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

arXiv: https://arxiv.org/abs/2206.00274 · HTML: https://mlsanity.com/paper/2206.00274/

## Key facts

- Cited by 11 papers in the map (data through 14 Oct 2026).
- Builds on 32 of its 48 references that are in the map.
- First posted on arXiv 1 Jun 2022.

## Builds on (most cited first, 30 of 32)

- [Deep Residual Learning for Image Recognition](https://mlsanity.com/paper/1512.03385/) (2015)
- [Microsoft COCO: Common Objects in Context](https://mlsanity.com/paper/1405.0312/) (2014)
- [Faster R-CNN: Towards Real-Time Object Detection with Region Proposal Networks](https://mlsanity.com/paper/1506.01497/) (2015)
- [End-to-End Object Detection with Transformers](https://mlsanity.com/paper/2005.12872/) (2020)
- [Mask R-CNN](https://mlsanity.com/paper/1703.06870/) (2017)
- [You Only Look Once: Unified, Real-Time Object Detection](https://mlsanity.com/paper/1506.02640/) (2015)
- [Deformable DETR: Deformable Transformers for End-to-End Object Detection](https://mlsanity.com/paper/2010.04159/) (2020)
- [SSD: Single Shot MultiBox Detector](https://mlsanity.com/paper/1512.02325/) (2015)
- [FCOS: Fully Convolutional One-Stage Object Detection](https://mlsanity.com/paper/1904.01355/) (2019)
- [LVIS: A Dataset for Large Vocabulary Instance Segmentation](https://mlsanity.com/paper/1908.03195/) (2019)
- [Simple Copy-Paste is a Strong Data Augmentation Method for Instance Segmentation](https://mlsanity.com/paper/2012.07177/) (2020)
- [Conditional Convolutions for Instance Segmentation](https://mlsanity.com/paper/2003.05664/) (2020)
- [Unbiased Teacher for Semi-Supervised Object Detection](https://mlsanity.com/paper/2102.09480/) (2021)
- [A Simple Semi-Supervised Learning Framework for Object Detection](https://mlsanity.com/paper/2005.04757/) (2020)
- [Weakly Supervised Deep Detection Networks](https://mlsanity.com/paper/1511.02853/) (2015)
- [BoxInst: High-Performance Instance Segmentation with Box Annotations](https://mlsanity.com/paper/2012.02310/) (2020)
- [Multiple Instance Detection Network with Online Instance Classifier Refinement](https://mlsanity.com/paper/1704.00138/) (2017)
- [TIDE: A General Toolbox for Identifying Object Detection Errors](https://mlsanity.com/paper/2008.08115/) (2020)
- [Instant-Teaching: An End-to-End Semi-Supervised Object Detection Framework](https://mlsanity.com/paper/2103.11402/) (2021)
- [Rethinking Classification and Localization for Object Detection](https://mlsanity.com/paper/1904.06493/) (2019)
- [PCL: Proposal Cluster Learning for Weakly Supervised Object Detection](https://mlsanity.com/paper/1807.03342/) (2018)
- [Pointly-Supervised Instance Segmentation](https://mlsanity.com/paper/2104.06404/) (2021)
- [Extreme clicking for efficient object annotation](https://mlsanity.com/paper/1708.02750/) (2017)
- [Instance-aware, Context-focused, and Memory-efficient Weakly Supervised Object Detection](https://mlsanity.com/paper/2004.04725/) (2020)
- [Points as Queries: Weakly Semi-supervised Object Detection by Points](https://mlsanity.com/paper/2104.07434/) (2021)
- [Interpolation-based semi-supervised learning for object detection](https://mlsanity.com/paper/2006.02158/) (2020)
- [ContextLocNet: Context-Aware Deep Network Models for Weakly Supervised Localization](https://mlsanity.com/paper/1609.04331/) (2016)
- [SOLO: A Simple Framework for Instance Segmentation](https://mlsanity.com/paper/2106.15947/) (2021)
- [Group R-CNN for Weakly Semi-supervised Object Detection with Points](https://mlsanity.com/paper/2205.05920/) (2022)
- [Object Instance Mining for Weakly Supervised Object Detection](https://mlsanity.com/paper/2002.01087/) (2020)

## Built on by (most cited first, 11 of 11)

- [Mapping Degeneration Meets Label Evolution: Learning Infrared Small Target Detection with Single Point Supervision](https://mlsanity.com/paper/2304.01484/) (2023)
- [BoxTeacher: Exploring High-Quality Pseudo Labels for Weakly Supervised Instance Segmentation](https://mlsanity.com/paper/2210.05174/) (2022)
- [Weakly Semi-Supervised Detection in Lung Ultrasound Videos](https://mlsanity.com/paper/2308.04463/) (2023)
- [POLO -- Point-based, multi-class animal detection](https://mlsanity.com/paper/2410.11741/) (2024)
- [Point-DETR3D: Leveraging Imagery Data with Spatial Point Prior for Weakly Semi-supervised 3D Object Detection](https://mlsanity.com/paper/2403.15317/) (2024)
- [Boosting Medical Image-based Cancer Detection via Text-guided Supervision from Reports](https://mlsanity.com/paper/2405.14230/) (2024)
- [A Point-Neighborhood Learning Framework for Nasal Endoscope Image Segmentation](https://mlsanity.com/paper/2405.20044/) (2024)
- [Sparse Generation: Making Pseudo Labels Sparse for Point Weakly Supervised Object Detection on Low Data Volume](https://mlsanity.com/paper/2403.19306/) (2024)
- [Detecting Endangered Marine Species in Autonomous Underwater Vehicle Imagery Using Point Annotations and Few-Shot Learning](https://mlsanity.com/paper/2406.01932/) (2024)
- [UAVDB: Point-Guided Masks for UAV Detection and Segmentation](https://mlsanity.com/paper/2409.06490/) (2024)
- [Overhead Wildlife Locator (OWL): Benchmarking Weakly Supervised Learning for Aerial Wildlife Surveys](https://mlsanity.com/paper/2606.13911/) (2026)

## 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.