mlsanityData to 7 Oct 2026

WeakSAM: Segment Anything Meets Weakly-supervised Instance-level Recognition

arXiv 2402.14812 ↗First posted 22 Feb 2024cs.CV cs.AIcited by 9

Not on the map. Why?

Abstract (arXiv)

Weakly supervised visual recognition using inexact supervision is a critical yet challenging learning problem. It significantly reduces human labeling costs and traditionally relies on multi-instance learning and pseudo-labeling. This paper introduces WeakSAM and solves the weakly-supervised object detection (WSOD) and segmentation by utilizing the pre-learned world knowledge contained in a vision foundation model, i.e., the Segment Anything Model (SAM). WeakSAM addresses two critical limitations in traditional WSOD retraining, i.e., pseudo ground truth (PGT) incompleteness and noisy PGT instances, through adaptive PGT generation and Region of Interest (RoI) drop regularization. It also addresses the SAM's problems of requiring prompts and category unawareness for automatic object detection and segmentation. Our results indicate that WeakSAM significantly surpasses previous state-of-the-art methods in WSOD and WSIS benchmarks with large margins, i.e. average improvements of 7.4% and 8.5%, respectively. The code is available at urlhttps://github.com/hustvl/WeakSAM.

Key facts. Cited by 9 papers in the map (data through 7 Oct 2026). Builds on 66 of its 105 references that are in the map. First posted on arXiv 22 Feb 2024.

Builds on

66 of 105 references.

