mlsanityData to 14 Oct 2026

Fast Segment Anything

arXiv 2306.12156 ↗First posted 21 Jun 2023cs.CV cs.AIcited by 290

Not on the map. Why?

Abstract (arXiv)

The recently proposed segment anything model (SAM) has made a significant influence in many computer vision tasks. It is becoming a foundation step for many high-level tasks, like image segmentation, image caption, and image editing. However, its huge computation costs prevent it from wider applications in industry scenarios. The computation mainly comes from the Transformer architecture at high-resolution inputs. In this paper, we propose a speed-up alternative method for this fundamental task with comparable performance. By reformulating the task as segments-generation and prompting, we find that a regular CNN detector with an instance segmentation branch can also accomplish this task well. Specifically, we convert this task to the well-studied instance segmentation task and directly train the existing instance segmentation method using only 1/50 of the SA-1B dataset published by SAM authors. With our method, we achieve a comparable performance with the SAM method at 50 times higher run-time speed. We give sufficient experimental results to demonstrate its effectiveness. The codes and demos will be released at https://github.com/CASIA-IVA-Lab/FastSAM.

Key facts. Cited by 290 papers in the map (data through 14 Oct 2026). Builds on 20 of its 34 references that are in the map. First posted on arXiv 21 Jun 2023.

Builds on

20 of 34 references.

References · 20

  1. 2021Learning Transferable Visual Models From Natural Language Supervisioncited by 33,744
  2. 2014Microsoft COCO: Common Objects in Contextcited by 17,608
  3. 2015Faster R-CNN: Towards Real-Time Object Detection with Region Proposal Networkscited by 9,639
  4. 2023Segment Anythingcited by 8,234
  5. 2020End-to-End Object Detection with Transformerscited by 7,414
  6. 2016Feature Pyramid Networks for Object Detectioncited by 5,036
  7. 2015Fast R-CNNcited by 2,933
  8. 2019LVIS: A Dataset for Large Vocabulary Instance Segmentationcited by 1,217
  9. 2021Per-Pixel Classification is Not All You Need for Semantic Segmentationcited by 1,152
  10. 2021YOLOX: Exceeding YOLO Series in 2021cited by 1,071
  11. 2022YOLOv7: Trainable bag-of-freebies sets new state-of-the-art for real-time object detectorscited by 982
  12. 2018Panoptic Segmentationcited by 802
8 more
  1. 2015Holistically-Nested Edge Detectioncited by 592
  2. 2019YOLACT: Real-time Instance Segmentationcited by 443
  3. 2021Learning Open-World Object Proposals without Learning to Classifycited by 109
  4. 2014Salient Object Detection: A Surveycited by 98
  5. 2015Learning to Segment Object Candidatescited by 79
  6. 2023Detecting Everything in the Open World: Towards Universal Object Detectioncited by 62
  7. 2020Learning Selective Mutual Attention and Contrast for RGB-D Saliency Detectioncited by 38
  8. 2022EDTER: Edge Detection with Transformercited by 36

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2023: 31; 2024: 104; 2025: 87; 2026: 68.

290 papers.

Sort:

By area:

