mlsanityData to 7 Oct 2026

Point-Teaching: Weakly Semi-Supervised Object Detection with Point Annotations

arXiv 2206.00274 ↗First posted 1 Jun 2022cs.CVcited by 10

Not on the map. Why?

Abstract (arXiv)

Point annotations are considerably more time-efficient than bounding box annotations. However, how to use cheap point annotations to boost the performance of semi-supervised object detection remains largely unsolved. In this work, we present Point-Teaching, a weakly semi-supervised object detection framework to fully exploit the point annotations. Specifically, we propose a Hungarian-based point matching method to generate pseudo labels for point annotated images. We further propose multiple instance learning (MIL) approaches at the level of images and points to supervise the object detector with point annotations. Finally, we propose a simple-yet-effective data augmentation, termed point-guided copy-paste, to reduce the impact of the unmatched points. Experiments demonstrate the effectiveness of our method on a few datasets and various data regimes.

Key facts. Cited by 10 papers in the map (data through 7 Oct 2026). Builds on 32 of its 48 references that are in the map. First posted on arXiv 1 Jun 2022.

Builds on

32 of 48 references.

References · 32

  1. 2015Deep Residual Learning for Image Recognitioncited by 51,809
  2. 2014Microsoft COCO: Common Objects in Contextcited by 17,498
  3. 2015Faster R-CNN: Towards Real-Time Object Detection with Region Proposal Networkscited by 9,617
  4. 2020End-to-End Object Detection with Transformerscited by 7,384
  5. 2017Mask R-CNNcited by 7,259
  6. 2015You Only Look Once: Unified, Real-Time Object Detectioncited by 4,829
  7. 2020Deformable DETR: Deformable Transformers for End-to-End Object Detectioncited by 3,410
  8. 2015SSD: Single Shot MultiBox Detectorcited by 3,125
  9. 2019FCOS: Fully Convolutional One-Stage Object Detectioncited by 1,573
  10. 2019LVIS: A Dataset for Large Vocabulary Instance Segmentationcited by 1,215
  11. 2020Simple Copy-Paste is a Strong Data Augmentation Method for Instance Segmentationcited by 595
  12. 2020Conditional Convolutions for Instance Segmentationcited by 314
20 more
  1. 2021Unbiased Teacher for Semi-Supervised Object Detectioncited by 305
  2. 2020A Simple Semi-Supervised Learning Framework for Object Detectioncited by 282
  3. 2015Weakly Supervised Deep Detection Networkscited by 183
  4. 2020BoxInst: High-Performance Instance Segmentation with Box Annotationscited by 150
  5. 2017Multiple Instance Detection Network with Online Instance Classifier Refinementcited by 117
  6. 2020TIDE: A General Toolbox for Identifying Object Detection Errorscited by 113
  7. 2021Instant-Teaching: An End-to-End Semi-Supervised Object Detection Frameworkcited by 112
  8. 2019Rethinking Classification and Localization for Object Detectioncited by 98
  9. 2018PCL: Proposal Cluster Learning for Weakly Supervised Object Detectioncited by 97
  10. 2021Pointly-Supervised Instance Segmentationcited by 83
  11. 2017Extreme clicking for efficient object annotationcited by 80
  12. 2020Instance-aware, Context-focused, and Memory-efficient Weakly Supervised Object Detectioncited by 80
  13. 2021Points as Queries: Weakly Semi-supervised Object Detection by Pointscited by 60
  14. 2020Interpolation-based semi-supervised learning for object detectioncited by 40
  15. 2016ContextLocNet: Context-Aware Deep Network Models for Weakly Supervised Localizationcited by 39
  16. 2021SOLO: A Simple Framework for Instance Segmentationcited by 32
  17. 2022Group R-CNN for Weakly Semi-supervised Object Detection with Pointscited by 23
  18. 2020Object Instance Mining for Weakly Supervised Object Detectioncited by 18
  19. 2014Weakly-supervised Discovery of Visual Pattern Configurationscited by 7
  20. 2021Object Detection Made Simpler by Eliminating Heuristic NMScited by 6

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2022: 1; 2023: 1; 2024: 7; 2025: 0; 2026: 1.

10 papers.

  1. 2023Mapping Degeneration Meets Label Evolution: Learning Infrared Small Target Detection with Single Point Supervisioncited by 50
  2. 2022BoxTeacher: Exploring High-Quality Pseudo Labels for Weakly Supervised Instance Segmentationcited by 31
  3. 2024POLO -- Point-based, multi-class animal detectioncited by 4
  4. 2024Point-DETR3D: Leveraging Imagery Data with Spatial Point Prior for Weakly Semi-supervised 3D Object Detectioncited by 3
  5. 2024Boosting Medical Image-based Cancer Detection via Text-guided Supervision from Reportscited by 2
  6. 2024A Point-Neighborhood Learning Framework for Nasal Endoscope Image Segmentationcited by 2
  7. 2024Sparse Generation: Making Pseudo Labels Sparse for Point Weakly Supervised Object Detection on Low Data Volumecited by 1
  8. 2024Detecting Endangered Marine Species in Autonomous Underwater Vehicle Imagery Using Point Annotations and Few-Shot Learningcited by 1
  9. 2024UAVDB: Point-Guided Masks for UAV Detection and Segmentationcited by 1
  10. 2026Overhead Wildlife Locator (OWL): Benchmarking Weakly Supervised Learning for Aerial Wildlife Surveyscited by 1