mlsanityData to 7 Oct 2026

Centerpoints Are All You Need in Overhead Imagery

arXiv 2210.01857 ↗First posted 4 Oct 2022cs.CV cs.AIcited by 2

Not on the map. Why?

Abstract (arXiv)

Labeling data to use for training object detectors is expensive and time consuming. Publicly available overhead datasets for object detection are labeled with image-aligned bounding boxes, object-aligned bounding boxes, or object masks, but it is not clear whether such detailed labeling is necessary. To test the idea, we developed novel single- and two-stage network architectures that use centerpoints for labeling. In this paper we show that these architectures achieve nearly equivalent performance to approaches using more detailed labeling on three overhead object detection datasets.

Key facts. Cited by 2 papers in the map (data through 7 Oct 2026). Builds on 24 of its 37 references that are in the map. First posted on arXiv 4 Oct 2022.

Builds on

24 of 37 references.

References · 24

  1. 2015Deep Residual Learning for Image Recognitioncited by 51,809
  2. 2014Microsoft COCO: Common Objects in Contextcited by 17,498
  3. 2017Mask R-CNNcited by 7,259
  4. 2019CenterNet: Keypoint Triplets for Object Detectioncited by 654
  5. 2019Generalizing from a Few Examples: A Survey on Few-Shot Learningcited by 462
  6. 2019Object Detection in Optical Remote Sensing Images: A Survey and A New Benchmarkcited by 339
  7. 2015What's the Point: Semantic Segmentation with Point Supervisioncited by 297
  8. 2021Object Detection in Aerial Images: A Large-Scale Benchmark and Challengescited by 202
  9. 2019iSAID: A Large-scale Dataset for Instance Segmentation in Aerial Imagescited by 195
  10. 2017Arbitrary-Oriented Scene Text Detection via Rotation Proposalscited by 176
  11. 2021Self-Supervised Representation Learning: Introduction, Advances and Challengescited by 147
  12. 2021FAIR1M: A Benchmark Dataset for Fine-grained Object Recognition in High-Resolution Remote Sensing Imagerycited by 143
12 more
  1. 2016A Large Contextual Dataset for Classification, Detection and Counting of Cars with Deep Learningcited by 86
  2. 2021Weakly Supervised Object Localization and Detection: A Surveycited by 84
  3. 2020RarePlanes: Synthetic Data Takes Flightcited by 48
  4. 2021Knowledge-aware Zero-Shot Learning: Survey and Perspectivecited by 41
  5. 2018Learning RoI Transformer for Detecting Oriented Objects in Aerial Imagescited by 37
  6. 2020Active Learning: Problem Settings and Recent Developmentscited by 23
  7. 2020The Synthinel-1 dataset: a collection of high resolution synthetic overhead imagery for building segmentationcited by 19
  8. 2021SyntEO: Synthetic Data Set Generation for Earth Observation and Deep Learning -- Demonstrated for Offshore Wind Farm Detectioncited by 6
  9. 2019Deep Built-Structure Counting in Satellite Imagery Using Attention Based Re-Weightingcited by 5
  10. 2021SIMPL: Generating Synthetic Overhead Imagery to Address Zero-shot and Few-Shot Detection Problemscited by 4
  11. 2021Cross-Region Building Counting in Satellite Imagery using Counting Consistencycited by 2
  12. 2021Disaster mapping from satellites: damage detection with crowdsourced point labelscited by 2

Built on by

Cited by year

Citing papers per year: 2023: 2.

2 papers.

  1. 2023Enabling Decision-Support Systems through Automated Cell Tower Detectioncited by 1
  2. 2023Impact of Label Types on Training SWIN Models with Overhead Imagerycited by 0