mlsanityData to 14 Oct 2026

Segment Anything Is Not Always Perfect: An Investigation of SAM on Different Real-world Applications

arXiv 2304.05750 ↗First posted 12 Apr 2023cs.CVcited by 121

Not on the map. Why?

Abstract (arXiv)

Recently, Meta AI Research approaches a general, promptable Segment Anything Model (SAM) pre-trained on an unprecedentedly large segmentation dataset (SA-1B). Without a doubt, the emergence of SAM will yield significant benefits for a wide array of practical image segmentation applications. In this study, we conduct a series of intriguing investigations into the performance of SAM across various applications, particularly in the fields of natural images, agriculture, manufacturing, remote sensing, and healthcare. We analyze and discuss the benefits and limitations of SAM, while also presenting an outlook on its future development in segmentation tasks. By doing so, we aim to give a comprehensive understanding of SAM's practical applications. This work is expected to provide insights that facilitate future research activities toward generic segmentation. Source code is publicly available.

Key facts. Cited by 121 papers in the map (data through 14 Oct 2026). Builds on 27 of its 66 references that are in the map. First posted on arXiv 12 Apr 2023.

Builds on

27 of 66 references.

References · 27

  1. 2021Learning Transferable Visual Models From Natural Language Supervisioncited by 33,744
  2. 2023Segment Anythingcited by 8,234
  3. 2017Skin Lesion Analysis Toward Melanoma Detection: A Challenge at the 2017 International Symposium on Biomedical Imaging (ISBI), Hosted by the International Skin Imaging Collaboration (ISIC)cited by 549
  4. 2020PraNet: Parallel Reverse Attention Network for Polyp Segmentationcited by 460
  5. 2021Concealed Object Detectioncited by 212
  6. 2021Visual Saliency Transformercited by 175
  7. 2021Camouflaged Object Segmentation with Distraction Miningcited by 151
  8. 2022Zoom In and Out: A Mixed-scale Triplet Network for Camouflaged Object Detectioncited by 145
  9. 2021Salient Object Detection via Integrity Learningcited by 133
  10. 2020Suppress and Balance: A Simple Gated Network for Salient Object Detectioncited by 126
  11. 2022Highly Accurate Dichotomous Image Segmentationcited by 110
  12. 2023Can SAM Segment Anything? When SAM Meets Camouflaged Object Detectioncited by 100
15 more
  1. 2014Salient Object Detection: A Surveycited by 98
  2. 2022Video Polyp Segmentation: A Deep Learning Perspectivecited by 82
  3. 2022High-resolution Iterative Feedback Network for Camouflaged Object Detectioncited by 78
  4. 2018Joint Optic Disc and Cup Segmentation Based on Multi-label Deep Network and Polar Transformationcited by 73
  5. 2022Deep Gradient Learning for Efficient Camouflaged Object Detectioncited by 65
  6. 2020EDN: Salient Object Detection via Extremely-Downsampled Networkcited by 64
  7. 2019RGB-T Image Saliency Detection via Collaborative Graph Learningcited by 58
  8. 2017Direction-aware Spatial Context Features for Shadow Detectioncited by 56
  9. 2021RGB-D Saliency Detection via Cascaded Mutual Information Minimizationcited by 50
  10. 2022Feature Aggregation and Propagation Network for Camouflaged Object Detectioncited by 40
  11. 2020Learning Selective Mutual Attention and Contrast for RGB-D Saliency Detectioncited by 38
  12. 2019Revisiting Shadow Detection: A New Benchmark Dataset for Complex Worldcited by 34
  13. 2022Promoting Saliency From Depth: Deep Unsupervised RGB-D Saliency Detectioncited by 12
  14. 2022BlazeNeo: Blazing fast polyp segmentation and neoplasm detectioncited by 10
  15. 2022Label-efficient Hybrid-supervised Learning for Medical Image Segmentationcited by 10

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2023: 47; 2024: 38; 2025: 23; 2026: 13.

121 papers.