References · 66

  1. 2015Deep Residual Learning for Image Recognitioncited by 51,809
  2. 2020An Image is Worth 16x16 Words: Transformers for Image Recognition at Scalecited by 29,915
  3. 2014Microsoft COCO: Common Objects in Contextcited by 17,498
  4. 2015Faster R-CNN: Towards Real-Time Object Detection with Region Proposal Networkscited by 9,617
  5. 2023Segment Anythingcited by 8,158
  6. 2017Mask R-CNNcited by 7,259
  7. 2020Training data-efficient image transformers & distillation through attentioncited by 4,560
  8. 2015Learning Deep Features for Discriminative Localizationcited by 2,430
  9. 2021Masked-attention Mask Transformer for Universal Image Segmentationcited by 2,338
  10. 2022DINO: DETR with Improved DeNoising Anchor Boxes for End-to-End Object Detectioncited by 1,306
  11. 2021Transformer in Transformercited by 632
  12. 2019Weakly Supervised Learning of Instance Segmentation with Inter-pixel Relationscited by 245
38 more
  1. 2020Weakly-Supervised Disentanglement Without Compromisescited by 237
  2. 2016Simple Does It: Weakly Supervised Instance and Semantic Segmentationcited by 226
  3. 2015Weakly Supervised Deep Detection Networkscited by 183
  4. 2020BoxInst: High-Performance Instance Segmentation with Box Annotationscited by 150
  5. 2020Mining Cross-Image Semantics for Weakly Supervised Semantic Segmentationcited by 144
  6. 2022Multi-class Token Transformer for Weakly Supervised Semantic Segmentationcited by 138
  7. 2022CLIP is Also an Efficient Segmenter: A Text-Driven Approach for Weakly Supervised Semantic Segmentationcited by 118
  8. 2017Multiple Instance Detection Network with Online Instance Classifier Refinementcited by 117
  9. 2021BBAM: Bounding Box Attribution Map for Weakly Supervised Semantic and Instance Segmentationcited by 104
  10. 2020Fast and Three-rious: Speeding Up Weak Supervision with Triplet Methodscited by 98
  11. 2018PCL: Proposal Cluster Learning for Weakly Supervised Object Detectioncited by 97
  12. 2015Multiscale Combinatorial Grouping for Image Segmentation and Object Proposal Generationcited by 90
  13. 2023Fine-Grained Visual Promptingcited by 81
  14. 2020Instance-aware, Context-focused, and Memory-efficient Weakly Supervised Object Detectioncited by 80
  15. 2018Weakly Supervised Instance Segmentation using Class Peak Responsecited by 74
  16. 2019C-MIL: Continuation Multiple Instance Learning for Weakly Supervised Object Detectioncited by 71
  17. 2023Segment Anything Model (SAM) Enhanced Pseudo Labels for Weakly Supervised Semantic Segmentationcited by 53
  18. 2019WSOD^2: Learning Bottom-up and Top-down Objectness Distillation for Weakly-supervised Object Detectioncited by 51
  19. 2020Comprehensive Attention Self-Distillation for Weakly-Supervised Object Detectioncited by 50
  20. 2016Weakly Supervised Cascaded Convolutional Networkscited by 47
  21. 2019Min-Entropy Latent Model for Weakly Supervised Object Detectioncited by 45
  22. 2019Towards Precise End-to-end Weakly Supervised Object Detection Networkcited by 41
  23. 2022Box-supervised Instance Segmentation with Level Set Evolutioncited by 41
  24. 2016ContextLocNet: Context-Aware Deep Network Models for Weakly Supervised Localizationcited by 39
  25. 2020Weakly Supervised Instance Segmentation by Learning Annotation Consistent Instancescited by 31
  26. 2022Point-to-Box Network for Accurate Object Detection via Single Point Supervisioncited by 31
  27. 2022BoxTeacher: Exploring High-Quality Pseudo Labels for Weakly Supervised Instance Segmentationcited by 31
  28. 2020SLV: Spatial Likelihood Voting for Weakly Supervised Object Detectioncited by 29
  29. 2017Deep Self-Taught Learning for Weakly Supervised Object Localizationcited by 27
  30. 2023Segment Anything is A Good Pseudo-label Generator for Weakly Supervised Semantic Segmentationcited by 27
  31. 2019Weakly Supervised Object Detection with Segmentation Collaborationcited by 26
  32. 2021Beyond Semantic to Instance Segmentation: Weakly-Supervised Instance Segmentation via Semantic Knowledge Transfer and Self-Refinementcited by 25
  33. 2018Zigzag Learning for Weakly Supervised Object Detectioncited by 24
  34. 2018Dissimilarity Coefficient based Weakly Supervised Object Detectioncited by 23
  35. 2021Adaptive Affinity Loss and Erroneous Pseudo-Label Refinement for Weakly Supervised Semantic Segmentationcited by 22
  36. 2022MutexMatch: Semi-Supervised Learning with Mutex-Based Consistency Regularizationcited by 22
  37. 2023WeakTr: Exploring Plain Vision Transformer for Weakly-supervised Semantic Segmentationcited by 22
  38. 2017C-WSL: Count-guided Weakly Supervised Localizationcited by 20

50 most cited of 66 All 66 (JSON)

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2024: 4; 2025: 3; 2026: 2.

9 papers.

  1. 2024Boosting Weakly-Supervised Referring Image Segmentation via Progressive Comprehensioncited by 10
  2. 2024DAWN: Domain-Adaptive Weakly Supervised Nuclei Segmentation via Cross-Task Interactionscited by 8
  3. 2024PC2: Pseudo-Classification Based Pseudo-Captioning for Noisy Correspondence Learning in Cross-Modal Retrievalcited by 3
  4. 2025Weakly-supervised Contrastive Learning with Quantity Prompts for Moving Infrared Small Target Detectioncited by 1
  5. 2025Fully Automated SAM for Single-source Domain Generalization in Medical Image Segmentationcited by 1
  6. 2026ViewSAM: Learning View-aware Cross-modal Semantics for Weakly Supervised Cross-view Referring Multi-Object Trackingcited by 1
  7. 2026Perceive-then-Plan: Layout-as-Policy for Monocular 3D Scene Layout Estimationcited by 1
  8. 2024Weakly Supervised Object Detection for Automatic Tooth-marked Tongue Recognitioncited by 0
  9. 2025Dual-Thresholded Heatmap-Guided Proposal Clustering and Negative Certainty Supervision with Enhanced Base Network for Weakly Supervised Object Detectioncited by 0