mlsanityData to 14 Oct 2026

SAMAug: Point Prompt Augmentation for Segment Anything Model

arXiv 2307.01187 ↗First posted 3 Jul 2023cs.CV cs.AIcited by 38

Not on the map. Why?

Abstract (arXiv)

This paper introduces SAMAug, a novel visual point augmentation method for the Segment Anything Model (SAM) that enhances interactive image segmentation performance. SAMAug generates augmented point prompts to provide more information about the user's intention to SAM. Starting with an initial point prompt, SAM produces an initial mask, which is then fed into our proposed SAMAug to generate augmented point prompts. By incorporating these extra points, SAM can generate augmented segmentation masks based on both the augmented point prompts and the initial prompt, resulting in improved segmentation performance. We conducted evaluations using four different point augmentation strategies: random sampling, sampling based on maximum difference entropy, maximum distance, and saliency. Experiment results on the COCO, Fundus, COVID QUEx, and ISIC2018 datasets show that SAMAug can boost SAM's segmentation results, especially using the maximum distance and saliency. SAMAug demonstrates the potential of visual prompt augmentation for computer vision. Codes of SAMAug are available at github.com/yhydhx/SAMAug

Key facts. Cited by 38 papers in the map (data through 14 Oct 2026). Builds on 47 of its 80 references that are in the map. First posted on arXiv 3 Jul 2023.

Builds on

47 of 80 references.

References · 47

  1. 2021Learning Transferable Visual Models From Natural Language Supervisioncited by 33,744
  2. 2020Language Models are Few-Shot Learnerscited by 32,419
  3. 2020An Image is Worth 16x16 Words: Transformers for Image Recognition at Scalecited by 30,186
  4. 2014Microsoft COCO: Common Objects in Contextcited by 17,608
  5. 2023Segment Anythingcited by 8,234
  6. 2014Fully Convolutional Networks for Semantic Segmentationcited by 4,859
  7. 2020Fourier Features Let Networks Learn High Frequency Functions in Low Dimensional Domainscited by 2,200
  8. 2022Visual Prompt Tuningcited by 1,681
  9. 2020Making Pre-trained Language Models Better Few-shot Learnerscited by 1,256
  10. 2022AdaptFormer: Adapting Vision Transformers for Scalable Visual Recognitioncited by 719
  11. 2021GPT Understands, Toocited by 716
  12. 2019Skin Lesion Analysis Toward Melanoma Detection 2018: A Challenge Hosted by the International Skin Imaging Collaboration (ISIC)cited by 669
35 more
  1. 2023Medical SAM Adapter: Adapting Segment Anything Model for Medical Image Segmentationcited by 490
  2. 2021Learning How to Ask: Querying LMs with Mixtures of Soft Promptscited by 377
  3. 2023A Comprehensive Survey on Pretrained Foundation Models: A History from BERT to ChatGPTcited by 368
  4. 2017Sampling Matters in Deep Embedding Learningcited by 285
  5. 2023BiomedGPT: A Generalist Vision-Language Foundation Model for Diverse Biomedical Taskscited by 201
  6. 2021Visual Saliency Transformercited by 175
  7. 2023Segment Anything Model (SAM) for Digital Pathology: Assess Zero-shot Segmentation on Whole Slide Imagingcited by 161
  8. 2023Visual Prompt Multi-Modal Trackingcited by 142
  9. 2023DeID-GPT: Zero-shot Medical Text De-Identification by GPT-4cited by 130
  10. 2022Convolutional Bypasses Are Better Vision Transformer Adapterscited by 121
  11. 2023Segment Anything Is Not Always Perfect: An Investigation of SAM on Different Real-world Applicationscited by 121
  12. 2023Automatic Prompt Augmentation and Selection with Chain-of-Thought from Labeled Datacited by 119
  13. 2022Black-box Prompt Learning for Pre-trained Language Modelscited by 70
  14. 2023A Comprehensive Survey on Segment Anything Model for Vision and Beyondcited by 64
  15. 2021PADA: Example-based Prompt Learning for on-the-fly Adaptation to Unseen Domainscited by 61
  16. 2023SAM.MD: Zero-shot medical image segmentation capabilities of the Segment Anything Modelcited by 61
  17. 2023An Iterative Optimizing Framework for Radiology Report Summarization with ChatGPTcited by 57
  18. 2023Input Augmentation with SAM: Boosting Medical Image Segmentation with Segmentation Foundation Modelcited by 56
  19. 2023When Brain-inspired AI Meets AGIcited by 54
  20. 2023Prompt Engineering for Healthcare: Methodologies and Applicationscited by 52
  21. 2023Evaluating Large Language Models on a Highly-specialized Topic, Radiation Oncology Physicscited by 49
  22. 2023Radiology-GPT: A Large Language Model for Radiologycited by 44
  23. 2022On the Power of Foundation Modelscited by 37
  24. 2023Artificial General Intelligence for Medical Imaging Analysiscited by 32
  25. 2023Differentiate ChatGPT-generated and Human-written Medical Textscited by 26
  26. 2023Mask-guided BERT for Few Shot Text Classificationcited by 25
  27. 2023Segment Anything Model (SAM) for Radiation Oncologycited by 24
  28. 2022Coarse-to-fine Knowledge Graph Domain Adaptation based on Distantly-supervised Iterative Trainingcited by 20
  29. 2022Rectify ViT Shortcut Learning by Visual Saliencycited by 14
  30. 2023Instruction-ViT: Multi-Modal Prompts for Instruction Learning in ViTcited by 14
  31. 2022Mask-guided Vision Transformer (MG-ViT) for Few-Shot Learningcited by 10
  32. 2022A Unified and Biologically-Plausible Relational Graph Representation of Vision Transformerscited by 7
  33. 2023Core-Periphery Principle Guided Redesign of Self-Attention in Transformerscited by 7
  34. 2022Disentangling Spatial-Temporal Functional Brain Networks via Twin-Transformerscited by 6
  35. 2023Gyri vs. Sulci: Disentangling Brain Core-Periphery Functional Networks via Twin-Transformercited by 3

