# Weakly-semi-supervised object detection in remotely sensed imagery

arXiv: https://arxiv.org/abs/2311.17449 · HTML: https://mlsanity.com/paper/2311.17449/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- Builds on 22 of its 35 references that are in the map.
- First posted on arXiv 29 Nov 2023.

## Builds on (most cited first, 22 of 22)

- [Deep Residual Learning for Image Recognition](https://mlsanity.com/paper/1512.03385/) (2015)
- [Feature Pyramid Networks for Object Detection](https://mlsanity.com/paper/1612.03144/) (2016)
- [What's the Point: Semantic Segmentation with Point Supervision](https://mlsanity.com/paper/1506.02106/) (2015)
- [A Simple Semi-Supervised Learning Framework for Object Detection](https://mlsanity.com/paper/2005.04757/) (2020)
- [Tackling Climate Change with Machine Learning](https://mlsanity.com/paper/1906.05433/) (2019)
- [Weakly Supervised Deep Detection Networks](https://mlsanity.com/paper/1511.02853/) (2015)
- [FAIR1M: A Benchmark Dataset for Fine-grained Object Recognition in High-Resolution Remote Sensing Imagery](https://mlsanity.com/paper/2103.05569/) (2021)
- [Deep learning in remote sensing: a review](https://mlsanity.com/paper/1710.03959/) (2017)
- [Instant-Teaching: An End-to-End Semi-Supervised Object Detection Framework](https://mlsanity.com/paper/2103.11402/) (2021)
- [Deep Unsupervised Domain Adaptation: A Review of Recent Advances and Perspectives](https://mlsanity.com/paper/2208.07422/) (2022)
- [PCL: Proposal Cluster Learning for Weakly Supervised Object Detection](https://mlsanity.com/paper/1807.03342/) (2018)
- [A Survey on Object Detection in Optical Remote Sensing Images](https://mlsanity.com/paper/1603.06201/) (2016)
- [C-MIL: Continuation Multiple Instance Learning for Weakly Supervised Object Detection](https://mlsanity.com/paper/1904.05647/) (2019)
- [Using satellite imagery to understand and promote sustainable development](https://mlsanity.com/paper/2010.06988/) (2020)
- [Recent Advances in Domain Adaptation for the Classification of Remote Sensing Data](https://mlsanity.com/paper/2104.07778/) (2021)
- [Points as Queries: Weakly Semi-supervised Object Detection by Points](https://mlsanity.com/paper/2104.07434/) (2021)
- [Weakly Supervised Learning with Side Information for Noisy Labeled Images](https://mlsanity.com/paper/2008.11586/) (2020)
- [Weakly Supervised Object Detection with Segmentation Collaboration](https://mlsanity.com/paper/1904.00551/) (2019)
- [UFO2: A Unified Framework towards Omni-supervised Object Detection](https://mlsanity.com/paper/2010.10804/) (2020)
- [Group R-CNN for Weakly Semi-supervised Object Detection with Points](https://mlsanity.com/paper/2205.05920/) (2022)
- [Weakly Supervised Vessel Segmentation in X-ray Angiograms by Self-Paced Learning from Noisy Labels with Suggestive Annotation](https://mlsanity.com/paper/2005.13366/) (2020)
- [Weakly- and Semi-Supervised Object Detection with Expectation-Maximization Algorithm](https://mlsanity.com/paper/1702.08740/) (2017)

## Built on by (most cited first, 1 of 1)

- [Boosting Medical Image-based Cancer Detection via Text-guided Supervision from Reports](https://mlsanity.com/paper/2405.14230/) (2024)

## Abstract (arXiv)

Deep learning for detecting objects in remotely sensed imagery can enable new technologies for important applications including mitigating climate change. However, these models often require large datasets labeled with bounding box annotations which are expensive to curate, prohibiting the development of models for new tasks and geographies. To address this challenge, we develop weakly-semi-supervised object detection (WSSOD) models on remotely sensed imagery which can leverage a small amount of bounding boxes together with a large amount of point labels that are easy to acquire at scale in geospatial data. We train WSSOD models which use large amounts of point-labeled images with varying fractions of bounding box labeled images in FAIR1M and a wind turbine detection dataset, and demonstrate that they substantially outperform fully supervised models trained with the same amount of bounding box labeled images on both datasets. Furthermore, we find that the WSSOD models trained with 2-10x fewer bounding box labeled images can perform similarly to or outperform fully supervised models trained on the full set of bounding-box labeled images. We believe that the approach can be extended to other remote sensing tasks to reduce reliance on bounding box labels and increase development of models for impactful applications.