mlsanityData to 14 Oct 2026

Active Pointly-Supervised Instance Segmentation

arXiv 2207.11493 ↗First posted 23 Jul 2022cs.CVcited by 15

Not on the map. Why?

Abstract (arXiv)

The requirement of expensive annotations is a major burden for training a well-performed instance segmentation model. In this paper, we present an economic active learning setting, named active pointly-supervised instance segmentation (APIS), which starts with box-level annotations and iteratively samples a point within the box and asks if it falls on the object. The key of APIS is to find the most desirable points to maximize the segmentation accuracy with limited annotation budgets. We formulate this setting and propose several uncertainty-based sampling strategies. The model developed with these strategies yields consistent performance gain on the challenging MS-COCO dataset, compared against other learning strategies. The results suggest that APIS, integrating the advantages of active learning and point-based supervision, is an effective learning paradigm for label-efficient instance segmentation.

Key facts. Cited by 15 papers in the map (data through 14 Oct 2026). Builds on 48 of its 63 references that are in the map. First posted on arXiv 23 Jul 2022.

Builds on

48 of 63 references.

References · 48

  1. 2014Microsoft COCO: Common Objects in Contextcited by 17,608
  2. 2017Mask R-CNNcited by 7,277
  3. 2016The Cityscapes Dataset for Semantic Urban Scene Understandingcited by 4,444
  4. 2016Simple and Scalable Predictive Uncertainty Estimation using Deep Ensemblescited by 3,926
  5. 2021Masked-attention Mask Transformer for Universal Image Segmentationcited by 2,351
  6. 2019Generalized Intersection over Union: A Metric and A Loss for Bounding Box Regressioncited by 1,368
  7. 2019LVIS: A Dataset for Large Vocabulary Instance Segmentationcited by 1,217
  8. 2017Deep Bayesian Active Learning with Image Datacited by 819
  9. 2018Path Aggregation Network for Instance Segmentationcited by 798
  10. 2019Hybrid Task Cascade for Instance Segmentationcited by 481
  11. 2020Conditional Convolutions for Instance Segmentationcited by 314
  12. 2015What's the Point: Semantic Segmentation with Point Supervisioncited by 298
36 more
  1. 2019Variational Adversarial Active Learningcited by 284
  2. 2019Mask Scoring R-CNNcited by 266
  3. 2016Simple Does It: Weakly Supervised Instance and Semantic Segmentationcited by 227
  4. 2017Cost-Effective Active Learning for Deep Image Classificationcited by 166
  5. 2016Deep Interactive Object Selectioncited by 160
  6. 2021Instances as Queriescited by 158
  7. 2020BoxInst: High-Performance Instance Segmentation with Box Annotationscited by 151
  8. 2017Suggestive Annotation: A Deep Active Learning Framework for Biomedical Image Segmentationcited by 146
  9. 2020Contextual Diversity for Active Learningcited by 139
  10. 2017Deep Extreme Cut: From Extreme Points to Object Segmentationcited by 127
  11. 2017An Analysis of Scale Invariance in Object Detection - SNIPcited by 120
  12. 2019Large-scale interactive object segmentation with human annotatorscited by 110
  13. 2020AutoAssign: Differentiable Label Assignment for Dense Object Detectioncited by 100
  14. 2015Multiscale Combinatorial Grouping for Image Segmentation and Object Proposal Generationcited by 91
  15. 2021Influence Selection for Active Learningcited by 84
  16. 2021Pointly-Supervised Instance Segmentationcited by 83
  17. 2017Extreme clicking for efficient object annotationcited by 81
  18. 2021Active Learning for Deep Object Detection via Probabilistic Modelingcited by 79
  19. 2021Multiple instance active learning for object detectioncited by 77
  20. 2021SOLQ: Segmenting Objects by Learning Queriescited by 68
  21. 2019Active Learning for Deep Detection Neural Networkscited by 62
  22. 2021Points as Queries: Weakly Semi-supervised Object Detection by Pointscited by 60
  23. 2021DiscoBox: Weakly Supervised Instance Segmentation and Semantic Correspondence from Box Supervisioncited by 59
  24. 2020Scalable Active Learning for Object Detectioncited by 58
  25. 2021ReDAL: Region-based and Diversity-aware Active Learning for Point Cloud Semantic Segmentationcited by 52
  26. 2018Localization-Aware Active Learning for Object Detectioncited by 48
  27. 2021RefineMask: Towards High-Quality Instance Segmentation with Fine-Grained Featurescited by 47
  28. 2021Look Closer to Segment Better: Boundary Patch Refinement for Instance Segmentationcited by 43
  29. 2018Weakly Supervised Scene Parsing with Point-based Distance Metric Learningcited by 33
  30. 2020Weakly Supervised Instance Segmentation by Learning Annotation Consistent Instancescited by 32
  31. 2021SOLO: A Simple Framework for Instance Segmentationcited by 32
  32. 2021All you need are a few pixels: semantic segmentation with PixelPickcited by 31
  33. 2021Fully Convolutional Networks for Panoptic Segmentation with Point-based Supervisioncited by 31
  34. 2019An Adaptive Supervision Framework for Active Learning in Object Detectioncited by 20
  35. 2019BAOD: Budget-Aware Object Detectioncited by 9
  36. 2020Semi-supervised Active Learning for Instance Segmentation via Scoring Predictionscited by 8

Built on by

Cited by year

Citing papers per year: 2022: 2; 2023: 7; 2024: 3; 2025: 3.

15 papers.

Sort:

  1. 2023A comprehensive survey on deep active learning in medical image analysiscited by 35
  2. 2023Point2Mask: Point-supervised Panoptic Segmentation via Optimal Transportcited by 24
  3. 2022From colouring-in to pointillism: revisiting semantic segmentation supervisioncited by 22
  4. 2022Box2Mask: Box-supervised Instance Segmentation via Level-set Evolutioncited by 22
  5. 2023Label-efficient Segmentation via Affinity Propagationcited by 7
  6. 2023GaPro: Box-Supervised 3D Point Cloud Instance Segmentation Using Gaussian Processes as Pseudo Labelerscited by 6
  7. 2024Finding Meaning in Points: Weakly Supervised Semantic Segmentation for Event Camerascited by 6
  8. 2023Active Coarse-to-Fine Segmentation of Moveable Parts from Real Imagescited by 5
  9. 2024Extreme Point Supervised Instance Segmentationcited by 3
  10. 2023PVPUFormer: Probabilistic Visual Prompt Unified Transformer for Interactive Image Segmentationcited by 2
  11. 2024Boosting Box-supervised Instance Segmentation with Pseudo Depthcited by 2
  12. 2023Two-Step Active Learning for Instance Segmentation with Uncertainty and Diversity Samplingcited by 1
3 more
  1. 2025P2Object: Single Point Supervised Object Detection and Instance Segmentationcited by 1
  2. 2025ReSAM: Refine, Requery, and Reinforce: Self-Prompting Point-Supervised Segmentation for Remote Sensing Imagescited by 1
  3. 2025HiLLIE: Human-in-the-Loop Training for Low-Light Image Enhancementcited by 0