mlsanityData to 14 Oct 2026

What's the Point: Semantic Segmentation with Point Supervision

arXiv 1506.02106 ↗First posted 6 Jun 2015cs.CVcited by 298

Not on the map. Why?

Abstract (arXiv)

The semantic image segmentation task presents a trade-off between test time accuracy and training-time annotation cost. Detailed per-pixel annotations enable training accurate models but are very time-consuming to obtain, image-level class labels are an order of magnitude cheaper but result in less accurate models. We take a natural step from image-level annotation towards stronger supervision: we ask annotators to point to an object if one exists. We incorporate this point supervision along with a novel objectness potential in the training loss function of a CNN model. Experimental results on the PASCAL VOC 2012 benchmark reveal that the combined effect of point-level supervision and objectness potential yields an improvement of 12.9% mIOU over image-level supervision. Further, we demonstrate that models trained with point-level supervision are more accurate than models trained with image-level, squiggle-level or full supervision given a fixed annotation budget.

Key facts. Cited by 298 papers in the map (data through 14 Oct 2026). First posted on arXiv 6 Jun 2015.

Builds on

No reference list yet.

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2021: 73; 2022: 72; 2023: 73; 2024: 43; 2025: 17; 2026: 20.

298 papers.

Sort:

By area:

  1. 2021Unsupervised Semantic Segmentation by Contrasting Object Mask Proposalscited by 190
  2. 2021Anti-Adversarially Manipulated Attributions for Weakly and Semi-Supervised Semantic Segmentationcited by 134
  3. 2022CLIP is Also an Efficient Segmenter: A Text-Driven Approach for Weakly Supervised Semantic Segmentationcited by 118
  4. 2022ReCo: Retrieve and Co-segment for Zero-shot Transfercited by 117
  5. 2021BBAM: Bounding Box Attribution Map for Weakly Supervised Semantic and Instance Segmentationcited by 105
  6. 2021Mixed supervision for surface-defect detection: from weakly to fully supervised learningcited by 101
  7. 2021Non-Salient Region Object Mining for Weakly Supervised Semantic Segmentationcited by 95
  8. 2021One Thing One Click: A Self-Training Approach for Weakly Supervised 3D Semantic Segmentationcited by 89
  9. 2022Self-supervised Image-specific Prototype Exploration for Weakly Supervised Semantic Segmentationcited by 87
  10. 2021Weakly Supervised Semantic Segmentation by Pixel-to-Prototype Contrastcited by 85
  11. 2021Open-Vocabulary Instance Segmentation via Robust Cross-Modal Pseudo-Labelingcited by 84
  12. 2021Pointly-Supervised Instance Segmentationcited by 83
38 more
  1. 2021Complementary Patch for Weakly Supervised Semantic Segmentationcited by 75
  2. 2022Cross Language Image Matching for Weakly Supervised Semantic Segmentationcited by 72
  3. 2021Context Decoupling Augmentation for Weakly Supervised Semantic Segmentationcited by 69
  4. 2023Token Contrast for Weakly-Supervised Semantic Segmentationcited by 65
  5. 2022Regional Semantic Contrast and Aggregation for Weakly Supervised Semantic Segmentationcited by 64
  6. 2021Points as Queries: Weakly Semi-supervised Object Detection by Pointscited by 60
  7. 2021DiscoBox: Weakly Supervised Instance Segmentation and Semantic Correspondence from Box Supervisioncited by 59
  8. 2022Weakly Supervised Semantic Segmentation using Out-of-Distribution Datacited by 58
  9. 2021A Closer Look at Self-training for Zero-Label Semantic Segmentationcited by 57
  10. 2022L2G: A Simple Local-to-Global Knowledge Transfer Framework for Weakly Supervised Semantic Segmentationcited by 57
  11. 2022Discovering Object Masks with Transformers for Unsupervised Semantic Segmentationcited by 54
  12. 2022Unsupervised Semantic Segmentation with Self-supervised Object-centric Representationscited by 54
  13. 2023Segment Anything Model (SAM) Enhanced Pseudo Labels for Weakly Supervised Semantic Segmentationcited by 53
  14. 2023Mapping Degeneration Meets Label Evolution: Learning Infrared Small Target Detection with Single Point Supervisioncited by 51
  15. 2021Temporal Action Segmentation from Timestamp Supervisioncited by 48
  16. 2021Pseudo-mask Matters in Weakly-supervised Semantic Segmentationcited by 48
  17. 2021Affinity Attention Graph Neural Network for Weakly Supervised Semantic Segmentationcited by 47
  18. 2022Tree Energy Loss: Towards Sparsely Annotated Semantic Segmentationcited by 47
  19. 2021Universal Weakly Supervised Segmentation by Pixel-to-Segment Contrastive Learningcited by 43
  20. 2021Multi-Layer Pseudo-Supervision for Histopathology Tissue Semantic Segmentation using Patch-level Classification Labelscited by 43
  21. 2021Learning Action Completeness from Points for Weakly-supervised Temporal Action Localizationcited by 42
  22. 2021Background-Aware Pooling and Noise-Aware Loss for Weakly-Supervised Semantic Segmentationcited by 41
  23. 2023CLIP in Medical Imaging: A Surveycited by 40
  24. 2021Unsupervised Discovery of the Long-Tail in Instance Segmentation Using Hierarchical Self-Supervisioncited by 39
  25. 2021Incremental Learning in Semantic Segmentation from Image Labelscited by 39
  26. 2021Every Annotation Counts: Multi-label Deep Supervision for Medical Image Segmentationcited by 37
  27. 2022Expansion and Shrinkage of Localization for Weakly-Supervised Semantic Segmentationcited by 37
  28. 2021All you need are a few pixels: semantic segmentation with PixelPickcited by 31
  29. 2021Fully Convolutional Networks for Panoptic Segmentation with Point-based Supervisioncited by 31
  30. 2021Semantic Segmentation of Remote Sensing Images with Sparse Annotationscited by 30
  31. 2021Uncertainty Estimation via Response Scaling for Pseudo-mask Noise Mitigation in Weakly-supervised Semantic Segmentationcited by 29
  32. 2021Activation Modulation and Recalibration Scheme for Weakly Supervised Semantic Segmentationcited by 29
  33. 2022Omni-DETR: Omni-Supervised Object Detection with Transformerscited by 29
  34. 2023Logic-induced Diagnostic Reasoning for Semi-supervised Semantic Segmentationcited by 29
  35. 2024EarthMarker: A Visual Prompting Multi-modal Large Language Model for Remote Sensingcited by 29
  36. 2023Segment Anything is A Good Pseudo-label Generator for Weakly Supervised Semantic Segmentationcited by 27
  37. 2021Beyond Semantic to Instance Segmentation: Weakly-Supervised Instance Segmentation via Semantic Knowledge Transfer and Self-Refinementcited by 26
  38. 2022TransCAM: Transformer Attention-based CAM Refinement for Weakly Supervised Semantic Segmentationcited by 26

50 most cited of 298 All 298 (JSON)