FCOS: A simple and strong anchor-free object detector

TL;DR

FCOS introduces an anchor-free, fully convolutional one-stage object detector that simplifies the detection process, reduces hyper-parameters, and achieves competitive accuracy compared to anchor-based methods.

Contribution

The paper presents FCOS, a novel anchor-free, proposal-free object detection framework that simplifies training and improves accuracy over traditional anchor-based detectors.

Findings

Achieves state-of-the-art detection accuracy without anchor boxes.

Simplifies the detection pipeline by removing anchor-related hyper-parameters.

Demonstrates competitive performance with fewer design complexities.

Abstract

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