mlsanityData to 14 Oct 2026

Can SAM Count Anything? An Empirical Study on SAM Counting

arXiv 2304.10817 ↗First posted 21 Apr 2023cs.CV cs.AIcited by 18

Not on the map. Why?

Abstract (arXiv)

Meta AI recently released the Segment Anything model (SAM), which has garnered attention due to its impressive performance in class-agnostic segmenting. In this study, we explore the use of SAM for the challenging task of few-shot object counting, which involves counting objects of an unseen category by providing a few bounding boxes of examples. We compare SAM's performance with other few-shot counting methods and find that it is currently unsatisfactory without further fine-tuning, particularly for small and crowded objects. Code can be found at urlhttps://github.com/Vision-Intelligence-and-Robots-Group/count-anything.

Key facts. Cited by 18 papers in the map (data through 14 Oct 2026). Builds on 14 of its 16 references that are in the map. First posted on arXiv 21 Apr 2023.

Builds on

14 of 16 references.

References · 14

  1. 2021Learning Transferable Visual Models From Natural Language Supervisioncited by 33,744
  2. 2020Language Models are Few-Shot Learnerscited by 32,419
  3. 2023GPT-4 Technical Reportcited by 18,396
  4. 2014Microsoft COCO: Common Objects in Contextcited by 17,608
  5. 2023Segment Anythingcited by 8,234
  6. 2017Model-Agnostic Meta-Learning for Fast Adaptation of Deep Networkscited by 4,897
  7. 2023Grounding DINO: Marrying DINO with Grounded Pre-Training for Open-Set Object Detectioncited by 3,332
  8. 2018Few-shot Object Detection via Feature Reweightingcited by 265
  9. 2019Few-Shot Object Detection with Attention-RPN and Multi-Relation Detectorcited by 206
  10. 2021Learning To Count Everythingcited by 150
  11. 2022Represent, Compare, and Learn: A Similarity-Aware Framework for Class-Agnostic Countingcited by 80
  12. 2022Few-shot Object Counting with Similarity-Aware Feature Enhancementcited by 62
2 more
  1. 2018One-Shot Instance Segmentationcited by 43
  2. 2021Object Counting: You Only Need to Look at Onecited by 13

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2023: 10; 2024: 2; 2025: 4; 2026: 2.

18 papers.

Sort:

By area:

  1. 2023Multimodal Foundation Models: From Specialists to General-Purpose Assistantscited by 247
  2. 2023SAM on Medical Images: A Comprehensive Study on Three Prompt Modescited by 82
  3. 2023Review of Large Vision Models and Visual Prompt Engineeringcited by 77
  4. 2023A Comprehensive Survey on Segment Anything Model for Vision and Beyondcited by 64
  5. 2023A Survey on Segment Anything Model (SAM): Vision Foundation Model Meets Prompt Engineeringcited by 45
  6. 2023Point, Segment and Count: A Generalized Framework for Object Countingcited by 39
  7. 2024RobustSAM: Segment Anything Robustly on Degraded Imagescited by 36
  8. 2023On the Robustness of Segment Anythingcited by 25
  9. 2023ABC Easy as 123: A Blind Counter for Exemplar-Free Multi-Class Class-agnostic Countingcited by 13
  10. 2023Open-NeRF: Towards Open Vocabulary NeRF Decompositioncited by 13
  11. 2025Generalized-Scale Object Counting with Gradual Query Aggregationcited by 5
  12. 2023Industrial Segment Anything -- a Case Study in Aircraft Manufacturing, Intralogistics, Maintenance, Repair, and Overhaulcited by 4
6 more
  1. 2024A Simple-but-effective Baseline for Training-free Class-Agnostic Countingcited by 3
  2. 2025Few-Shot Pattern Detection via Template Matching and Regressioncited by 1
  3. 2025CoDi -- an exemplar-conditioned diffusion model for low-shot countingcited by 1
  4. 2026OCCAM: Class-Agnostic, Training-Free, Prior-Free and Multi-Class Object Countingcited by 1
  5. 2026AdaCount: Training-Free Similarity-Guided Spatial and Feature Adaptation for Zero-Shot Object Countingcited by 1
  6. 2025CountZES: Counting via Zero-Shot Exemplar Selectioncited by 0