# Tackling the Background Bias in Sparse Object Detection via Cropped Windows

arXiv: https://arxiv.org/abs/2106.02288 · HTML: https://mlsanity.com/paper/2106.02288/

## Key facts

- Cited by 5 papers in the map (data through 14 Oct 2026).
- Builds on 24 of its 33 references that are in the map.
- First posted on arXiv 4 Jun 2021.

## Builds on (most cited first, 24 of 24)

- [Deep Residual Learning for Image Recognition](https://mlsanity.com/paper/1512.03385/) (2015)
- [Adam: A Method for Stochastic Optimization](https://mlsanity.com/paper/1412.6980/) (2014)
- [Faster R-CNN: Towards Real-Time Object Detection with Region Proposal Networks](https://mlsanity.com/paper/1506.01497/) (2015)
- [Fast R-CNN](https://mlsanity.com/paper/1504.08083/) (2015)
- [CutMix: Regularization Strategy to Train Strong Classifiers with Localizable Features](https://mlsanity.com/paper/1905.04899/) (2019)
- [YOLOv4: Optimal Speed and Accuracy of Object Detection](https://mlsanity.com/paper/2004.10934/) (2020)
- [Objects as Points](https://mlsanity.com/paper/1904.07850/) (2019)
- [EfficientNetV2: Smaller Models and Faster Training](https://mlsanity.com/paper/2104.00298/) (2021)
- [EfficientDet: Scalable and Efficient Object Detection](https://mlsanity.com/paper/1911.09070/) (2019)
- [Stacked Hourglass Networks for Human Pose Estimation](https://mlsanity.com/paper/1603.06937/) (2016)
- [CenterNet: Keypoint Triplets for Object Detection](https://mlsanity.com/paper/1904.08189/) (2019)
- [DOTA: A Large-scale Dataset for Object Detection in Aerial Images](https://mlsanity.com/paper/1711.10398/) (2017)
- [Network In Network](https://mlsanity.com/paper/1312.4400/) (2013)
- [Object Detection in Aerial Images: A Large-Scale Benchmark and Challenges](https://mlsanity.com/paper/2102.12219/) (2021)
- [TIDE: A General Toolbox for Identifying Object Detection Errors](https://mlsanity.com/paper/2008.08115/) (2020)
- [Data Augmentation using Random Image Cropping and Patching for Deep CNNs](https://mlsanity.com/paper/1811.09030/) (2018)
- [Augmentation for small object detection](https://mlsanity.com/paper/1902.07296/) (2019)
- [SeaDronesSee: A Maritime Benchmark for Detecting Humans in Open Water](https://mlsanity.com/paper/2105.01922/) (2021)
- [Pelee: A Real-Time Object Detection System on Mobile Devices](https://mlsanity.com/paper/1804.06882/) (2018)
- [AutoFocus: Efficient Multi-Scale Inference](https://mlsanity.com/paper/1812.01600/) (2018)
- [Fixing the train-test resolution discrepancy: FixEfficientNet](https://mlsanity.com/paper/2003.08237/) (2020)
- [Measuring the Ripeness of Fruit with Hyperspectral Imaging and Deep Learning](https://mlsanity.com/paper/2104.09808/) (2021)
- [PENet: Object Detection using Points Estimation in Aerial Images](https://mlsanity.com/paper/2001.08247/) (2020)
- [Object detection on aerial imagery using CenterNet](https://mlsanity.com/paper/1908.08244/) (2019)

## Built on by (most cited first, 5 of 5)

- [Transformers in Small Object Detection: A Benchmark and Survey of State-of-the-Art](https://mlsanity.com/paper/2309.04902/) (2023)
- [A Guide to Image and Video based Small Object Detection using Deep Learning : Case Study of Maritime Surveillance](https://mlsanity.com/paper/2207.12926/) (2022)
- [Self-Supervised Visual Representation Learning via Residual Momentum](https://mlsanity.com/paper/2211.09861/) (2022)
- [Comprehensive Analysis of the Object Detection Pipeline on UAVs](https://mlsanity.com/paper/2203.00306/) (2022)
- [Deployment Prior Injection for Run-time Calibratable Object Detection](https://mlsanity.com/paper/2402.17207/) (2024)

## Abstract (arXiv)

Object detection on Unmanned Aerial Vehicles (UAVs) is still a challenging task. The recordings are mostly sparse and contain only small objects. In this work, we propose a simple tiling method that improves the detection capability in the remote sensing case without modifying the model itself. By reducing the background bias and enabling the usage of higher image resolutions during training, our method can improve the performance of models substantially. The procedure was validated on three different data sets and outperformed similar approaches in performance and speed.