mlsanityData to 7 Oct 2026

Crowd-SAM: SAM as a Smart Annotator for Object Detection in Crowded Scenes

arXiv 2407.11464 ↗First posted 16 Jul 2024cs.CVcited by 13

Not on the map. Why?

Abstract (arXiv)

In computer vision, object detection is an important task that finds its application in many scenarios. However, obtaining extensive labels can be challenging, especially in crowded scenes. Recently, the Segment Anything Model (SAM) has been proposed as a powerful zero-shot segmenter, offering a novel approach to instance segmentation tasks. However, the accuracy and efficiency of SAM and its variants are often compromised when handling objects in crowded and occluded scenes. In this paper, we introduce Crowd-SAM, a SAM-based framework designed to enhance SAM's performance in crowded and occluded scenes with the cost of few learnable parameters and minimal labeled images. We introduce an efficient prompt sampler (EPS) and a part-whole discrimination network (PWD-Net), enhancing mask selection and accuracy in crowded scenes. Despite its simplicity, Crowd-SAM rivals state-of-the-art (SOTA) fully-supervised object detection methods on several benchmarks including CrowdHuman and CityPersons. Our code is available at https://github.com/FelixCaae/CrowdSAM.

Key facts. Cited by 13 papers in the map (data through 7 Oct 2026). Builds on 55 of its 65 references that are in the map. First posted on arXiv 16 Jul 2024.

Builds on

55 of 65 references.

References · 55

  1. 2015Deep Residual Learning for Image Recognitioncited by 51,809
  2. 2014Adam: A Method for Stochastic Optimizationcited by 36,960
  3. 2020An Image is Worth 16x16 Words: Transformers for Image Recognition at Scalecited by 29,915
  4. 2014Microsoft COCO: Common Objects in Contextcited by 17,498
  5. 2015Faster R-CNN: Towards Real-Time Object Detection with Region Proposal Networkscited by 9,617
  6. 2023Segment Anythingcited by 8,158
  7. 2023DINOv2: Learning Robust Visual Features without Supervisioncited by 7,764
  8. 2020End-to-End Object Detection with Transformerscited by 7,384
  9. 2017Mask R-CNNcited by 7,259
  10. 2021Emerging Properties in Self-Supervised Vision Transformerscited by 6,893
  11. 2015You Only Look Once: Unified, Real-Time Object Detectioncited by 4,829
  12. 2020Bootstrap your own latent: A new approach to self-supervised Learningcited by 4,712
38 more
  1. 2020Deformable DETR: Deformable Transformers for End-to-End Object Detectioncited by 3,410
  2. 2015SSD: Single Shot MultiBox Detectorcited by 3,125
  3. 2015Fast R-CNNcited by 2,930
  4. 2013Rich feature hierarchies for accurate object detection and semantic segmentationcited by 2,160
  5. 2019FCOS: Fully Convolutional One-Stage Object Detectioncited by 1,573
  6. 2022DINO: DETR with Improved DeNoising Anchor Boxes for End-to-End Object Detectioncited by 1,306
  7. 2019Bridging the Gap Between Anchor-based and Anchor-free Detection via Adaptive Training Sample Selectioncited by 539
  8. 2020Sparse R-CNN: End-to-End Object Detection with Learnable Proposalscited by 494
  9. 2023Medical SAM Adapter: Adapting Segment Anything Model for Medical Image Segmentationcited by 485
  10. 2023Segment Anything in High Qualitycited by 373
  11. 2023Faster Segment Anything: Towards Lightweight SAM for Mobile Applicationscited by 345
  12. 2021End-to-End Semi-Supervised Object Detection with Soft Teachercited by 315
  13. 2021Unbiased Teacher for Semi-Supervised Object Detectioncited by 305
  14. 2023Fast Segment Anythingcited by 286
  15. 2018CrowdHuman: A Benchmark for Detecting Human in a Crowdcited by 283
  16. 2020Frustratingly Simple Few-Shot Object Detectioncited by 280
  17. 2018Few-shot Object Detection via Feature Reweightingcited by 265
  18. 2023Personalize Segment Anything Model with One Shotcited by 250
  19. 2021DetCo: Unsupervised Contrastive Learning for Object Detectioncited by 205
  20. 2019Meta R-CNN : Towards General Solver for Instance-level Few-shot Learningcited by 182
  21. 2023RSPrompter: Learning to Prompt for Remote Sensing Instance Segmentation based on Visual Foundation Modelcited by 180
  22. 2017CityPersons: A Diverse Dataset for Pedestrian Detectioncited by 171
  23. 2021FSCE: Few-Shot Object Detection via Contrastive Proposal Encodingcited by 168
  24. 2023Matcher: Segment Anything with One Shot Using All-Purpose Feature Matchingcited by 142
  25. 2017Multiple Instance Detection Network with Online Instance Classifier Refinementcited by 117
  26. 2021Humble Teachers Teach Better Students for Semi-Supervised Object Detectioncited by 115
  27. 2018Pose2Seg: Detection Free Human Instance Segmentationcited by 107
  28. 2021DeFRCN: Decoupled Faster R-CNN for Few-Shot Object Detectioncited by 106
  29. 2021Deep Occlusion-Aware Instance Segmentation with Overlapping BiLayerscited by 104
  30. 2021DETReg: Unsupervised Pretraining with Region Priors for Object Detectioncited by 76
  31. 2020Self-EMD: Self-Supervised Object Detection without ImageNetcited by 70
  32. 2022Unbiased Teacher v2: Semi-supervised Object Detection for Anchor-free and Anchor-based Detectorscited by 69
  33. 2019Adaptive NMS: Refining Pedestrian Detection in a Crowdcited by 66
  34. 2017Repulsion Loss: Detecting Pedestrians in a Crowdcited by 62
  35. 2018Occlusion-aware R-CNN: Detecting Pedestrians in a Crowdcited by 58
  36. 2019WSOD^2: Learning Bottom-up and Top-down Objectness Distillation for Weakly-supervised Object Detectioncited by 51
  37. 2022Progressive End-to-End Object Detection in Crowded Scenescited by 31
  38. 2019PedHunter: Occlusion Robust Pedestrian Detector in Crowded Scenescited by 30