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2023: 14; 2024: 14; 2025: 7; 2026: 3.

38 papers.

Sort:

By area:

  1. 2023Set-of-Mark Prompting Unleashes Extraordinary Visual Grounding in GPT-4Vcited by 299
  2. 2023Multimodal Foundation Models: From Specialists to General-Purpose Assistantscited by 247
  3. 2024Large Language Models for Robotics: Opportunities, Challenges, and Perspectivescited by 89
  4. 2023MA-SAM: Modality-agnostic SAM Adaptation for 3D Medical Image Segmentationcited by 82
  5. 2024VRP-SAM: SAM with Visual Reference Promptcited by 75
  6. 2024Understanding LLMs: A Comprehensive Overview from Training to Inferencecited by 59
  7. 2023Radiology-Llama2: Best-in-Class Large Language Model for Radiologycited by 42
  8. 2024MedCLIP-SAMv2: Towards Universal Text-Driven Medical Image Segmentationcited by 39
  9. 2024Foundation Models for Biomedical Image Segmentation: A Surveycited by 28
  10. 2024Curriculum Point Prompting for Weakly-Supervised Referring Image Segmentationcited by 23
  11. 2023Holistic Evaluation of GPT-4V for Biomedical Imagingcited by 19
  12. 2023RadOnc-GPT: A Large Language Model for Radiation Oncologycited by 18
26 more
  1. 2024PA-SAM: Prompt Adapter SAM for High-Quality Image Segmentationcited by 17
  2. 2024Biomedical SAM 2: Segment Anything in Biomedical Images and Videoscited by 14
  3. 2025SAM2 for Image and Video Segmentation: A Comprehensive Surveycited by 13
  4. 2023Evaluating Large Language Models for Radiology Natural Language Processingcited by 12
  5. 2023RGB-T Tracking via Multi-Modal Mutual Prompt Learningcited by 8
  6. 2025SAMed-2: Selective Memory Enhanced Medical Segment Anything Modelcited by 8
  7. 2023Large Scale Foundation Models for Intelligent Manufacturing Applications: A Surveycited by 6
  8. 2024Benchmarking Human and Automated Prompting in the Segment Anything Modelcited by 6
  9. 2023Hierarchical Semantic Tree Concept Whitening for Interpretable Image Classificationcited by 5
  10. 2023AdapterShadow: Adapting Segment Anything Model for Shadow Detectioncited by 5
  11. 2025S^4M: Boosting Semi-Supervised Instance Segmentation with SAMcited by 5
  12. 2023Evaluating multiple large language models in pediatric ophthalmologycited by 4
  13. 2024EchoONE: Segmenting Multiple echocardiography Planes in One Modelcited by 4
  14. 2023PharmacyGPT: The AI Pharmacistcited by 3
  15. 2024SamLP: A Customized Segment Anything Model for License Plate Detectioncited by 3
  16. 2023AI-SAM: Automatic and Interactive Segment Anything Modelcited by 2
  17. 2025HyPSAM: Hybrid Prompt-driven Segment Anything Model for RGB-Thermal Salient Object Detectioncited by 2
  18. 2024Foundation Models for Amodal Video Instance Segmentation in Automated Drivingcited by 1
  19. 2024EP-SAM: Weakly Supervised Histopathology Segmentation via Enhanced Prompt with Segment Anythingcited by 1
  20. 2024MatSAM: Efficient Extraction of Microstructures of Materials via Visual Large Modelcited by 0
  21. 2025Promoting SAM for Camouflaged Object Detection via Selective Key Point-based Guidancecited by 0
  22. 2025A Segmentation-driven Editing Method for Bolt Defect Augmentation and Detectioncited by 0
  23. 2025Attack for Defense: Adversarial Agents for Point Prompt Optimization Empowering Segment Anything Modelcited by 0
  24. 2026HFP-SAM: Hierarchical Frequency Prompted SAM for Efficient Marine Animal Segmentationcited by 0
  25. 2026PinPoint: Prompting with Informative Interior Pointscited by 0
  26. 2026Memory-Supported Synergistic Adaptation for Training-Free Test-Time Medical Image Segmentationcited by 0