Sort:

By area:

  1. 2023Segment Anything in Medical Imagescited by 227
  2. 2023SAM-6D: Segment Anything Model Meets Zero-Shot 6D Object Pose Estimationcited by 117
  3. 2024Segment Anything Model for Medical Image Segmentation: Current Applications and Future Directionscited by 97
  4. 2023Weakly-Supervised Concealed Object Segmentation with SAM-based Pseudo Labeling and Multi-scale Feature Groupingcited by 92
  5. 2023SAM on Medical Images: A Comprehensive Study on Three Prompt Modescited by 82
  6. 2023Review of Large Vision Models and Visual Prompt Engineeringcited by 77
  7. 2024What Matters When Repurposing Diffusion Models for General Dense Perception Tasks?cited by 74
  8. 20233DSAM-adapter: Holistic adaptation of SAM from 2D to 3D for promptable tumor segmentationcited by 70
  9. 2024Convolution Meets LoRA: Parameter Efficient Finetuning for Segment Anything Modelcited by 69
  10. 2023A Comprehensive Survey on Segment Anything Model for Vision and Beyondcited by 64
  11. 2023Can SAM Segment Polyps?cited by 59
  12. 2023Med-UniC: Unifying Cross-Lingual Medical Vision-Language Pre-Training by Diminishing Biascited by 57
38 more
  1. 2023Adapting Segment Anything Model for Change Detection in HR Remote Sensing Imagescited by 56
  2. 2023SayNav: Grounding Large Language Models for Dynamic Planning to Navigation in New Environmentscited by 53
  3. 2023Generalist Vision Foundation Models for Medical Imaging: A Case Study of Segment Anything Model on Zero-Shot Medical Segmentationcited by 51
  4. 2023Annotation-free Audio-Visual Segmentationcited by 46
  5. 2023A Survey on Segment Anything Model (SAM): Vision Foundation Model Meets Prompt Engineeringcited by 45
  6. 2023Segment anything, from space?cited by 42
  7. 2023SAM3D: Zero-Shot 3D Object Detection via Segment Anything Modelcited by 40
  8. 2023Segment Anything Model for Medical Images?cited by 39
  9. 2023SAMAug: Point Prompt Augmentation for Segment Anything Modelcited by 38
  10. 2024A Survey of Camouflaged Object Detection and Beyondcited by 37
  11. 2024RobustSAM: Segment Anything Robustly on Degraded Imagescited by 36
  12. 2023Self-Prompting Large Vision Models for Few-Shot Medical Image Segmentationcited by 35
  13. 2025DFormerv2: Geometry Self-Attention for RGBD Semantic Segmentationcited by 31
  14. 2024Foundation Models for Biomedical Image Segmentation: A Surveycited by 28
  15. 2024CAT-SAM: Conditional Tuning for Few-Shot Adaptation of Segment Anything Modelcited by 27
  16. 2023On the Robustness of Segment Anythingcited by 25
  17. 2023Segment Anything Model (SAM) for Radiation Oncologycited by 24
  18. 2023An Empirical Study on the Robustness of the Segment Anything Model (SAM)cited by 23
  19. 2024Learning Spectral-Decomposed Tokens for Domain Generalized Semantic Segmentationcited by 22
  20. 2023Towards Segment Anything Model (SAM) for Medical Image Segmentation: A Surveycited by 21
  21. 2023A Survey on Continual Semantic Segmentation: Theory, Challenge, Method and Applicationcited by 21
  22. 2024Leveraging Hallucinations to Reduce Manual Prompt Dependency in Promptable Segmentationcited by 20
  23. 2023Self-Sampling Meta SAM: Enhancing Few-shot Medical Image Segmentation with Meta-Learningcited by 18
  24. 2024Spider: A Unified Framework for Context-dependent Concept Segmentationcited by 18
  25. 2024SAFIRE: Segment Any Forged Image Regioncited by 18
  26. 2023Any-to-Any Style Transfer: Making Picasso and Da Vinci Collaboratecited by 17
  27. 2023RepViT-SAM: Towards Real-Time Segmenting Anythingcited by 17
  28. 2024Interactive 3D Medical Image Segmentation with SAM 2cited by 17
  29. 2023Knowledge distillation with Segment Anything (SAM) model for Planetary Geological Mappingcited by 16
  30. 2024On Efficient Variants of Segment Anything Model: A Surveycited by 16
  31. 2023UGainS: Uncertainty Guided Anomaly Instance Segmentationcited by 15
  32. 2024BA-SAM: Scalable Bias-Mode Attention Mask for Segment Anything Modelcited by 15
  33. 2023NTO3D: Neural Target Object 3D Reconstruction with Segment Anythingcited by 14
  34. 2025Improving SAM for Camouflaged Object Detection via Dual Stream Adapterscited by 13
  35. 2024ASAM: Boosting Segment Anything Model with Adversarial Tuningcited by 12
  36. 2024Harnessing Massive Satellite Imagery with Efficient Masked Image Modelingcited by 12
  37. 2025Self-Prompt SAM: Medical Image Segmentation via Automatic Prompt SAM Adaptationcited by 12
  38. 2024Generative Active Learning for Long-tailed Instance Segmentationcited by 10

50 most cited of 121 All 121 (JSON)