# FCOS: A simple and strong anchor-free object detector

arXiv: https://arxiv.org/abs/2006.09214 · HTML: https://mlsanity.com/paper/2006.09214/

## Key facts

- Cited by 171 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 14 Jun 2020.

## Built on by (most cited first, 30 of 171)

- [YOLOv7: Trainable bag-of-freebies sets new state-of-the-art for real-time object detectors](https://mlsanity.com/paper/2207.02696/) (2022)
- [YOLOv10: Real-Time End-to-End Object Detection](https://mlsanity.com/paper/2405.14458/) (2024)
- [YOLOv9: Learning What You Want to Learn Using Programmable Gradient Information](https://mlsanity.com/paper/2402.13616/) (2024)
- [Instances as Queries](https://mlsanity.com/paper/2105.01928/) (2021)
- [Probabilistic two-stage detection](https://mlsanity.com/paper/2103.07461/) (2021)
- [Transformer-Based Visual Segmentation: A Survey](https://mlsanity.com/paper/2304.09854/) (2023)
- [Towards Large-Scale Small Object Detection: Survey and Benchmarks](https://mlsanity.com/paper/2207.14096/) (2022)
- [VinVL: Revisiting Visual Representations in Vision-Language Models](https://mlsanity.com/paper/2101.00529/) (2021)
- [ResT: An Efficient Transformer for Visual Recognition](https://mlsanity.com/paper/2105.13677/) (2021)
- [MTP: Advancing Remote Sensing Foundation Model via Multi-Task Pretraining](https://mlsanity.com/paper/2403.13430/) (2024)
- [Radar-Camera Fusion for Object Detection and Semantic Segmentation in Autonomous Driving: A Comprehensive Review](https://mlsanity.com/paper/2304.10410/) (2023)
- [Temporally Efficient Vision Transformer for Video Instance Segmentation](https://mlsanity.com/paper/2204.08412/) (2022)
- [Dynamic Coarse-to-Fine Learning for Oriented Tiny Object Detection](https://mlsanity.com/paper/2304.08876/) (2023)
- [Neural Network Diffusion](https://mlsanity.com/paper/2402.13144/) (2024)
- [Overcoming Data Scarcity in Biomedical Imaging with a Foundational Multi-Task Model](https://mlsanity.com/paper/2311.09847/) (2023)
- [Ultra Fast Deep Lane Detection with Hybrid Anchor Driven Ordinal Classification](https://mlsanity.com/paper/2206.07389/) (2022)
- [FastInst: A Simple Query-Based Model for Real-Time Instance Segmentation](https://mlsanity.com/paper/2303.08594/) (2023)
- [Progressive End-to-End Object Detection in Crowded Scenes](https://mlsanity.com/paper/2203.07669/) (2022)
- [STAR: A First-Ever Dataset and A Large-Scale Benchmark for Scene Graph Generation in Large-Size Satellite Imagery](https://mlsanity.com/paper/2406.09410/) (2024)
- [Wise-IoU: Bounding Box Regression Loss with Dynamic Focusing Mechanism](https://mlsanity.com/paper/2301.10051/) (2023)
- [Continual Object Detection: A review of definitions, strategies, and challenges](https://mlsanity.com/paper/2205.15445/) (2022)
- [Instance Shadow Detection with A Single-Stage Detector](https://mlsanity.com/paper/2207.04614/) (2022)
- [ACDC: The Adverse Conditions Dataset with Correspondences for Robust Semantic Driving Scene Perception](https://mlsanity.com/paper/2104.13395/) (2021)
- [The State of Aerial Surveillance: A Survey](https://mlsanity.com/paper/2201.03080/) (2022)
- [Plane Geometry Diagram Parsing](https://mlsanity.com/paper/2205.09363/) (2022)
- [Are NeRFs ready for autonomous driving? Towards closing the real-to-simulation gap](https://mlsanity.com/paper/2403.16092/) (2024)
- [Interpreting Object-level Foundation Models via Visual Precision Search](https://mlsanity.com/paper/2411.16198/) (2024)
- [Instance and Panoptic Segmentation Using Conditional Convolutions](https://mlsanity.com/paper/2102.03026/) (2021)
- [Cascade-DETR: Delving into High-Quality Universal Object Detection](https://mlsanity.com/paper/2307.11035/) (2023)
- [Deep Learning Technique for Human Parsing: A Survey and Outlook](https://mlsanity.com/paper/2301.00394/) (2023)

## Abstract (arXiv)

In computer vision, object detection is one of most important tasks, which underpins a few instance-level recognition tasks and many downstream applications. Recently one-stage methods have gained much attention over two-stage approaches due to their simpler design and competitive performance. Here we propose a fully convolutional one-stage object detector (FCOS) to solve object detection in a per-pixel prediction fashion, analogue to other dense prediction problems such as semantic segmentation. Almost all state-of-the-art object detectors such as RetinaNet, SSD, YOLOv3, and Faster R-CNN rely on pre-defined anchor boxes. In contrast, our proposed detector FCOS is anchor box free, as well as proposal free. By eliminating the pre-defined set of anchor boxes, FCOS completely avoids the complicated computation related to anchor boxes such as calculating the intersection over union (IoU) scores during training. More importantly, we also avoid all hyper-parameters related to anchor boxes, which are often sensitive to the final detection performance. With the only post-processing non-maximum suppression (NMS), we demonstrate a much simpler and flexible detection framework achieving improved detection accuracy. We hope that the proposed FCOS framework can serve as a simple and strong alternative for many other instance-level tasks. Code and pre-trained models are available at: https://git.io/AdelaiDet