  1. 2023Faster Segment Anything: Towards Lightweight SAM for Mobile Applicationscited by 352
  2. 2023Tracking Anything with Decoupled Video Segmentationcited by 197
  3. 2023EfficientSAM: Leveraged Masked Image Pretraining for Efficient Segment Anythingcited by 188
  4. 2025FoundationStereo: Zero-Shot Stereo Matchingcited by 173
  5. 2023SAM-6D: Segment Anything Model Meets Zero-Shot 6D Object Pose Estimationcited by 117
  6. 2023SAM-CLIP: Merging Vision Foundation Models towards Semantic and Spatial Understandingcited by 111
  7. 2023Foundational Models Defining a New Era in Vision: A Survey and Outlookcited by 110
  8. 2024SAMURAI: Adapting Segment Anything Model for Zero-Shot Visual Tracking with Motion-Aware Memorycited by 94
  9. 2023Talk2BEV: Language-enhanced Bird's-eye View Maps for Autonomous Drivingcited by 89
  10. 2023CNOS: A Strong Baseline for CAD-based Novel Object Segmentationcited by 87
  11. 2024General Flow as Foundation Affordance for Scalable Robot Learningcited by 85
  12. 2023Foundational Models in Medical Imaging: A Comprehensive Survey and Future Visioncited by 76
38 more
  1. 2024Open-Vocabulary SAM: Segment and Recognize Twenty-thousand Classes Interactivelycited by 75
  2. 2024Image-of-Thought Prompting for Visual Reasoning Refinement in Multimodal Large Language Modelscited by 65
  3. 2024EVF-SAM: Early Vision-Language Fusion for Text-Prompted Segment Anything Modelcited by 65
  4. 2023FreeZe: Training-free zero-shot 6D pose estimation with geometric and vision foundation modelscited by 57
  5. 2023Adapting Segment Anything Model for Change Detection in HR Remote Sensing Imagescited by 56
  6. 2024Watermark Anything with Localized Messagescited by 53
  7. 2025Perceive Anything: Recognize, Explain, Caption, and Segment Anything in Images and Videoscited by 51
  8. 2025Move to Understand a 3D Scene: Bridging Visual Grounding and Exploration for Efficient and Versatile Embodied Navigationcited by 51
  9. 2023SPOC: Imitating Shortest Paths in Simulation Enables Effective Navigation and Manipulation in the Real Worldcited by 48
  10. 2023A New Learning Paradigm for Foundation Model-based Remote Sensing Change Detectioncited by 47
  11. 2024Surgical SAM 2: Real-time Segment Anything in Surgical Video by Efficient Frame Pruningcited by 47
  12. 2024IRSAM: Advancing Segment Anything Model for Infrared Small Target Detectioncited by 46
  13. 2023MobileSAMv2: Faster Segment Anything to Everythingcited by 42
  14. 2024EmbodiedSAM: Online Segment Any 3D Thing in Real Timecited by 40
  15. 2023SAM-Assisted Remote Sensing Imagery Semantic Segmentation with Object and Boundary Constraintscited by 35
  16. 2024Segment Any Changecited by 35
  17. 2024CorrCLIP: Reconstructing Patch Correlations in CLIP for Open-Vocabulary Semantic Segmentationcited by 34
  18. 2024PTQ4SAM: Post-Training Quantization for Segment Anythingcited by 32
  19. 2024SAGD: Boundary-Enhanced Segment Anything in 3D Gaussian via Gaussian Decompositioncited by 30
  20. 2024Hi-SAM: Marrying Segment Anything Model for Hierarchical Text Segmentationcited by 30
  21. 2024Moving Object Segmentation: All You Need Is SAM (and Flow)cited by 30
  22. 2024Open-YOLO 3D: Towards Fast and Accurate Open-Vocabulary 3D Instance Segmentationcited by 30
  23. 2023Follow Anything: Open-set detection, tracking, and following in real-timecited by 29
  24. 2024CAT-SAM: Conditional Tuning for Few-Shot Adaptation of Segment Anything Modelcited by 27
  25. 2024AIDE: An Automatic Data Engine for Object Detection in Autonomous Drivingcited by 26
  26. 2024OpenECAD: An Efficient Visual Language Model for Editable 3D-CAD Designcited by 26
  27. 2025Dynam3D: Dynamic Layered 3D Tokens Empower VLM for Vision-and-Language Navigationcited by 23
  28. 2024SuperGaussian: Repurposing Video Models for 3D Super Resolutioncited by 22
  29. 2023Text Augmented Spatial-aware Zero-shot Referring Image Segmentationcited by 21
  30. 2023Segment Change Model (SCM) for Unsupervised Change detection in VHR Remote Sensing Images: a Case Study of Buildingscited by 21
  31. 2024Subobject-level Image Tokenizationcited by 21
  32. 2024Efficient Track Anythingcited by 21
  33. 2025EdgeTAM: On-Device Track Anything Modelcited by 21
  34. 2025DynamicEarth: How Far are We from Open-Vocabulary Change Detection?cited by 21
  35. 2023SlimSAM: 0.1% Data Makes Segment Anything Slimcited by 20
  36. 2025SegDINO: An Efficient Design for Medical and Natural Image Segmentation with DINO-V3cited by 20
  37. 2023FoodSAM: Any Food Segmentationcited by 19
  38. 2024Revisit Anything: Visual Place Recognition via Image Segment Retrievalcited by 19

50 most cited of 290 All 290 (JSON)