# FCOSR: A Simple Anchor-free Rotated Detector for Aerial Object Detection

arXiv: https://arxiv.org/abs/2111.10780 · HTML: https://mlsanity.com/paper/2111.10780/

## Key facts

- Cited by 10 papers in the map (data through 14 Oct 2026).
- Builds on 37 of its 47 references that are in the map.
- First posted on arXiv 21 Nov 2021.

## Builds on (most cited first, 30 of 37)

- [Faster R-CNN: Towards Real-Time Object Detection with Region Proposal Networks](https://mlsanity.com/paper/1506.01497/) (2015)
- [Mask R-CNN](https://mlsanity.com/paper/1703.06870/) (2017)
- [Feature Pyramid Networks for Object Detection](https://mlsanity.com/paper/1612.03144/) (2016)
- [You Only Look Once: Unified, Real-Time Object Detection](https://mlsanity.com/paper/1506.02640/) (2015)
- [MobileNetV2: Inverted Residuals and Linear Bottlenecks](https://mlsanity.com/paper/1801.04381/) (2018)
- [Fast R-CNN](https://mlsanity.com/paper/1504.08083/) (2015)
- [YOLOv3: An Incremental Improvement](https://mlsanity.com/paper/1804.02767/) (2018)
- [Aggregated Residual Transformations for Deep Neural Networks](https://mlsanity.com/paper/1611.05431/) (2016)
- [Rich feature hierarchies for accurate object detection and semantic segmentation](https://mlsanity.com/paper/1311.2524/) (2013)
- [FCOS: Fully Convolutional One-Stage Object Detection](https://mlsanity.com/paper/1904.01355/) (2019)
- [Deformable Convolutional Networks](https://mlsanity.com/paper/1703.06211/) (2017)
- [MMDetection: Open MMLab Detection Toolbox and Benchmark](https://mlsanity.com/paper/1906.07155/) (2019)
- [Objects as Points](https://mlsanity.com/paper/1904.07850/) (2019)
- [YOLOX: Exceeding YOLO Series in 2021](https://mlsanity.com/paper/2107.08430/) (2021)
- [Fast and Accurate Deep Network Learning by Exponential Linear Units (ELUs)](https://mlsanity.com/paper/1511.07289/) (2015)
- [Focal Loss for Dense Object Detection](https://mlsanity.com/paper/1708.02002/) (2017)
- [DOTA: A Large-scale Dataset for Object Detection in Aerial Images](https://mlsanity.com/paper/1711.10398/) (2017)
- [General E(2)-Equivariant Steerable CNNs](https://mlsanity.com/paper/1911.08251/) (2019)
- [Generalized Focal Loss: Learning Qualified and Distributed Bounding Boxes for Dense Object Detection](https://mlsanity.com/paper/2006.04388/) (2020)
- [Oriented R-CNN for Object Detection](https://mlsanity.com/paper/2108.05699/) (2021)
- [ReDet: A Rotation-equivariant Detector for Aerial Object Detection](https://mlsanity.com/paper/2103.07733/) (2021)
- [R3Det: Refined Single-Stage Detector with Feature Refinement for Rotating Object](https://mlsanity.com/paper/1908.05612/) (2019)
- [Align Deep Features for Oriented Object Detection](https://mlsanity.com/paper/2008.09397/) (2020)
- [Arbitrary-Oriented Scene Text Detection via Rotation Proposals](https://mlsanity.com/paper/1703.01086/) (2017)
- [FCOS: A simple and strong anchor-free object detector](https://mlsanity.com/paper/2006.09214/) (2020)
- [Rethinking Rotated Object Detection with Gaussian Wasserstein Distance Loss](https://mlsanity.com/paper/2101.11952/) (2021)
- [Learning High-Precision Bounding Box for Rotated Object Detection via Kullback-Leibler Divergence](https://mlsanity.com/paper/2106.01883/) (2021)
- [Dense Label Encoding for Boundary Discontinuity Free Rotation Detection](https://mlsanity.com/paper/2011.09670/) (2020)
- [Dynamic Refinement Network for Oriented and Densely Packed Object Detection](https://mlsanity.com/paper/2005.09973/) (2020)
- [Oriented Object Detection in Aerial Images with Box Boundary-Aware Vectors](https://mlsanity.com/paper/2008.07043/) (2020)

## Built on by (most cited first, 10 of 10)

- [The KFIoU Loss for Rotated Object Detection](https://mlsanity.com/paper/2201.12558/) (2022)
- [AO2-DETR: Arbitrary-Oriented Object Detection Transformer](https://mlsanity.com/paper/2205.12785/) (2022)
- [Dynamic Coarse-to-Fine Learning for Oriented Tiny Object Detection](https://mlsanity.com/paper/2304.08876/) (2023)
- [PP-YOLOE-R: An Efficient Anchor-Free Rotated Object Detector](https://mlsanity.com/paper/2211.02386/) (2022)
- [Oriented Tiny Object Detection: A Dataset, Benchmark, and Dynamic Unbiased Learning](https://mlsanity.com/paper/2412.11582/) (2024)
- [LanePtrNet: Revisiting Lane Detection as Point Voting and Grouping on Curves](https://mlsanity.com/paper/2403.05155/) (2024)
- [Rethinking Scale Imbalance in Semi-supervised Object Detection for Aerial Images](https://mlsanity.com/paper/2310.14718/) (2023)
- [Structure Tensor Representation for Robust Oriented Object Detection](https://mlsanity.com/paper/2411.10497/) (2024)
- [Boundary and Position Information Mining for Aerial Small Object Detection](https://mlsanity.com/paper/2601.16617/) (2026)
- [DTKDP: A Dual Teacher Knowledge Distillation and Pruning Framework for Lightweight Oriented SAR Ship Detection](https://mlsanity.com/paper/2609.24872/) (2026)

## Abstract (arXiv)

Existing anchor-base oriented object detection methods have achieved amazing results, but these methods require some manual preset boxes, which introduces additional hyperparameters and calculations. The existing anchor-free methods usually have complex architectures and are not easy to deploy. Our goal is to propose an algorithm which is simple and easy-to-deploy for aerial image detection. In this paper, we present a one-stage anchor-free rotated object detector (FCOSR) based on FCOS, which can be deployed on most platforms. The FCOSR has a simple architecture consisting of only convolution layers. Our work focuses on the label assignment strategy for the training phase. We use ellipse center sampling method to define a suitable sampling region for oriented bounding box (OBB). The fuzzy sample assignment strategy provides reasonable labels for overlapping objects. To solve the insufficient sampling problem, a multi-level sampling module is designed. These strategies allocate more appropriate labels to training samples. Our algorithm achieves 79.25, 75.41, and 90.15 mAP on DOTA1.0, DOTA1.5, and HRSC2016 datasets, respectively. FCOSR demonstrates superior performance to other methods in single-scale evaluation. We convert a lightweight FCOSR model to TensorRT format, which achieves 73.93 mAP on DOTA1.0 at a speed of 10.68 FPS on Jetson Xavier NX with single scale. The code is available at: https://github.com/lzh420202/FCOSR