Light-weight, General-purpose, and Mobile-friendly Vision Transformercited by 642
  32. 2022Detecting Twenty-thousand Classes using Image-level Supervisioncited by 614
  33. 2023Retentive Network: A Successor to Transformer for Large Language Modelscited by 613
  34. 2023Segment Everything Everywhere All at Oncecited by 548
  35. 2022ZeroQuant: Efficient and Affordable Post-Training Quantization for Large-Scale Transformerscited by 526
  36. 2021MetaFormer Is Actually What You Need for Visioncited by 524
  37. 2021MViTv2: Improved Multiscale Vision Transformers for Classification and Detectioncited by 519
  38. 2022Hungry Hungry Hippos: Towards Language Modeling with State Space Modelscited by 499

50 most cited of 172 All 172 (JSON)

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2025: 13; 2026: 3.

16 papers.

Sort:

By area:

  1. 2025ROS-SAM: High-Quality Interactive Segmentation for Remote Sensing Moving Objectcited by 15
  2. 2025SAM2 for Image and Video Segmentation: A Comprehensive Surveycited by 13
  3. 2026LMMs Meet Object-Centric Vision: Understanding, Segmentation, Editing and Generationcited by 6
  4. 2025Can Foundation Models Really Segment Tumors? A Benchmarking Odyssey in Lung CT Imagingcited by 5
  5. 2025Segment This Thing: Foveated Tokenization for Efficient Point-Prompted Segmentationcited by 5
  6. 2025EfficientSAM3: Progressive Hierarchical Distillation for Video Concept Segmentation from SAM1, 2, and 3cited by 4
  7. 2025AHCQ-SAM: Toward Accurate and Hardware-Compatible Post-Training Segment Anything Model Quantizationcited by 3
  8. 2025Prompt Engineering in Segment Anything Model: Methodologies, Applications, and Emerging Challengescited by 3
  9. 2025Segment Anything for Video: A Comprehensive Review of Video Object Segmentation and Tracking from Past to Futurecited by 2
  10. 2025The SAM2-to-SAM3 Gap in the Segment Anything Model Family: Why Prompt-Based Expertise Fails in Concept-Driven Image Segmentationcited by 2
  11. 2026Efficient-SAM2: Accelerating SAM2 with Object-Aware Visual Encoding and Memory Retrievalcited by 2
  12. 2025Towards Explicit Geometry-Reflectance Collaboration for Generalized LiDAR Segmentation in Adverse Weathercited by 1
4 more
  1. 2025Towards Generalized Range-View LiDAR Segmentation in Adverse Weathercited by 0
  2. 2025Promptable Fire Segmentation: Unleashing SAM2's Potential for Real-Time Mobile Deployment with Strategic Bounding Box Guidancecited by 0
  3. 2025AD-SAM: Adapting the Segment Anything Model for Semantic Segmentation in Autonomous Drivingcited by 0
  4. 2026Lean-SAM2: Target-Anchored Memory and Encoder Acceleration for SAM2cited by 0