50 most cited of 55 All 55 (JSON)

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2024: 2; 2025: 5; 2026: 6.

13 papers.

Sort:

  1. 2025Foundation Models and Transformers for Anomaly Detection: A Surveycited by 8
  2. 2025Mix-QSAM: Mixed-Precision Quantization of the Segment Anything Modelcited by 4
  3. 2024Detection, Pose Estimation and Segmentation for Multiple Bodies: Closing the Virtuous Circlecited by 2
  4. 2025Holmes: Towards Effective and Harmless Model Ownership Verification to Personalized Large Vision Models via Decoupling Common Featurescited by 2
  5. 2025Point2RBox-v3: Self-Bootstrapping from Point Annotations via Integrated Pseudo-Label Refinement and Utilizationcited by 2
  6. 2024Adapting Segment Anything Model for Unseen Object Instance Segmentationcited by 1
  7. 2025Weakly-supervised Contrastive Learning with Quantity Prompts for Moving Infrared Small Target Detectioncited by 1
  8. 2026SAM-pose2seg: Pose-Guided Human Instance Segmentation in Crowdscited by 1
  9. 2026Towards Unbiased Source-Free Object Detection via Vision Foundation Modelscited by 0
  10. 2026BBoxMaskPose v2: Expanding Mutual Conditioning to 3Dcited by 0
  11. 2026Exclusivity-Guided Mask Learning for Semi-Supervised Crowd Instance Segmentation and Countingcited by 0
  12. 2026Dense Point-to-Mask Optimization with Reinforced Point Selection for Crowd Instance Segmentationcited by 0
1 more
  1. 2026SRPR-Net: Semantic and Relational Prompt Refinement for Automated SAM-based Instance Segmentationcited by 0